Method, program, and apparatus for constructing test environment

Abstract

Disclosed are a method, a program, and an apparatus for constructing a test environment, according to an embodiment of the present disclosure. The method may comprise the steps of: providing a first user interface that induces a test taker to capture a test-taking environment by using a camera; and providing a second user interface that induces the test taker to install the camera within the test-taking environment, in order to monitor the behavior of the test taker.

Description

Methods, programs, and devices for setting up a test environment

[0001] The present disclosure relates to a method for setting up a test environment prior to taking a test, and more particularly, to a method and device for assisting a test taker to set up a test environment on his / her own according to requirements of a test administrator.

[0002]

[0003] In educational environments where testing takes place, it's crucial to monitor test takers' behavior during the test. Unlike offline testing, it's difficult to effectively monitor test takers' behavior and surroundings in online testing. Therefore, in online testing environments, it's even more crucial for administrators to accurately analyze test takers' actions in real time to determine if there was any cheating.

[0004] For administrators to accurately analyze test takers' actions in real time in online exams, objectively and accurately establishing the test-taking environment is a prerequisite. Because the test-taking environment in online exams is typically constructed by the test takers, not the administrators, it's difficult to reliably eliminate environmental factors that could contribute to cheating. Furthermore, it's difficult to establish the environment in accordance with administrator-required regulations (e.g., manuals, verbal instructions, etc.). Furthermore, because administrators sequentially conduct one-on-one verification processes for each test taker, waiting times for each test taker inevitably occur, resulting in wasted time waiting to begin the test. Therefore, in online exams, it's essential to guide test takers to objectively and accurately establish their own test-taking environment before taking the test.

[0005]

[0006] The present disclosure is conceived in response to the aforementioned background technology, and seeks to provide a method for guiding online test takers to construct their own test environment.

[0007] However, the problems to be solved in this disclosure are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood based on the description below.

[0008]

[0009] According to one embodiment of the present disclosure, a method for constructing a test environment, performed by a computing device, is disclosed to achieve the aforementioned task. The method may include the steps of providing a first user interface that prompts a test taker to photograph the test-taking environment using a camera; and the steps of providing a second user interface that prompts the test taker to install a camera within the test-taking environment to monitor the test taker's actions.

[0010] Alternatively, the step of providing a first user interface that induces the test taker to photograph the test-taking environment using a camera may include the step of implementing a first graphic through the first user interface that expresses a shooting range of the test-taking environment using the camera, a shooting direction of the camera, and a shooting order; the step of analyzing an object existing in an image captured and generated by the camera according to the first graphic using a pre-learned first neural network model; and the step of implementing a second graphic for guiding a problem of the test-taking environment or a third graphic for expressing that the shooting of the test-taking environment has been completed based on the analysis result, through the first user interface.

[0011] Alternatively, the first graphic may include a first split screen representing a reference position from which shooting begins within the shooting range of the test-taking environment; and a plurality of second split screens arranged adjacent to the first split screen to represent the shooting direction and shooting order of the camera.

[0012] Alternatively, the step of analyzing an object present in an image captured and generated according to the first graphic using the first pre-trained neural network model may include the step of inputting an image captured and generated according to the first graphic into the first neural network model to detect an object present in the image; and the step of determining a prohibited item present among the detected objects by reflecting the reliability of the first neural network model for the detected object based on a prohibition intensity that varies depending on the type of prohibited item to be excluded from the test-taking environment.

[0013] Alternatively, in the above method, the higher the prohibition strength, the lower the reliability of the detected objects required to determine whether a prohibited item exists among the detected objects.

[0014] Alternatively, based on the analysis results, the step of implementing a second graphic for guiding a problem in the test-taking environment or a third graphic for indicating that the shooting of the test-taking environment has been completed through the first user interface may include a step of implementing, through the first user interface, the second graphic for expressing the status of the existing prohibited item and guiding the test taker to take action to remove the existing prohibited item, if the prohibited item exists among the detected objects.

[0015] Alternatively, based on the analysis results, the step of implementing a second graphic for guiding a problem in the test-taking environment or a third graphic for indicating that the shooting of the test-taking environment has been completed through the first user interface may include a step of implementing the third graphic through the first user interface when it is determined that the prohibited item does not exist among the detected objects.

[0016] Alternatively, the step of providing a second user interface that guides the test taker to install a camera within the test-taking environment in order to monitor the test taker's behavior may include the step of implementing a fourth graphic through the second user interface for guiding a location where the camera should be initially installed based on a location of the test taker within an area captured through the first user interface; the step of implementing a fifth graphic through the second user interface for guiding the test taker's action so that a detection element necessary for monitoring the test taker's behavior is exposed within the camera's capture screen when the initial installation of the camera is completed according to the fourth graphic; the step of analyzing the detection element present in an image captured and generated by the camera using a pre-trained second neural network model when the placement of the detection element is completed according to the fifth graphic; and the step of implementing an alarm through the second user interface for guiding the test taker's action so that at least one of exposure, exposure location, or exposure direction of the detection element is adjusted based on the analysis result, or a step of expressing that the installation of the camera has been completed.

[0017] Alternatively, the sensing element may include at least one of a user terminal used for taking a test, a component of the user terminal, the test taker, the face of the test taker, or the hand of the test taker.

[0018] Alternatively, the fifth graphic may include a silhouette graphic that roughly represents where the sensing element should be placed within the camera's shooting screen.

[0019] Alternatively, when the arrangement of the sensing elements according to the fifth graphic is completed, the step of analyzing the sensing elements present in the image captured and generated by the camera using the pre-trained second neural network model may include the step of inputting an image in which the sensing elements whose arrangement according to the fifth graphic is completed are expressed into the second neural network model, thereby detecting the sensing elements present in the image; and, based on the detection result, analyzing at least one of the gaze direction of the test taker, which can be determined based on the position or direction of the detected sensing elements within the captured screen of the camera, the ratio between the detected sensing elements and the captured screen of the camera, or the reliability of the second neural network model for the detected sensing elements.

[0020] Alternatively, the step of implementing an alarm for guiding the test taker's action to adjust at least one of the exposure, exposure location, or exposure direction of the detection element based on the analysis result, or a sixth graphic for expressing that the installation of the camera is complete, through the second user interface, may include a step of implementing the alarm through the second user interface until the reference ratio or reference reliability is satisfied, when the ratio between the detected detection element and the camera's capture screen is equal to or greater than a predetermined reference ratio, or when the reliability of the detected detection element is equal to or less than the reference reliability.

[0021] According to one embodiment of the present disclosure for achieving the aforementioned task, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed on one or more processors, it causes operations for constructing a test environment. At this time, the operations may include an operation of providing a first user interface that prompts a test taker to photograph the test-taking environment using a camera; and an operation of providing a second user interface that prompts the test taker to install a camera within the test-taking environment to monitor the test taker's actions.

[0022] According to one embodiment of the present disclosure for achieving the above-described task, a computing device is disclosed. The device may include a processor including at least one core; and a memory including program codes executable by the processor. In this case, the processor may provide a first user interface that prompts a test taker to photograph a test-taking environment using a camera, and a second user interface that prompts the test taker to install a camera within the test-taking environment in order to monitor the test taker's behavior.

[0023]

[0024] The method according to the present disclosure allows test takers to eliminate unnecessary environmental factors for the test and smoothly set up devices necessary for behavioral monitoring, such as cameras, thereby primarily preventing test environment problems that may arise in online tests and minimizing the resources required for online test supervision and management.

[0025] Additionally, by allowing test takers to seamlessly create their own testing environment, preparation time before the test can be significantly reduced, and test takers can reduce their anxiety and fatigue before the test.

[0026]

[0027] FIG. 1 is a block diagram of a computing device according to one embodiment of the present disclosure.

[0028] FIG. 2 is a block diagram illustrating a process for constructing a test environment according to one embodiment of the present disclosure.

[0029] FIGS. 3 and 4 are conceptual diagrams illustrating a screen providing a first graphic of a first user interface according to one embodiment of the present disclosure.

[0030] FIG. 5 is a conceptual diagram illustrating a screen providing a second graphic of a first user interface according to one embodiment of the present disclosure.

[0031] FIG. 6 is a conceptual diagram illustrating a screen providing a third graphic of a first user interface according to one embodiment of the present disclosure.

[0032] FIG. 7 is a conceptual diagram illustrating a screen providing a fourth graphic of a second user interface according to one embodiment of the present disclosure.

[0033] FIG. 8 is a conceptual diagram illustrating a screen providing a fifth graphic of a second user interface according to one embodiment of the present disclosure.

[0034] FIGS. 9 and 10 are conceptual diagrams illustrating a screen providing a sixth graphic of a second user interface according to one embodiment of the present disclosure.

[0035] FIG. 11 is a flowchart illustrating a method for constructing a test environment according to one embodiment of the present disclosure.

[0036]

[0037] Below, embodiments of the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present disclosure. The embodiments presented in this disclosure are provided to enable those skilled in the art to utilize or implement the contents of the present disclosure. Accordingly, various modifications to the embodiments of the present disclosure will be apparent to those skilled in the art. That is, the present disclosure may be implemented in various different forms and is not limited to the embodiments described below.

[0038] Throughout the specification of this disclosure, identical or similar drawing numbers refer to identical or similar components. Furthermore, for the purpose of clearly describing the disclosure, drawing numbers for parts in the drawings that are not relevant to the description of the disclosure may be omitted.

[0039] The term "or" as used herein is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified herein or clear from context, "X employs A or B" should be understood to mean either of the natural inclusive permutations. For example, unless otherwise specified herein or clear from context, "X employs A or B" can be interpreted to mean either X employs A, X employs B, or X employs both A and B.

[0040] The term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the related concepts listed.

[0041] The terms "comprises" and / or "comprising" as used herein should be understood to mean the presence of certain features and / or components. However, it should be understood that the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other features, other components, and / or combinations thereof.

[0042] Unless otherwise specified in this disclosure or unless the context makes it clear that the singular form is intended to be referred to, the singular should generally be construed to include “one or more.”

[0043] The term "Nth (N is a natural number)" used in the present disclosure can be understood as an expression used to mutually distinguish components of the present disclosure based on a predetermined standard such as a functional perspective, a structural perspective, or convenience of explanation. For example, components performing different functional roles in the present disclosure can be distinguished as a first component or a second component. However, components that are substantially the same within the technical spirit of the present disclosure but must be distinguished for convenience of explanation may also be distinguished as a first component or a second component.

[0044] The term "acquisition" as used in this disclosure may be understood to refer to generating or receiving data in an on-device form, as well as receiving data via a wireless communication network with an external device or system.

[0045] Meanwhile, the term "module" or "unit" used in the present disclosure can be understood as a term referring to an independent functional unit that processes computing resources, such as a computer-related entity, firmware, software or a part thereof, hardware or a part thereof, or a combination of software and hardware. At this time, the "module" or "unit" may be a unit composed of a single element, or a unit expressed as a combination or set of multiple elements. For example, as a narrow concept, a "module" or "unit" may refer to a hardware element of a computing device or a set thereof, an application program that performs a specific function of software, a processing process implemented through software execution, or a set of instructions for program execution, etc. In addition, as a broad concept, a "module" or "unit" may refer to the computing device itself that constitutes the system, or an application running on the computing device, etc. However, since the above-described concept is only an example, the concept of “module” or “part” may be defined in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0046] The term "model" as used herein may be understood as a system implemented using mathematical concepts and language to solve a specific problem, a set of software units to solve a specific problem, or an abstract model of a processing process to solve a specific problem. For example, a deep learning "model" may refer to an entire system implemented as a neural network that has problem-solving capabilities through learning. In this case, the neural network can have problem-solving capabilities by optimizing parameters connecting nodes or neurons through learning. A deep learning "model" may include a single neural network or a set of neural networks that are a combination of multiple neural networks.

[0047] The term "image" as used herein may refer to multidimensional data composed of discrete image elements. In other words, "image" may be understood as a term referring to a digital representation of an object visible to the human eye. For example, "image" may refer to multidimensional data composed of elements corresponding to pixels in a two-dimensional image. "Image" may refer to multidimensional data composed of elements corresponding to voxels in a three-dimensional image.

[0048] The explanation of the above terms is intended to aid understanding of the present disclosure. Therefore, unless explicitly stated as limiting the contents of the present disclosure, it should be noted that the above terms are not intended to limit the technical ideas of the contents of the present disclosure.

[0049] FIG. 1 is a block diagram of a computing device according to one embodiment of the present disclosure.

[0050] A computing device (100) according to one embodiment of the present disclosure may be a hardware device or a part of a hardware device that performs comprehensive processing and calculation of data, or may be a software-based computing environment connected to a communication network. For example, the computing device (100) may be a server that performs intensive data processing functions and shares resources, or may be a client that shares resources through interaction with a server. In addition, the computing device (100) may be a cloud system that enables multiple servers and clients to interact with each other to comprehensively process data. Since the above description is only one example related to the type of computing device (100), the type of computing device (100) may be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0051] Referring to FIG. 1, a computing device (100) according to one embodiment of the present disclosure may include a processor (110), a memory (120), and a network unit (130). However, FIG. 1 is merely an example, and the computing device (100) may include other components for implementing a computing environment. In addition, only some of the disclosed components may be included in the computing device (100).

[0052] The processor (110) according to one embodiment of the present disclosure may be understood as a configuration unit including hardware and / or software for performing computing operations. For example, the processor (110) may read a computer program and perform operations for data processing. The processor (110) may process computational processes such as processing input data for machine learning, feature extraction for machine learning, and error calculation based on backpropagation. The processor (110) may generate a user interface for communication with an external terminal or device. The processor (110) for performing such data processing may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA). The type of processor (110) described above is only one example, and thus the type of processor (110) can be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0053] The processor (110) can generate a user interface that includes information guiding a test taker to establish a test-taking environment. Furthermore, the processor (110) can provide the generated user interface. In this case, if the computing device (100) is a server, the processor (110) can provide the user interface to the test taker client via the network unit (130). If the computing device (100) is a test taker client, the processor (110) can output the user interface via an input / output unit included in the test taker client.

[0054] Specifically, the processor (110) may generate a first user interface that guides the test taker to take a picture of the test-taking environment using a camera. The processor (110) may implement various graphics, sounds, etc. that guide the test taker to take a picture of the test-taking environment through the first user interface. For example, the processor (110) may graphically implement shooting guidance information on how to take a picture of the test-taking environment through the first user interface. The processor (110) may graphically implement the results of detecting prohibited items that may influence the test taker's judgment of cheating in the test-taking environment captured through the first user interface. In this way, the processor (110) may guide the test taker on how to organize and prepare the test-taking environment before taking the test through the first user interface.

[0055] The processor (110) may generate a second user interface that guides how a camera for monitoring the test taker's behavior should be installed within the test-taking environment. The processor (110) may implement various graphics, sounds, etc. to guide the installation of a camera to capture the test-taking environment through the second user interface. For example, the processor (110) may graphically implement information through the second user interface that guides how a sensing element for monitoring the test taker's behavior should be arranged within the camera screen. In addition, the processor (110) may graphically implement a result as to whether the sensing element is appropriately arranged according to the guidance information. In this case, appropriate arrangement can be understood as the sensing element being arranged within a predetermined error range from the reference position included in the guidance information. In this way, the processor (110) may guide the test taker through the second user interface on how to install the camera required for the test-taking process and how to maintain posture within the camera screen.

[0056] Meanwhile, the processor (110) can process user input receivable through the user interface. For example, the processor (110) can perform data processing, such as additional graphic implementation, based on user input, such as a click on a graphic implemented through the user interface. In this case, the user input is not limited to the click described above, and can be defined in various ways to suit the implementation form of various interface elements that induce user input.

[0057] The memory (120) according to one embodiment of the present disclosure may be understood as a configuration unit including hardware and / or software for storing and managing data processed in the computing device (100). That is, the memory (120) may store any type of data generated or determined by the processor (110) and any type of data received by the network unit (130). For example, the memory (120) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory, a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, or an optical disk. In addition, the memory (120) may also include a database system that controls and manages data in a predetermined system. The type of memory (120) described above is only one example, and thus the type of memory (120) can be configured in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.

[0058] The memory (120) can structure and organize and manage data, combinations of data, and program codes executable by the processor (110) required for the processor (110) to perform operations. For example, the memory (120) can store input data acquired through the network unit (130) described below. The memory (120) can store data regarding user input and requests received through the user interface. The memory (120) can store program codes that cause the processor (110) to perform operations to implement graphics of a user interface for building a test environment based on the input data. In addition, the memory (120) can store program codes that cause the processor (110) to train a deep learning model, program codes that cause the processor (110) to perform inference operations on the trained deep learning model, and various data generated as the program codes are executed.

[0059] The network unit (130) according to one embodiment of the present disclosure may be understood as a component that transmits and receives data through any type of known wired or wireless communication system. For example, the network unit (130) may perform data transmission and reception using a wired or wireless communication system such as a local area network (LAN), wideband code division multiple access (WCDMA), long term evolution (LTE), wireless broadband internet (WiBro), fifth generation mobile communication (5G), ultra wide-band, ZigBee, radio frequency (RF) communication, wireless LAN, wireless fidelity, near field communication (NFC), or Bluetooth. Since the above-described communication systems are only examples, the wired and wireless communication system for data transmission and reception of the network unit (130) may be applied in various ways other than the above-described examples.

[0060] The network unit (130) can receive data necessary for the processor (110) to perform calculations through wired or wireless communication with any system, server, client, etc. In addition, the network unit (130) can transmit data generated through calculations of the processor (110) through wired or wireless communication with any system, server, client, etc. For example, the network unit (130) can receive user input or input data for establishing a test environment through wired or wireless communication with a client, etc. The network unit (130) can transmit various data generated through calculations of the processor (110) based on user input or input data through wired or wireless communication with a client, etc.

[0061] FIG. 2 is a block diagram illustrating a process for constructing a test environment according to one embodiment of the present disclosure. In the following description of FIG. 2, it is assumed that the computing device (100) is a cloud-based server that provides a user interface through communication with a client used by a test taker.

[0062] Referring to FIG. 2, when a test taker accesses an online test service through a client and begins test preparation (10), the computing device (100) may provide a first user interface (20) through the input / output unit of the client that guides the test taker to capture a test-taking environment using a camera. For example, the computing device (100) may provide the test taker with information for guiding how to capture a test-taking environment using a camera through the first user interface (20) implemented through the input / output unit of the client. In addition, the computing device (100) may provide the test taker with information for guiding whether there is a problem with the test-taking environment captured using the camera through the first user interface (20) implemented through the input / output unit of the client. In this case, a problem with the test-taking environment may be understood as the presence of prohibited items, such as a smartphone or textbook, in the image captured using the camera, which may influence the test taker's behavior to be recognized as cheating. If there are no issues with the test-taking environment captured using the camera, the computing device (100) can provide the test taker with information indicating that the capture of the test-taking environment has been completed through the first user interface (20) implemented via the client's input / output unit. In this case, the completion of the capture of the test-taking environment can be understood as meaning that it has been determined that there are no prohibited items in the test-taking environment captured using the camera.

[0063] The computing device (100) can analyze whether there are any problems in the test-taking environment captured using a camera. Specifically, the computing device (100) can detect objects present in the test-taking environment captured using the camera using a pre-trained first neural network model. At this time, the first neural network model may include a neural network that receives an image and detects objects. In addition, the first neural network model may be pre-trained based on supervised learning. The computing device (100) can determine which prohibited items are present among the objects detected through the first neural network model. The computing device (100) can determine which prohibited items are present among the objects detected through the first neural network model based on a preset prohibition level and the detection reliability of the first neural network model. At this time, the prohibition level may be an indicator that varies depending on the type of items to be excluded from the test-taking environment. If the prohibited item is a high prohibited item, the computing device (100) can determine the item as a prohibited item even if the detection reliability of the first neural network model is lower than a reference value. In the case of an item with a low prohibition level, the computing device (100) can determine the item as a prohibited item only if the detection reliability of the first neural network model is higher than a threshold. For example, an item with a high possibility of being considered a fraudulent act, such as a smartphone, may have a high prohibition level. If an object identified as a smartphone is detected through the first neural network model, the computing device (100) can determine the object as a prohibited item even if the detection reliability is 20% to 30%, which is lower than the threshold of 50%.Conversely, items that are less likely to be considered cheating, such as vases, may have a lower prohibition level set. When an object identified as a vase is detected through the first neural network model, the computing device (100) can determine the object as a prohibited item only if the detection reliability is higher than 60% to 70%, which is higher than the standard of 50%. In other words, the higher the prohibition level, the lower the reliability required to determine whether a prohibited item exists among the objects detected through the first neural network model, which may be an inversely proportional relationship. In this way, the computing device (100) can minimize the possibility of cheating in a test-taking environment and minimize damage to test-takers due to unexpected prohibited items by comprehensively considering the prohibition level set for each type of prohibited item and the detection reliability of the first neural network model when determining prohibited items. Meanwhile, the above-described numerical values ​​are merely examples, and thus the relationship between the prohibition level and the detection reliability of the present disclosure is not limited to the above-described numerical values.

[0064] When the shooting of the test-taking environment is completed through the first user interface (20), the computing device (100) may provide a second user interface (30) through the input / output unit of the client to guide the test-taker to install a camera within the test-taking environment in order to monitor the test-taker's behavior. For example, the computing device (100) may provide the test-taker with information guiding where the camera should be initially installed based on the test-taker's location through the second user interface (30) implemented through the input / output unit of the client. In addition, the computing device (100) may provide the test-taker with information guiding where a detection element for monitoring the test-taker's behavior should be positioned within the screen of the initially installed camera through the second user interface (30) implemented through the input / output unit of the client. Here, the detection element for monitoring the test-taker's behavior may be an object used to determine whether the test-taker's behavior is cheating or an abnormal behavior suspected of cheating. In addition, the computing device (100) can determine whether the sensing element exposed within the camera screen is appropriately positioned. At this time, appropriate positioning can be understood as meaning that the sensing element is positioned within a predetermined error range based on guidance on where it should be positioned within the camera screen. If the sensing element is appropriately positioned within the camera screen, the computing device (100) can provide information indicating that the camera installation is complete to the test taker through the second user interface (30) implemented through the input / output unit of the client. At this time, the completion of the shooting of the test-taking environment can be understood as meaning that the test-taking environment is finally established and preparations for the test are complete.If the sensing element is not properly positioned within the camera screen, the computing device (100) may provide the test taker with information to adjust the position of the sensing element through a second user interface (30) implemented via the input / output unit of the client, which guides the test taker's action. In this case, adjusting the position of the sensing element may include adjusting the position of the sensing element based on the screen of the currently installed camera, as well as adjusting the position of the currently installed camera while fixing the current position of the sensing element.

[0065] The computing device (100) can analyze what kind of sensing elements are present within the screen of the installed camera through the second user interface (30). Specifically, the computing device (100) can detect sensing elements present in the test-taking environment captured by the camera installed through the second user interface (30) using a pre-trained second neural network model. At this time, the second neural network model may include a neural network that receives an image as input and detects an object. In addition, the second neural network model may be pre-trained based on supervised learning. The computing device (100) can analyze the gaze direction of the test taker based on the position or direction of the sensing elements detected through the second neural network model. For example, the computing device (100) can analyze the direction in which the test taker is gazing by using the direction of the test taker's face, the position of components of the user terminal used for the test, etc. The gaze direction of the test taker analyzed in this way can be utilized to monitor the test taker's behavior during the test-taking process. The computing device (100) can analyze at least one of the ratio between the detection element detected through the second neural network model and the captured screen of the camera installed through the second user interface (30) or the reliability of the detection element detected through the second neural network model. Then, the computing device (100) can determine how the detection element should be arranged within the captured screen of the camera installed through the second user interface (30) based on at least one of the analyzed ratio or reliability. For example, the computing device (100) can determine whether the ratio between the test taker detected through the second neural network model and the captured screen of the camera installed through the second user interface (30) is equal to or greater than the standard ratio of 1 / 3. Then, the computing device (100) can determine where the test taker should be positioned to satisfy the standard ratio based on the currently installed camera.In addition, the computing device (100) can determine whether the reliability of the test taker's face detected through the second neural network model is greater than or equal to the standard reliability level of 50%. At this time, the computing device (100) can generate an alarm to guide the test taker to adjust the exposure, exposure location, or exposure direction of the detection element based on the result of the above-described determination, and provide the alarm to the test taker through the second user interface (30). The alarm can be dynamically generated and provided to the test taker through the second user interface (30) until the adjusted result satisfies the standard ratio or standard reliability level. In this way, the computing device (100) can guide the camera to be installed appropriately according to the test-taking conditions, thereby allowing even first-time test takers to easily and accurately create a test-taking environment, thereby increasing user convenience and minimizing the resources required to create a test environment from the test administrator's perspective. Meanwhile, the above-described numerical values ​​are merely examples, and the relationship between the inhibition intensity and detection reliability of the present disclosure is not limited to the above-described numerical values.

[0066] FIGS. 3 and 4 are conceptual diagrams illustrating a screen providing a first graphic of a first user interface according to one embodiment of the present disclosure.

[0067] A computing device (100) according to one embodiment of the present disclosure may implement a first graphic representing a shooting range of a test-taking environment using a camera, a shooting direction of the camera, and a shooting order through a first user interface. In addition, the first graphic implemented through the first user interface may be output through an input / output unit of a client or computing device (100) possessed by a test taker. At this time, the first graphic may include a first split screen representing a reference position from which shooting begins within the shooting range of the test-taking environment, and a plurality of second split screens arranged adjacent to the first split screen to represent the shooting direction and shooting order of the camera. That is, the computing device (100) may guide a test taker on how to shoot a test-taking environment through the first graphic.

[0068] For example, referring to FIGS. 3 and 4, the first graphic may include nine split screens that display the shooting order. In other words, the first graphic may include a first split screen corresponding to the center of the test-taking environment, which is a reference position for the start of shooting, and eight second split screens that are arranged without overlapping areas at the corners of the first split screen and correspond to the remaining areas excluding the center of the test-taking environment. When the first graphic is implemented as an overlay on the first screen (210), the test taker can set the center point of the test-taking environment based on the first split screen. Once the center point is set, the first screen (210) may be switched to a second screen (220) that induces shooting of the first split screen. The test taker may position the computing device to be used for the test at the center of the screen of the client on which the first graphic is provided to shoot the first split screen. Once the first split screen is shot, the second screen (220) may be switched to a third screen (230) that induces camera movement. The test taker can move the client's camera to the left in accordance with the first graphic implemented as an overlay on the third screen (230). Then, when the client's camera is moved to the left, the computing device (100) can determine whether the camera has moved to a state that satisfies the condition of being the leftmost area that does not overlap with the first split screen, through the value of the acceleration sensor equipped in the client. If the camera has moved and the above-described condition is satisfied, the shooting can be performed automatically even if the test taker does not manually shoot. When the shooting of the second split screen that is aligned with the first graphic implemented on the remaining fourth screen (240) and fifth screen (250) is repeatedly performed so as to correspond to the shooting process that is aligned with the first graphic implemented on the third screen (230) described above, the computing device (100) can combine the nine split screens to create a full image of the test-taking environment.In addition, the computing device (100) can analyze the entire image of the test-taking environment generated by combining nine split screens, as shown in 260 of FIG. 4. Meanwhile, guidance text guiding the test taker to perform the aforementioned tasks may be implemented as a second graphic at the bottom of the screen of the first user interface. Additionally, sounds guiding the test taker to perform the aforementioned tasks may be provided through the first user interface.

[0069] FIG. 5 is a conceptual diagram illustrating a screen providing a second graphic of a first user interface according to one embodiment of the present disclosure.

[0070] The computing device (100) can analyze objects present in an image captured and generated by the camera based on the first graphic using a pre-trained first neural network model. Furthermore, the computing device (100) can implement a second graphic to guide the test-taker through the first user interface based on the analysis results. Specifically, if a prohibited item is present among the detected objects, the computing device (100) can implement a second graphic through the first user interface that expresses the status of the existing prohibited item and guides the test-taker to take action to remove the existing prohibited item.

[0071] For example, referring to FIG. 5, in the screen (270) where the second graphic is implemented, the second graphic may include an image graphic that overlays the result of detecting prohibited items in the entire image of the test-taking environment created by combining nine split screens, and a text graphic that guides the status of the prohibited items and induces the removal of the prohibited items and re-shooting. At this time, the text graphic that induces re-shooting may be implemented as a button-type icon that can receive a user input such as a click. The entire image of the test-taking environment expressed in the screen (270) where the second graphic is implemented may be enlarged based on the user input. The test taker can intuitively grasp the location and status of the prohibited items through the second graphic implemented through the first user interface, and easily construct an environment where the prohibited items have been removed.

[0072] FIG. 6 is a conceptual diagram illustrating a screen providing a third graphic of a first user interface according to one embodiment of the present disclosure.

[0073] The computing device (100) can analyze objects present in an image captured and generated by the camera based on the first graphic using a pre-trained first neural network model. Furthermore, the computing device (100) can implement a third graphic, through the first user interface, to indicate that the capture of the test-taking environment has been completed based on the analysis results. Specifically, if it is determined that the prohibited item does not exist among the detected objects, the computing device (100) can provide the third graphic through the first user interface.

[0074] For example, referring to FIG. 6, in the screen (280) where the third graphic is implemented, the third graphic may include an image graphic that expresses the entire image of the test-taking environment without any prohibited items, and a text graphic that notifies that the shooting is complete and guides the user to the next task based on the second user interface. In this case, the text graphic that guides the next task may be implemented as a button-type icon that can receive user input, such as a click.

[0075] FIG. 7 is a conceptual diagram illustrating a screen providing a fourth graphic of a second user interface according to one embodiment of the present disclosure.

[0076] A computing device (100) according to one embodiment of the present disclosure may implement a fourth graphic, through a second user interface, to guide the location where the camera should be initially installed based on the location of the test taker within the area captured through the first user interface. Furthermore, the fourth graphic implemented through the second user interface may be output through an input / output unit of a client or computing device (100) possessed by the test taker.

[0077] For example, referring to FIG. 7, in the screen (280) where the fourth graphic is implemented, the fourth graphic may include a text graphic that guides the camera to be positioned at a certain distance from a certain location in the test-taking environment captured by the first user interface. In this case, the text graphic may be displayed as an overlay on the entire image of the test-taking environment captured by the first user interface. The test-taker can easily install the camera at the designated location according to the guidance provided by the fourth graphic.

[0078] FIG. 8 is a conceptual diagram illustrating a screen providing a fifth graphic of a second user interface according to one embodiment of the present disclosure.

[0079] When the initial installation of the camera is completed according to the fourth graphic, the computing device (100) can implement a fifth graphic through the second user interface that guides the test taker's actions so that the detection elements necessary for monitoring the test taker's behavior are exposed within the camera's capture screen. At this time, the detection elements may include at least one of the user terminal used for taking the test, a component of the user terminal, the test taker itself, the test taker's face, or the test taker's hand. That is, the computing device (100) can guide the placement of the detection elements through the fifth graphic so that the detection elements necessary for analyzing the test taker's behavior are stably exposed within the screen of the camera that performs capture during the test taking process.

[0080] For example, the fifth graphic may include a silhouette-shaped graphic that roughly represents the location where the detection element should be placed within the camera's capture screen. When the fifth graphic is implemented in the first screen (320) of FIG. 8, a text graphic containing guidance phrases such as "Please adjust the camera so that your face, both hands, and the PC screen are visible" or "Do not wear clothing or accessories unrelated to the test that may obscure your face." may also be implemented. In addition, when the camera is adjusted according to these text graphics, the first screen (320) of FIG. 8 switches to the second screen (330) of FIG. 8, and together with the fifth graphic, a text graphic containing guidance phrases such as "Please sit down and maintain a gaze posture for at least 3 seconds" or "Your current gaze posture is being captured." may also be implemented. Through the fifth graphic and the text graphics, the test taker can easily identify the location where the detection element should be exposed within the camera screen and place the detection element in the identified location. Meanwhile, the guidance phrases may also be implemented as sound in addition to text graphics and provided to the test taker.

[0081] FIGS. 9 and 10 are conceptual diagrams illustrating a screen providing a sixth graphic of a second user interface according to one embodiment of the present disclosure.

[0082] When the arrangement of the sensing elements is completed according to the fifth graphic, the computing device (100) can analyze the sensing elements present in the image captured and generated by the camera using the second pre-trained neural network model. Then, the computing device (100) can implement an alarm to guide the test taker to adjust at least one of the exposure, exposure position, or exposure direction of the sensing elements based on the analysis result, or a sixth graphic to express that the camera installation is complete, through the second user interface. Specifically, if the sensing elements are not exposed in the image captured and generated by the camera even though they are arranged according to the fifth graphic, or are exposed to a degree that does not satisfy the standard arrangement, the computing device (100) can implement an alarm to guide the test taker to adjust at least one of the exposure, exposure position, or exposure direction of the sensing elements, through the second user interface. Conversely, if the sensing elements are all exposed in the image captured and generated by the camera so as to satisfy the standard arrangement, the computing device (100) can implement a sixth graphic to express that the camera installation is complete, through the second user interface. At this time, the reference arrangement can be understood as the minimum exposure required to detect the sensing element for monitoring the test taker's behavior.

[0083] For example, when the detection elements, such as a person, a face, a hand, and a monitor, are positioned on an image captured and generated by a camera according to the fifth graphic, if the test taker's hands are not exposed unlike other detection elements, an alarm such as "Both hands are not visible" may be implemented as a text graphic, as in the screen (340) of FIG. 9. This alarm may be implemented not only as a text graphic but also as a sound through the second user interface. In addition, although not disclosed in FIG. 9, if the face is not visible by more than 50%, an alarm that prompts the test taker to adjust the position or orientation of the detection elements, such as "Rotate your face to the right to expose more of your face," may also be implemented as a text graphic. When the alarm is implemented through the second user interface in this way, the test taker can easily adjust the position of the detection elements within the camera's screen until the detection elements satisfy the preset reference placement.

[0084] Referring to FIG. 9, in the screen (350) where the sixth graphic is implemented, the sixth graphic may include a text graphic to inform the administrator that the camera installation has been completed and that the test-taking environment has been constructed. In this case, the text graphic to inform the administrator that the test-taking environment has been constructed may be implemented as a button-type icon capable of receiving user input, such as a click.

[0085] FIG. 11 is a flowchart illustrating a method for constructing a test environment according to one embodiment of the present disclosure.

[0086] Referring to FIG. 11, a computing device (100) according to one embodiment of the present disclosure may provide a first user interface that prompts a test taker to take a picture of the test-taking environment using a camera (S110). If the computing device (100) is a cloud server providing a test service, the computing device (100) may generate a first user interface and provide the first user interface to the test taker through communication with a client possessed by the test taker. If the computing device (100) is a client equipped with an input / output unit, the computing device (100) may provide the first user interface to the test taker through the input / output unit.

[0087] The computing device (100) may implement a first graphic, which expresses the shooting range of the test-taking environment using a camera, the shooting direction of the camera, and the shooting order, through the first user interface. In addition, the computing device (100) may implement a second graphic, which guides the problem of the test-taking environment, or a third graphic, which indicates that the shooting of the test-taking environment has been completed, through the first user interface. In this case, the first graphic to the third graphic implemented through the first user interface may not be expressed visually but may also be implemented in the form of sound.

[0088] The computing device (100) may provide a second user interface that prompts the test taker to install a camera within the test-taking environment to monitor the test taker's behavior. If the computing device (100) is a cloud server providing a test service, the computing device (100) may generate a second user interface and provide the second user interface to the test taker through communication with a client possessed by the test taker. If the computing device (100) is a client equipped with an input / output unit, the computing device (100) may provide the second user interface to the test taker through the input / output unit.

[0089] The computing device (100) may implement a fourth graphic through the second user interface to guide the location where the camera should be initially installed based on the location of the test taker within the area captured through the first user interface. When the initial installation of the camera is completed according to the fourth graphic, the computing device (100) may implement a fifth graphic through the second user interface to guide the test taker to take action so that a detection element necessary for monitoring the test taker's behavior is exposed within the camera's capture screen. In addition, the computing device (100) may implement an alarm through the second user interface to guide the test taker to take action so that at least one of the exposure, exposure location, or exposure direction of the detection element is adjusted, or a sixth graphic to express that the camera installation is complete. At this time, the fourth and fifth graphics implemented through the second user interface may not be expressed visually but may also be implemented in the form of sound.

[0090] The various embodiments of the present disclosure described above can be combined with additional embodiments and modified within the scope understood by those skilled in the art in light of the detailed description above. It should be understood that the embodiments of the present disclosure are illustrative in all respects and not restrictive. For example, each component described as a single component may be implemented in a distributed manner, and likewise, components described as distributed may be implemented in a combined manner. Accordingly, all changes or modifications derived from the meaning, scope, and equivalent concepts of the claims of the present disclosure should be construed as being included within the scope of the present disclosure.

Claims

1. A method for constructing a test environment, performed by a computing device including at least one processor, A step of providing a first user interface that prompts the test taker to take a picture of the test-taking environment using a camera; and A step of providing a second user interface that prompts the test taker to install a camera within the test-taking environment to monitor the test taker's behavior; including, method.

2. In paragraph 1, The step of providing a first user interface that prompts the test taker to take a picture of the test-taking environment using a camera is as follows: A step of implementing a first graphic expressing the shooting range of the test-taking environment using the camera, the shooting direction of the camera, and the shooting order through the first user interface; A step of analyzing an object present in an image captured and generated by the camera according to the first graphic using a pre-trained first neural network model; and Based on the above analysis results, a step of implementing a second graphic for guiding the problem of the test-taking environment or a third graphic for expressing that the filming of the test-taking environment has been completed through the first user interface; including, method.

3. In paragraph 2, The first graphic above is, A first split screen expressing a reference position from which shooting begins within the shooting range of the above test-taking environment; and A plurality of second split screens arranged adjacent to the first split screen, indicating the shooting direction and shooting order of the camera; including, method.

4. In paragraph 2, The step of analyzing an object existing in an image captured and generated according to the first graphic using the above-mentioned pre-learned first neural network model is as follows: A step of inputting an image generated by photographing along the first graphic into the first neural network model to detect an object present in the image; and A step of determining which prohibited items exist among the detected objects by reflecting the reliability of the first neural network model for the detected objects based on the degree of prohibition that varies depending on the type of prohibited items that must be excluded from the test-taking environment; including, method.

5. In paragraph 4, The higher the intensity of the prohibition, the lower the reliability of the detected objects required to determine whether there are prohibited items among the detected objects. method.

6. In paragraph 4, Based on the above analysis results, the step of implementing a second graphic to guide the problem of the test-taking environment or a third graphic to express that the shooting of the test-taking environment has been completed through the first user interface is as follows. A step of implementing the second graphic, which expresses the status of the existing prohibited item and guides the test taker to take action to remove the existing prohibited item, through the first user interface, if the prohibited item exists among the detected objects; including, method.

7. In paragraph 4, Based on the above analysis results, the step of implementing a second graphic to guide the problem of the test-taking environment or a third graphic to express that the shooting of the test-taking environment has been completed through the first user interface is as follows. A step of implementing the third graphic through the first user interface when it is determined that the prohibited item does not exist among the detected objects; including, method.

8. In paragraph 1, In order to monitor the behavior of the test taker, a step of providing a second user interface that prompts the test taker to install a camera within the test taking environment is provided. A step of implementing a fourth graphic for guiding the location where the camera should be initially installed based on the location of the test taker within the area captured through the first user interface through the second user interface; Upon completion of the initial installation of the camera according to the fourth graphic, a step of implementing a fifth graphic through the second user interface to guide the test taker's actions so that the detection elements necessary for monitoring the test taker's actions are exposed within the camera's shooting screen; When the arrangement of the detection elements is completed according to the fifth graphic, a step of analyzing the detection elements present in the image captured and generated by the camera using a pre-trained second neural network model; and Based on the analysis results, a step of implementing an alarm to induce the test taker to take action to adjust at least one of the exposure, exposure location, or exposure direction of the detection element, or a sixth graphic to indicate that the installation of the camera has been completed through a second user interface; including, method.

9. In paragraph 8, The above detection element is, A user terminal used for taking a test, comprising at least one of a component of the user terminal, the test taker, the face of the test taker, or the hand of the test taker. method.

10. In paragraph 8, The fifth graphic above is, Including a silhouette-shaped graphic roughly representing the position where the detection element should be placed within the shooting screen of the camera; method.

11. In paragraph 8, When the arrangement of the detection elements is completed according to the fifth graphic, the step of analyzing the detection elements present in the image captured and generated by the camera using the pre-trained second neural network model is as follows. A step of inputting an image in which a detection element whose arrangement is completed along the fifth graphic is expressed into the second neural network model, and detecting the detection element present in the image; and A step of analyzing at least one of the gaze direction of the test taker, which can be determined based on the position or direction of the detected sensing element within the camera's shooting screen, the ratio between the detected sensing element and the camera's shooting screen, or the reliability of the second neural network model for the detected sensing element, based on the detection result; including, method.

12. In paragraph 11, Based on the analysis results, the step of implementing an alarm to induce the test taker to take action to adjust at least one of the exposure, exposure location, or exposure direction of the detection element or a sixth graphic to indicate that the installation of the camera has been completed through the second user interface is as follows. A step of implementing the alarm through a second user interface when the ratio between the detected detection element and the camera's shooting screen is greater than or equal to a predetermined standard ratio or the reliability of the detected detection element is less than or equal to the standard reliability until the standard ratio or standard reliability is satisfied; including, method.

13. A computer program stored in a computer-readable storage medium, wherein the computer program, when executed on one or more processors, performs operations for constructing a test environment. The above actions are, An action providing a first user interface that prompts the test taker to take a picture of the test-taking environment using a camera; and An action of providing a second user interface that prompts the test taker to install a camera within the test-taking environment to monitor the test taker's behavior; including, Computer program.

14. As a computing device for establishing a test environment, a processor comprising at least one core; and A memory containing program codes executable by the processor; Including, The above processor, Provides a first user interface that prompts test takers to use a camera to capture the test-taking environment; In order to monitor the behavior of the test taker, a second user interface is provided that prompts the test taker to install a camera within the test taking environment. device.

Images