KR20210155381A - System for verifying testing with online-based artificial intelligence and operating method thereof - Google Patents

Abstract

A system for verifying an online-based test with artificial intelligence according to an embodiment of the present invention includes: a test terminal which photographs a user's surrounding information and facial information during a test time to provide the same after accessing a website based on the user's application number and biometric information; and an AI test verification server which determines whether cheating on the test is conducted, based on surrounding image information, face image information, and dynamic memory/network traffic change amount transmitted from the test terminal.

Description

Online artificial intelligence test verification system and its operating method {System for verifying testing with online-based artificial intelligence and operating method thereof}

The present invention relates to an online artificial intelligence test verification system and an operating method thereof.

Due to the increasing number of online education and evaluation users due to convenience or distance, advanced evaluation fairness is required. Various methods have been proposed to secure the fairness and reliability of the test. [0003] Current questioners (especially cyber colleges) disable or enable the use of function keys during online evaluation, a method of recording the use of function keys, and a warning action or fraudulent action against attempts to use other programs through a function key usage detection function As a way to secure data to be considered as a 'Corruption', it is passively responding to expected misconduct by continuously changing the testing system and evaluation method. [0004] Techniques using fingerprint recognition or iris recognition technology to confirm identity have also been proposed. However, although fingerprint recognition or iris recognition technology is already quite advanced, it is difficult for the examinee to have a separate fingerprint or iris recognition device, so it is insufficient technology to be applied in the online test, which has the advantage of remoteness.

Meanwhile, Korean Patent Registration No. 10-1499769 (Application No. 10-2009-0038799) discloses a method for securing the authenticity of online evaluation test takers using a webcam. It discloses a method that can detect cheating by registering a test taker's digital image at the time of course registration for online education or at the beginning of the semester and using it as a reference image for future judgments to check the face during the test. .

Meanwhile, Korean Patent Laid-Open Patent Publication 10-2007-0050029 (Application No. 10-2007-0039984) discloses contents applied to online education attendance authentication and testing using still cuts using a camera connected to a terminal.

In addition, in the Republic of Korea Patent Registration 10-0478157 (Application No. 10-1998-0709046), the server of the test evaluator in real time using the video and sound data of the test subject using an expensive device that combines a microphone, a camera, and fingerprint recognition A control method was proposed. If there is a reason for disqualification during the exam, the exam will be stopped immediately, and there is a lot of room for controversy in the future. In addition, in order to discover the reason for disqualification in real time, the test manager must always observe the test management status, but when the number of people increases, it is difficult to apply.

In other words, several methods have been proposed to verify the identity of the person taking the online test so far. However, there was no way to detect or limit cheating, such as when test takers search for answers or teach others the answers to questions submitted online, while taking the online test, so the fairness of the online test could not be properly established. .

Korean Patent Registration 10-1499769 (Registration Date: 2015.03.02) Korean Patent Laid-Open Patent Publication 10-2007-0050029 (Published date: 2007. 05. 14) Korean Patent Registration 10-0478157 (Registration Date: March 11, 2005) Korean Patent Laid-Open Patent Publication 10-2002-0010949 (Published date: 2002.02.07)

An object to be solved by the present invention is to provide an online artificial intelligence test verification system capable of solving conventional problems and an operating method thereof.

The online artificial intelligence test verification system according to an embodiment of the present invention for solving the above problems connects to a website based on the user's application number and biometric information, and then captures the user's surrounding information and facial information during the test time A test terminal provided by: and an AI test verification server that determines whether a test is cheating based on the surrounding image information, face image information, and dynamic memory/network traffic volume transmitted from the test terminal.

In one embodiment, the test terminal is a display unit for displaying the test questions of the test website website; an input unit having a fingerprint sensor for sensing the examinee's fingerprint information; an image collection unit that captures and collects a user's face image and surrounding images; and the display unit is characterized in that when the fingerprint sensor is deactivated, the display operation is deactivated.

In one embodiment, the test terminal is characterized in that it transmits the dynamic memory and traffic information of the network during the test time in real time.

In one embodiment, the AI test verification server is characterized in that it confirms the user's self-authentication based on the fingerprint information and the examination number input from the test terminal.

In one embodiment, the AI test verification server is characterized in that it tracks the movement of the facial contour and the movement of the pupil region (coordinates) in the face image transmitted from the test terminal during the online test time.

In one embodiment, the AI test verification server is characterized in that it monitors the amount of traffic change of the dynamic memory and the network transmitted from the test terminal during the online test time.

In one embodiment, the AI test verification server is characterized in that it determines the existence of an object corresponding to the face image in the surrounding image transmitted from the test terminal.

In one embodiment, the AI test verification server sets, as a reference (ref), the face image and the surrounding image of the examinee who gazed at the preset display point before the test, and when the test is conducted, based on the set reference, the test taker It is characterized by calculating the amount of dynamic change in the facial contour region and the pupil region.

In one embodiment, the AI test verification server is characterized in that, when the online test starts, the dynamic movement of the pupil region and the facial contour region according to the mouse cursor position of the examinee is tracked.

In one embodiment, the AI test verification server counts the number of times each of the amount of change in the dynamic movement of the pupil region and the face contour region and the amount of traffic change exceeds the reference value, and then the sum of the accumulated count values exceeds the reference value, It is characterized in that the examinee is judged as a cheater.

In an embodiment, the AI test verification server calculates the sum of the counts by adding a relative weight to the amount of change in the movement of the image object (pupil region and facial contour region) and the traffic change.

The operation method of the artificial intelligence online test verification system according to an embodiment of the present invention for solving the above problems includes the steps of confirming the identity of the examinee in the AI test verification server based on the examination information and fingerprint information input from the test terminal ; if the identity verification is confirmed, approving the test terminal access to the test website; accessing the test website from the test terminal; transmitting the face image and the surrounding image of the examinee who gazed at the preset display point in the test terminal to the AI test verification server; transmitting the dynamic memory and network traffic amount from the test terminal to the AI test verification server; checking the facial contour and pupil coordinates of the examinee who gazed at a preset display point in the AI test verification server; When the online test starts, the dynamic movement of the pupil region and facial contour region according to the mouse cursor position of the examinee is tracked, and after analyzing the dynamic memory of the test terminal and the amount of traffic change in the network, the movement of pupil/face contour coordinates comparing the change amount and the traffic change amount with reference values, respectively; counting the number of times each of the movement change amount and the traffic change amount of the pupil/face contour coordinates exceeds a reference value; and when the sum of the cumulative count values for the amount of change in motion of the pupil/face contour coordinates and the amount of change in traffic exceeds a reference value, blocking access to the test question website.

According to the present invention, by using the user's fingerprint and image information, there is an advantage that a reliable and fair online test can be conducted by detecting and notifying an act suspected of cheating by the examinee.

In addition, several supervisors were required to supervise multiple examinees taking the computer-based test (CBT) in one classroom at a time. Since one examinee's exam is stopped, there is no need for multiple supervisors.

Furthermore, there is an advantage that the online test can be conducted fairly and conveniently at home even during a time when a mass infectious disease is spreading like COVID-19.

The purpose of the embodiments of the present invention is not limited to the above-mentioned purpose, and other objects not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description. .

1 is a network configuration diagram of an online test verification system according to an embodiment of the present invention.
FIG. 2 is a configuration diagram of the test terminal shown in FIG. 1 .
3 is a block diagram showing the detailed configuration of the AI test verification server shown in FIG.
4 is a flowchart illustrating an operating method of an online test verification system according to an embodiment of the present invention.
5 illustrates an example computing environment in which one or more embodiments disclosed herein may be implemented.

It should be noted that the technical terms used in the present invention are only used to describe specific embodiments, and are not intended to limit the present invention. In addition, the technical terms used in the present invention should be interpreted as meanings generally understood by those of ordinary skill in the art to which the present invention belongs, unless otherwise specifically defined in the present invention, and excessively comprehensive It should not be construed in the meaning of a human being or in an excessively reduced meaning. In addition, when the technical term used in the present invention is an incorrect technical term that does not accurately express the spirit of the present invention, it should be understood by being replaced with a technical term that can be correctly understood by those skilled in the art. In addition, the general terms used in the present invention should be interpreted according to the definition in the dictionary or according to the context before and after, and should not be interpreted in an excessively reduced meaning.

Also, the singular expression used in the present invention includes the plural expression unless the context clearly dictates otherwise. In the present invention, terms such as “consisting of” or “comprising” should not be construed as necessarily including all of the various components or various steps described in the invention, and some components or some steps may not be included. It should be construed that it may further include additional components or steps.

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

Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in the description of the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, it should be noted that the accompanying drawings are only for easy understanding of the spirit of the present invention, and should not be construed as limiting the spirit of the present invention by the accompanying drawings.

Hereinafter, an artificial intelligence online test verification system according to an embodiment of the present invention will be described in more detail based on the accompanying drawings.

1 is a network configuration diagram of an artificial intelligence online test verification system according to an embodiment of the present invention, FIG. 2 is a configuration diagram of the test terminal shown in FIG. 1, and FIG. 3 is the AI test verification server shown in FIG. It is a block diagram showing the detailed configuration of

As shown in FIG. 1 , the artificial intelligence online test verification system 10 according to an embodiment of the present invention includes a test terminal 200 and an AI test verification server 300 .

The test terminal 200 and the AI test verification server 300 are connected through a network.

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers. Examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, Long Term Evolution (LTE). ) network, 5rd Generation Partnership Project (5GPP) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. include, but are not limited thereto.

In the following, the term at least one is defined as a term including the singular and the plural, and even if the at least one term does not exist, each element may exist in the singular or plural, and may mean the singular or plural. it will be self-evident In addition, that each component is provided in singular or plural may be changed according to embodiments.

The test terminal 200 may be a terminal that accesses a preset website that provides online test questions based on the test number and test taker authentication information.

The test terminal 200 may be a terminal that provides the examinee's face image, surrounding image, and dynamic memory/network traffic information to the AI test verification server 300 to be described later during the test time.

The test terminal 200 includes a display unit for displaying the test questions of the test preparation website, an input unit having a fingerprint sensor for sensing the examinee's fingerprint information, and an image collecting unit for capturing and collecting the user's face image and surrounding images. The display unit may be configured such that, when the fingerprint sensor is deactivated, the display operation is deactivated.

For reference, the photographing area of the image collecting unit is classified into a peripheral area and an examinee area of the examinee, and objects extracted from the surrounding area and the examinee area act as a means for determining whether or not a negative test is performed.

For example, when objects such as books, people, and video media are extracted from the surrounding area, the tester's test behavior is considered a fraudulent test. can be considered

On the other hand, the test terminal 200 is a terminal running a platform supported by the AI test verification server 300 to be described later, and the platform supports an interface for checking test information, test taker identification information, test taker biometric information, etc. .

In addition, the test terminal 200 provides the traffic amount of the internal dynamic memory and the traffic amount of the network to the AI test verification server 300 in real time during the test time. This may be to block the flow of information between the test terminal 200 and an external device interlocked.

The test terminal 200 is a smartphone (Smart Phone), a portable terminal (Portable Terminal), a mobile terminal (Mobile Terminal), a foldable terminal (Foldable Terminal), a personal digital assistant (PDA), PMP (Portable) Multimedia Player) terminal, telematics terminal, navigation terminal, personal computer, notebook computer, slate PC, tablet PC, ultrabook, wearable device ( Wearable Device, for example, watch-type terminal (Smartwatch), glass-type terminal (Smart Glass), HMD (Head Mounted Display), etc.), Wibro (Wibro) terminal, IPTV (Internet Protocol Television) terminal, smart TV, digital It can be applied to various terminals such as a broadcasting terminal, an AVN (Audio Video Navigation) terminal, an A/V (Audio/Video) system, a flexible terminal, and a digital signage device.

Next, the AI test verification server 300 may be configured to determine whether the test is cheating based on the surrounding image information, the face image information, and the amount of dynamic memory/network traffic transmitted from the test terminal 200 .

More specifically, the AI test verification server 300 includes an input/output unit 310 , an examinee authentication unit 320 , an image object processing unit 330 , a traffic monitoring unit 340 , a fraudulent activity determination unit 350 , and access approval. / Including the blocking portion (360).

The input/output unit 310 may be configured to receive fingerprint information, face image information, and surrounding image information from the test terminal, and to output test taker authentication information and misconduct determination information, which will be described later, to the test terminal.

The test taker authentication unit 320 may be configured to confirm the test taker's identity authentication based on the test taker's fingerprint information and test number input from the test terminal 200 .

The image object processing unit 330 extracts the facial contour region and the pupil region in the face image information transmitted from the test terminal 200, and then tracks the dynamic change (coordinate change) of the facial contour region and the pupil region during the test time. can be

Also, the image object processing unit 330 may determine whether an object corresponding to the face image exists in the surrounding image transmitted from the test terminal 200 .

The image object processing unit 330 sets, as a reference (ref), an image of the examinee's face and surrounding images at which the examinee gazed at a preset display point before the test. It is possible to calculate the amount of dynamic change of the region and the pupil region.

In addition, when the online test starts, the image object processing unit 330 tracks the dynamic movement of the pupil region and the facial contour region according to the position of the examinee's mouse cursor.

In this case, the image object processing unit 330 may receive mouse cursor information of the test terminal from the input/output unit.

Additionally, the image object processing unit 330 employs a deep learning algorithm, and using the deep learning algorithm to extract objects (facial region and pupil region) in the face image and surrounding images of the examinee transmitted from the test terminal. Also, the shape of an external object (person or face) in the surrounding image may be extracted.

The deep learning algorithm may include a Deep Belief Network, Autoencoder, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Deep Q-Network, etc., and the deep learning algorithm listed in the present invention is only an example, The present invention is not limited thereto.

Next, the traffic monitoring unit 340 analyzes the amount of traffic change by comparing the dynamic memory of the test terminal and the amount of network traffic before and during the online test.

Additionally, the traffic monitoring unit 340 recognizes the network traffic state as any one of a congestion state, a normal state, and a smooth state. Here, the traffic state of the network includes at least one parameter among Rx, Tx, Ec/Io, Received Signal Strength Indication (RSSI), transmission rate, and the number of allocated slave terminals, which are parameters included in the radio wave environment signal, as a preset network state threshold. Recognize the network state by comparing it with the value. By comparing the parameter with the network status threshold, if the parameter is less than the network status threshold, the network status is recognized as a smooth status. Recognize the state as a normal state.

In addition, the traffic monitoring unit 340 transmits traffic from a plurality of test terminals to the AI test verification server by using a traffic control program. The individual network status (Physical Layer, RF layer, MAC layer, IP layer, etc.) Layers can be monitored.

If the path network assigned to the test terminal is in a congested state, the corresponding path network may be replaced with another path network.

Next, the misconduct determination unit 350 counts the number of times each of the amount of change in the dynamic movement of the pupil region and the face contour region and the amount of traffic change exceeds the reference value, and then, when the sum of the accumulated count values exceeds the reference value, It may be configured to judge the examinee as a cheater.

Here, the cheating determination unit 350 may calculate the sum of the counts by adding a relative weight to the amount of change in the movement of the image object (the pupil region and the face contour region) and the amount of traffic change.

Next, the access approval/blocking unit 360 may be configured to approve access to the test questioning website of the test terminal based on the test taker authentication confirmation information.

In addition, the access approval/blocking unit 360 may be configured to block access to the test question website based on the determination information of the misconduct determination unit 350 .

4 is a flowchart illustrating an operating method of an artificial intelligence online test verification system according to an embodiment of the present invention.

Referring to FIG. 4 , in the operating method ( S700 ) of the online artificial intelligence test verification system according to an embodiment of the present invention, first, based on the test information and fingerprint information input from the test terminal 200 , the test taker's identity is authenticated. The AI test verification server 300 confirms (S710).

Thereafter, when the test taker's identity verification is confirmed, if the test terminal 200 approves access to the test test website, the test terminal 200 accesses the test test website (S720).

When the test website is accessed, the test terminal transmits the face image and surrounding images of the test taker who took the test at the preset display point to the AI test verification server (S730), and also the dynamic memory and network traffic volume in the test terminal. It is transmitted to the test verification server (S740).

Thereafter, the facial contour and pupil coordinates of the examinee in the face image gazing at the preset display point in the AI test verification server 300 are checked (S750).

Next, when the online test starts, the AI test verification server 300 tracks the movement of the pupil coordinates and face contour coordinates according to the mouse cursor position of the examinee, and also the dynamic memory of the test terminal and the amount of change in the traffic volume of the network After analyzing (S760), the amount of change in motion of pupil/face contour coordinates and the amount of change in traffic are compared with reference values, respectively (S770).

Next, after counting (S780) the number of times each of the amount of change in movement of the pupil/face contour coordinates and the amount of traffic change exceeds the reference value (S780), the cumulative count value for the amount of change in the movement of the pupil/face contour coordinates and the amount of traffic change If the combined value exceeds the standard value, the access to the test preparation website is blocked (S790), and then a message is provided to the test terminal that regards the examinee as a cheater.

Therefore, according to the present invention, by using the examinee's biometric information and surrounding image information, it is possible to monitor whether the examinee has cheated or not, and furthermore, to understand the process of interworking with an external terminal in real time through dynamic memory and network traffic. By doing so, it is possible to eradicate cheating due to external contact for online exams.

5 is a diagram illustrating an example computing environment in which one or more embodiments disclosed herein may be implemented, and is an illustration of a system 1000 including a computing device 1100 configured to implement one or more embodiments described above. shows For example, computing device 1100 may be a personal computer, server computer, handheld or laptop device, mobile device (mobile phone, PDA, media player, etc.), multiprocessor system, consumer electronics, minicomputer, mainframe computer, distributed computing environments including any of the aforementioned systems or devices, and the like.

The computing device 1100 may include at least one processing unit 1110 and a memory 1120 . Here, the processing unit 1110 may include, for example, a central processing unit (CPU), a graphic processing unit (GPU), a microprocessor, an Application Specific Integrated Circuit (ASIC), Field Programmable Gate Arrays (FPGA), etc. and may have a plurality of cores. The memory 1120 may be a volatile memory (eg, RAM, etc.), a non-volatile memory (eg, ROM, flash memory, etc.), or a combination thereof. Additionally, computing device 1100 may include additional storage 1130 . Storage 1130 includes, but is not limited to, magnetic storage, optical storage, and the like. The storage 1130 may store computer readable instructions for implementing one or more embodiments disclosed herein, and other computer readable instructions for implementing an operating system, an application program, and the like. Computer readable instructions stored in storage 1130 may be loaded into memory 1120 for execution by processing unit 1110 . Computing device 1100 may also include input device(s) 1140 and output device(s) 1150 .

Here, the input device(s) 1140 may include, for example, a keyboard, mouse, pen, voice input device, touch input device, infrared camera, video input device, or any other input device, or the like. Further, the output device(s) 1150 may include, for example, one or more displays, speakers, printers, or any other output device, or the like. Also, the computing device 1100 may use an input device or an output device included in another computing device as the input device(s) 1140 or the output device(s) 1150 . Computing device 1100 may also include communication connection(s) 1160 that enable computing device 1100 to communicate with another device (eg, computing device 1300 ).

Here, communication connection(s) 1160 may be a modem, network interface card (NIC), integrated network interface, radio frequency transmitter/receiver, infrared port, USB connection, or other for connecting computing device 1100 to another computing device. It may include interfaces. Also, the communication connection(s) 1160 may include a wired connection or a wireless connection. Each component of the above-described computing device 1100 may be connected by various interconnections such as a bus (eg, peripheral component interconnection (PCI), USB, firmware (IEEE 1394), optical bus structure, etc.) and may be interconnected by a network 1200 . As used herein, terms such as "component," "system," and the like, generally refer to a computer-related entity that is hardware, a combination of hardware and software, software, or software in execution.

For example, a component can be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer. For example, both an application running on a controller and a controller may be a component. One or more components may reside within a process and/or thread of execution, and components may be localized on one computer or distributed between two or more computers.

Those skilled in the art to which the present invention pertains will understand that the present invention may be embodied in other specific forms without changing the technical spirit or essential characteristics thereof. Therefore, the embodiments described above are to be understood as illustrative and not restrictive in all respects, and the scope of the present invention is indicated by the following claims rather than the above detailed description, the meaning and scope of the claims, and All changes or modifications derived from the equivalent concept should be construed as being included in the scope of the present invention.

100: Artificial Intelligence Online Test Verification System
200: test terminal
300: AI test verification server
310: input/output unit
320: examinee authentication unit
330: image object processing unit
340: traffic monitoring unit
350: cheating judgment unit
360: access permission/block

Claims (5)

After accessing the website based on the user's application number and biometric information, the test terminal provides the user's surrounding information and facial information during the test period: and
An online artificial intelligence test validation system comprising an AI test validation server that determines whether a test is cheating based on the surrounding image information, face image information, and dynamic memory/network traffic change amount transmitted from the test terminal. According to claim 1,
The test terminal is
a display unit for displaying the exam questions of the exam preparation website;
an input unit having a fingerprint sensor for sensing the examinee's fingerprint information;
an image collection unit for capturing and collecting a user's face image and surrounding images; and
The display unit artificial intelligence online test verification system, characterized in that the display operation is deactivated when the fingerprint sensor is deactivated. 3. The method of claim 2,
The test terminal is
An artificial intelligence online test verification system, characterized in that the dynamic memory and network traffic information are transmitted in real time during the test time. 4. The method of claim 3,
The AI test verification server is
Verifies the user's identity authentication based on the fingerprint information and the examination number entered in the test terminal,
During the online test time, the movement of the facial contour and the movement change (coordinates) of the pupil region in the facial image transmitted from the test terminal are tracked,
Monitoring the amount of traffic change of the dynamic memory and network transmitted from the test terminal during the online test time,
It is determined whether there is an object corresponding to the face image in the surrounding image transmitted from the test terminal,
Before the test, the test taker sets the face image and the surrounding image of the test taker who gazed at the preset mark as the reference (ref). calculate,
When the online test starts, the dynamic movement of the pupil area and facial contour area according to the mouse cursor position of the examinee is tracked,
After counting the number of times each of the amount of change in dynamic movement and traffic change in the pupil area and facial contour area exceeds the reference value, if the sum of the accumulated count values exceeds the reference value, the examinee is judged as a cheater,
An artificial intelligence online test verification system, characterized in that the sum of the counts is calculated by adding a relative weight to the amount of change in the movement of the image object (pupil region and face contour region) and the amount of traffic change. The AI test verification server confirms the identity of the test taker based on the test information and fingerprint information input from the test terminal;
when the identity verification is confirmed, approving the test terminal access to the test website;
accessing a web site for test questions from the test terminal;
transmitting the face image and the surrounding image of the examinee who gazed at the preset display point in the test terminal to the AI test verification server;
transmitting the dynamic memory and network traffic amount from the test terminal to the AI test verification server;
checking the facial contour and pupil coordinates of the examinee who gazed at a preset display point in the AI test verification server;
When the online test starts, the dynamic movement of the pupil region and the facial contour region according to the mouse cursor position of the examinee is tracked, the dynamic memory of the test terminal and the amount of traffic change in the network are analyzed, and then the pupil/face contour coordinates are moved comparing the change amount and the traffic change amount with reference values, respectively;
counting the number of times each of the movement change amount and the traffic change amount of the pupil/face contour coordinates exceeds a reference value;
When the sum of the cumulative count values for the amount of change in the movement of the pupil/face contour coordinates and the amount of traffic change exceeds the reference value, blocking access to the test question website;
During the test, when an external object is recognized in the surrounding image transmitted from the test terminal, the operation method of the artificial intelligence online test verification system further comprising the step of blocking access to the test preparation website.

Images