Information processing method, program, and information processing device

Abstract

This invention provides an information processing method that enables the detection of impersonation. [Solution] Before the online exam date, the computer obtains first photographic data of the examinee's official photo ID and second photographic data of the examinee. The computer then grants permission to take the online exam if it authenticates the examinee's identity based on the first and second photographic data. The computer also obtains third photographic data of the examinee who has been granted permission to take the online exam on the day of the exam.

Description

Technical Field

[0001] The present disclosure relates to an information processing method, a program, and an information processing apparatus.

Background Art

[0002] In recent years, online tests have been implemented in which examinees can take tests such as certification tests or qualification tests at home via a communication network such as the Internet. Patent Document 1 discloses a technique for monitoring examinees during an online test.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In an online test, in addition to preventing cheating during the test, it is necessary to take measures to prevent "impersonation" where a person other than the examinee takes the test. In Patent Document 1, since a proof photo taken for identity verification is printed on the certificate of qualification, the examinee can be identified by the photo on the certificate of qualification, so impersonation can be prevented. However, with the technique disclosed in Patent Document 1, it is not possible to detect impersonation when applying for the test or when taking the test.

[0005] An object of the present disclosure is to provide an information processing method and the like capable of detecting impersonation.

Means for Solving the Problems

[0006] An information processing method according to one aspect of this disclosure involves a computer executing a process to acquire, before the online examination date, first photographic data of a photograph of the examinee's official identification document with a photograph and second photographic data of the examinee, and if the examinee's identity is authenticated based on the first and second photographic data, the computer permits the examinee to take the online examination, and on the day of the online examination, it obtains third photographic data of the examinee who has been permitted to take the examination. [Effects of the Invention]

[0007] According to this disclosure, it will be possible to detect impersonation. [Brief explanation of the drawing]

[0008] [Figure 1] This is an explanatory diagram showing an example configuration of an online examination system. [Figure 2] This block shows an example configuration of the server and examinee terminals. [Figure 3] This is an explanatory diagram showing an example of the record layout of the examinee database stored on the server. [Figure 4] This is an explanatory diagram showing an example of a learning model configuration. [Figure 5] This flowchart shows an example of the pre-exam candidate authentication process. [Figure 6] This is an explanatory diagram showing an example screen on a test-taker's device. [Figure 7] This is a flowchart illustrating an example of the online exam processing procedure. [Figure 8] This is a flowchart illustrating an example of the online exam processing procedure. [Figure 9] This is an explanatory diagram showing an example screen on a test-taker's device. [Figure 10] This is an explanatory diagram showing an example screen on a test-taker's device. [Figure 11] This flowchart shows an example of a procedure for determining fraudulent activity. [Figure 12] This is an explanatory diagram showing an example screen on an operator terminal. [Figure 13] This is a flowchart showing an example of the processing procedure for the online test in Embodiment 2. [Modes for carrying out the invention]

[0009] The information processing method, program, and information processing apparatus of this disclosure will be described in detail below, based on drawings showing an online test system which is an embodiment thereof.

[0010] (Embodiment 1) This invention describes an online examination system that provides online examinations, such as certification or accreditation tests, that examinees take from their homes or other locations via a network. In this embodiment, the online examination is an Internet-Based Testing (IBT) test that examinees take at their homes or offices using terminals owned by themselves or their companies. However, the online examination system of this embodiment is also applicable to systems that provide Computer-Based Testing (CBT) tests that examinees take at designated test venues using terminals provided by the operator. Furthermore, in this embodiment, the online examination is an examination that can be taken at any time within a specified examination period, but it may also be an examination that can only be taken on a specified examination day.

[0011] Figure 1 is an explanatory diagram showing an example configuration of an online examination system. The online examination system of this embodiment includes a server 10, examinee terminals 20, an authentication server 30, and an operator terminal 40, and each device is connected to communicate via a network N. Multiple examinee terminals 20 and multiple operator terminals 40 may be provided. The network N may be the Internet or a public telephone network, or a LAN (Local Area Network) built within the facility where the online examination system is installed.

[0012] Server 10 and authentication server 30 are information processing devices capable of various information processing and information transmission / reception, such as server computers, personal computers, or quantum computers. Server 10 may be managed by the company operating the online exam, or by a company entrusted with the operation of the online exam. Authentication server 30 is a server that provides user authentication (examinee authentication) using a publicly issued photo ID, such as providing an eKYC (electronic Know Your Customer) system. Authentication server 30 may be managed by the company operating the online exam, or by another company entrusted with examinee authentication. Examinee terminals 20 and operator terminals 40 are information processing devices capable of various information processing and information transmission / reception, such as personal computers, tablet terminals, smartphones, etc. Examinee terminal 20 is the terminal device of an examinee taking the online exam provided by server 10, and may be a notebook computer or a desktop computer. Operator terminal 40 is the terminal device of a person in charge (operator) of the company operating the online exam.

[0013] In the online examination system of this embodiment, server 10 has the functionality of a web server and provides an online examination site 12S (see Figure 2) for conducting online examinations to examinee terminals 20 via network N. Before taking the online examination, examinee terminal 20 sends images of the examinee's official identification document and an image of the examinee's face to server 10 as pre-examination information. Server 10 sends the images of the official identification document and the examinee to authentication server 30, where authentication server 30 performs examinee authentication (verification of the examinee's identity) and permits examinees authenticated by authentication server 30 to take the online examination. Immediately before taking the online examination, examinee terminal 20 sends images of the examinee's face and a video of the desk and room where the examination will be conducted to server 10 as pre-examination information. Server 10 performs examinee authentication based on the examinee's image obtained here and the images of the official identification document or the examinee obtained as pre-examination information, and verifies the examinee's legitimacy. Furthermore, the examinee terminal 20 records a video of the examinee's face (upper body), collects room audio, and tracks the cursor position during the exam, and transmits the examinee's recorded video, room audio, and cursor position to the server 10 as exam information. The exam information may be transmitted to the server 10 in real time each time the examinee terminal 20 acquires it, or it may be transmitted to the server 10 all at once after the exam is completed. The examinee terminal 20 is not limited to a configuration in which the examinee's recorded video, room audio, and cursor position are acquired separately during the exam. For example, the examinee's recorded video, including room audio, may be displayed on a part of the exam screen, and screen data including the exam screen on which the recorded video is displayed and the cursor moving on the exam screen may be acquired. In this case, the examinee's recorded video, room audio, and cursor position can be acquired together as a single screen data. For example, in a configuration where an online exam is taken using a system that exchanges recorded video and spoken audio via network N, and screen sharing occurs between server 10 and examinee terminal 20, server 10 may acquire various information from examinee terminal 20 (examinee's recorded video, room audio, cursor position) through screen sharing. Based on the information obtained during the exam, server 10 determines whether or not the examinee is cheating.As described above, in this embodiment, by performing examinee authentication using a public certificate in advance and examinee authentication based on a captured image immediately before the examination, the legitimacy of the examinee can be confirmed and impersonation by others can be prevented. In addition, it is possible to determine whether or not an improper act such as cheating has been committed during the examination by using the data of the video, voice, and cursor position collected during the examination.

[0014] FIG. 2 is a block diagram showing a configuration example of the server 10 and the examinee terminal 20. The server 10 includes a control unit 11, a storage unit 12, a communication unit 13, a reading unit 14, etc., and each unit is interconnected via a bus. The control unit 11 includes one or more processors (arithmetic processing units) such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), or GPU (Graphics Processing Unit). The control unit 11 executes the processes to be performed by the server 10 by appropriately executing the program 12P stored in the storage unit 12. When the control unit 11 includes a plurality of processors, each process may be executed by the same processor, or each process may be executed by different processors.

[0015] The storage unit 12 includes a RAM (Random Access Memory), a flash memory, a hard disk, an SSD (Solid State Drive), etc. The storage unit 12 stores a program 12P (program product, computer program) executed by the control unit 11 and various types of data. Also, the storage unit 12 temporarily stores data and the like generated when the control unit 11 executes the program 12P. Further, the storage unit 12 stores an online test site 12S and a test taker DB 12a. Furthermore, the storage unit 12 stores a learned learning model 12M that has learned training data by machine learning. The learning model 12M is assumed to be used as a program module constituting artificial intelligence software. The learning model 12M performs a predetermined operation on input data and outputs an operation result. In the storage unit 12, data such as coefficients and threshold values of a function that defines this operation is stored as the learning model 12M. In addition to the configuration stored in the storage unit 12, the learning model 12M may be configured such that the server 10 accesses and reads the learning model 12M from another server that stores it. The storage unit 12 may be composed of a plurality of storage devices, and a part of the storage unit 12 may be another storage device connected to the server 10, or may be another storage device that the server 10 can communicate with.

[0016] The communication unit 13 is a communication module for performing processing related to wired communication or wireless communication, and transmits and receives information to and from other devices via the network N. The reading unit 14 reads information recorded on a recording medium 10a such as a memory card or an optical disk. The program 12P and various types of data stored in the storage unit 12 may be read from the recording medium 10a by the control unit 11 via the reading unit 14 and stored in the storage unit 12. Also, the program 12P and various types of data stored in the storage unit 12 may be written into the storage unit 12 at the manufacturing stage of the server 10, or may be downloaded by the control unit 11 from another device via the communication unit 13 and stored in the storage unit 12.

[0017] In this embodiment, the server 10 is not limited to a single computer, but may be a multi-computer consisting of multiple computers, or a virtual machine virtually constructed by software within a single device. Furthermore, the server 10 may be a local server installed in a facility where the server 10 (online examination system) is located, or it may be a cloud server connected via network N. The program 12P may be deployed and executed on a single computer or at a single site, or it can be distributed across multiple sites and deployed to run on multiple computers interconnected via network N. In addition, the server 10 may be configured to include an input unit for receiving user input, a display unit for displaying various information, etc.

[0018] The authentication server 30 has the same configuration as the server 10, so a description of its configuration will be omitted. The storage unit of the authentication server 30 stores an authentication program for authenticating examinees based on a photograph of the examinee's official identification document and a photograph of the examinee's face. In this embodiment, the authentication server 30, which performs examinee authentication based on the photograph of the official identification document, is provided separately from the server 10, but the server 10 may also have the functionality of the authentication server 30. Alternatively, the online examination operating company may manage both the server 10 and the authentication server 30. Furthermore, the server 10 may perform examinee authentication based on the photograph of the official identification document, for example, by using a method such as pattern matching. Specifically, the server 10 may extract features from the photograph of the examinee's official identification document and the photograph of the examinee's face, calculate the similarity of each feature, and consider authentication successful if the calculated similarity is above a threshold, and unsuccessful if it is below the threshold. Similarity can be calculated using the correlation coefficient, cosine similarity, etc.

[0019] The examinee terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, a display unit 25, a camera 26, a microphone 27, etc., and each unit is interconnected via a bus. The control unit 21, storage unit 22, and communication unit 23 of the examinee terminal 20 have the same configuration as the control unit 11, storage unit 12, and communication unit 13 of the server 10, so a description of their configuration will be omitted. In addition to the program 22P executed by the control unit 21, the storage unit 22 of the examinee terminal 20 stores a web browser (hereinafter referred to as browser 22B) for accessing the web server.

[0020] The display unit 25 is a liquid crystal display or an organic EL display, etc., and displays various information according to instructions from the control unit 21. The input unit 24 includes, for example, a mouse and keyboard, and receives operation input from the examinee and sends control signals corresponding to the operation content to the control unit 21. The input unit 24 of the examinee terminal 20 in this embodiment has a pointing device 24a that can operate a cursor displayed on the screen of the display unit 25, and the pointing device 24a can be, for example, a mouse, touchpad, trackball, joystick, etc.

[0021] Camera 26 is an imaging device having a lens and an image sensor, etc. It takes pictures according to instructions from the control unit 21 and acquires one image data (still image data) or image data such as 15 or 30 frames per second (moving image data), and stores the acquired image data in the storage unit 22. Camera 26 is positioned to photograph the face (for example, the area from the chest up) of the examinee taking the test using the examinee terminal 20. Microphone 27 collects sound according to instructions from the control unit 21 and acquires audio data, and stores the acquired audio data in the storage unit 22. Camera 26 and microphone 27 may be built into the examinee terminal 20 or they may be externally attached to the examinee terminal 20. Multiple cameras 26 and microphones 27 may also be provided.

[0022] The operator terminal 40 has the same configuration as the examinee terminal 20, so its explanation will be omitted. Note that the operator terminal 40 may not have a camera or microphone.

[0023] Figure 3 is an explanatory diagram showing an example of the record layout of the examinee DB 12a stored in the server 10. The examinee DB 12a is a database that stores information of examinees who have registered to take an online exam provided by the server 10. The examinee DB 12a is prepared, for example, for each online exam or for each exam period specified for an online exam. In the example in Figure 3, the examinee DB 12a is stored in the storage unit 12, associating the exam ID assigned to each online exam with the exam period for that online exam.

[0024] The examinee DB12a shown in Figure 3 includes columns such as examinee ID, examinee information, pre-exam information, immediate post-exam information, exam information, and exam information, and stores various types of information associated with the identification information (examinee ID) assigned to each examinee. The examinee information column stores information about the examinee, such as the examinee's name, date of birth, address or location, contact information, and authentication information used for login when taking the online exam. The pre-exam information column stores information that is registered in advance before the online exam date (exam period). The pre-exam information is information related to examinee authentication using official documents performed in advance, and includes a photograph of the official document, a photograph of the examinee's face, and the result of examinee authentication. The official document used for examinee authentication is an official document with a photograph, such as a driver's license, My Number card, residence card, or special permanent resident certificate. The immediate post-exam information column stores information that is registered before the start of the online exam on the exam day (the day of the exam). The pre-exam information includes images of the examinee's face and video footage of the examination environment (indoors) taken by the examinee terminal 20 immediately before the start of the exam, as well as the results of examinee authentication performed based on the images of the examinee's face. For example, the video footage of the examination environment can be a video of the area above and below the desk used for the exam, and the interior of the room used for the exam, taken for a predetermined period (e.g., 30 seconds). The in-exam information column stores information collected by the examinee terminal 20 during the exam. The in-exam information includes video footage of the examinee's face (e.g., the area from the chest up) taken during the exam, audio data of the room collected during the exam, and cursor position data detected by the pointing device 24a during the exam. The cursor position data is data showing the results of tracking the position of the cursor on the exam screen. Note that the cursor position data may also be, for example, the time period when the cursor position was outside the exam screen (the time when it moved outside the exam screen and the time when it returned to the exam screen from outside the exam screen). The exam information column stores information related to the exam. The examination information includes the examination date, answer data, examination results, whether or not cheating occurred, and the operator's verification results. The examination date may be a year, month, and day, or it may be the start and end dates of the examination.The answer data is the answer data to the exam questions entered by the examinee via the examinee terminal 20, and the exam result is the pass or fail judgment (pass or fail) based on the answer data. The presence or absence of cheating is the result of the server 10's determination of whether or not cheating occurred using the exam information, and the operator's confirmation result is the result of the operator confirming whether or not cheating occurred based on the server 10's determination of cheating. Note that confirmation by the operator is performed only if the server 10 determines that cheating occurred, so the operator's confirmation result is stored only if the server 10's determination result is that cheating occurred. The contents stored in the examinee DB 12a are not limited to the example shown in Figure 3, and various types of information necessary for the online exam may be stored. For example, if the examinee terminal 20 acquires the examinee's recorded video, room audio, and screen data including the cursor position as exam information, the screen data may be stored as exam information. Also, the examinee DB 12a may be divided into multiple DBs and each piece of information may be stored there, and some information may be registered in the DBs of other servers. For example, exam information and / or exam information may be stored on other servers in association with the examinee ID.

[0025] Figure 4 is an explanatory diagram showing an example configuration of the learning model 12M. The learning model 12M shown in Figure 4A is trained to take video data of the examinee, audio data of the room, and cursor position data tracked by the examinee's terminal 20 during the online exam as input, perform calculations to estimate whether or not the examinee has cheated based on each input data, and output the result of the calculation. The learning model 12M is constructed using algorithms such as CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), Transformer, decision tree, random forest, and SVM (Support Vector Machine), and may be constructed by combining multiple algorithms.

[0026] The learning model 12M has an input layer, a hidden layer, and an output layer. The input layer has multiple input nodes, through which the examinee's video data, room audio data, and cursor position data are input. The hidden layer uses various functions and thresholds to calculate output values ​​from each data input via the input layer, and outputs the calculated output values ​​to the output layer. The output layer has multiple output nodes. Each output node is associated with one of the following states: cheating due to gaze direction, cheating due to room audio, cheating due to cursor position, and normal (no cheating). Each output node outputs the probability (confidence level) that the associated state should be determined to be true. The output value of each output node is, for example, a value between 0 and 1, and the sum of the probabilities output from each output node is 1 (100%).

[0027] Server 10 identifies the output node that produced the highest output value (confidence level) among the output values ​​from each output node in the learning model 12M described above, and identifies the state associated with the identified output node as the state of the examinee to be estimated. Note that instead of having multiple output nodes that output confidence levels for each state, the learning model 12M may also be configured to have a single output node that outputs the state with the highest confidence level.

[0028] The learning model 12M is generated by machine learning using training data that associates training video data, audio data, and cursor position data with correct labels indicating the examinee's state (presence and type of cheating). For example, training data is generated by acquiring video of the examinee's face (e.g., the area from the chest up), audio of the room where the examinee is taking the exam, and the position of the cursor operated by the examinee during an online exam, and then assigning the examinee's state to each of the acquired data. Alternatively, training data may be generated by assigning the examinee's state to video of the examinee, audio of the room, and cursor position data acquired from an examinee taking a simulated online exam, or an examinee in a situation similar to an online exam. The examinee's state can be a label determined by an evaluator who can determine the presence or absence of cheating based on each examinee's video data, audio data, and cursor position data. The training data thus generated is stored in a training DB (not shown) prepared in the memory unit 12, for example, and used during the learning process of the learning model 12M.

[0029] The learning model 12M learns to take video data, audio data, and cursor position data from the training data as input, and adjust the output value from the output node corresponding to the state indicated by the correct label to approach 1, while the output values ​​from other output nodes approach 0. During the learning process, the learning model 12M performs calculations based on the input video data, audio data, and cursor position data to calculate the output value from each output node. The learning model 12M then compares the calculated output value of each output node with the value corresponding to the correct label (1 for output nodes corresponding to the state indicated by the correct label, and 0 for other output nodes) and optimizes the parameters used in the calculation process so that each output value approximates the value corresponding to the correct label. The parameters to be optimized are the weights (coupling coefficients) between nodes in the learning model 12M, and optimization methods such as backpropagation and steepest descent can be used. This provides a learning model 12M that, when video data, audio data, and cursor position data collected by the examinee's terminal 20 during an online exam are input, estimates whether and what type of cheating occurred by the examinee and outputs the estimation result.

[0030] The learning model 12M may be trained on the server 10, or on other learning devices. The trained learning model 12M generated by training on other learning devices is downloaded from the learning device to the server 10, for example, via the network N or recording medium 10a, and stored in the storage unit 12. The learning model 12M is not limited to the configuration shown in Figure 4. For example, the learning model 12M may be configured to take video data of the examinee and audio data of the room collected during the online exam as input, and output confidence levels for three states: cheating due to gaze direction, cheating due to room audio, and normal. Furthermore, the states associated with each output node are not limited to the example in Figure 4, and may include other types of cheating that can be determined from the examinee's video, room audio, and cursor position. Furthermore, the states associated with each output node may include various states related to the examinee's behavior and the examination environment, such as whether or not cheating is occurring, whether or not the examinee is away from their seat, whether or not there are people other than the examinee, and whether or not there is noise. Furthermore, the process of determining whether or not cheating is occurring due to the cursor position based on the cursor position data may be performed in a rule-based configuration. For example, by setting a threshold time for determining whether cheating has occurred when the cursor is outside the test screen, the time the cursor is outside the test screen during the test can be measured, and if the measured time exceeds the threshold, it can be determined that cheating has occurred (or is suspected).

[0031] Figure 4B is an explanatory diagram showing another example configuration of the learning model. When the server 10 acquires the examinee's video recording, room audio, and cursor position from the examinee terminal 20 as a single screen data, the learning model 12Ma shown in Figure 4B may be used to estimate whether or not the examinee has cheated. The learning model 12Ma shown in Figure 4B is trained to take screen data (data including the examinee's video data, room audio data, and cursor position data) collected by the examinee terminal 20 during the online exam as input, estimate whether or not the examinee has cheated based on the input screen data, and output the estimation result. Although the input data of the learning model 12Ma is different from that of the learning model 12M, the output values ​​from each output node are the same as those of the learning model 12M. Even when using the learning model 12Ma shown in Figure 4B, the presence and type of cheating by the examinee can be estimated. Furthermore, the learning models may include separate models for estimating whether or not a test-taker has cheated based on the test-taker's recorded video, for estimating whether or not a test-taker has cheated based on the room's audio, and for estimating whether or not a test-taker has cheated based on the cursor position.

[0032] The following describes the processing related to online examinations using the online examination system of this embodiment. In the system of this embodiment, examinees perform examinee authentication in advance using an official identification document. In addition, examinees perform examinee authentication using a photograph of their face immediately before taking the exam, and can start the exam if authenticated. Figure 5 is a flowchart showing an example of the pre-examination examinee authentication process, and Figure 6 is an explanatory diagram showing an example screen on the examinee terminal 20. In Figure 5, the processing performed by the examinee terminal 20 is shown on the left, the processing performed by the server 10 is shown in the center, and the processing performed by the authentication server 30 is shown on the right. Note that the examinee terminal 20 used for pre-examination examinee authentication using an official identification document and the examinee terminal 20 used for examinee authentication using a photograph of the examinee immediately before taking the exam and for taking the exam may be the same terminal or different terminals. For example, an examinee may use their smartphone for pre-examination examinee authentication and their personal computer for examinee authentication immediately before taking the exam and for taking the exam.

[0033] In the system of this embodiment, the control unit 21 of the examinee terminal 20 accesses the online examination site 12S according to the operation input from the examinee via the input unit 24 (S11). After applying for the online examination, the examinee obtains a pre-examination URL (Uniform Resource Locator) from the examination administration company via an examination guidance email or the like. The control unit 21 launches the browser 22B and accesses the online examination site 12S based on the obtained URL.

[0034] The control unit 11 of the server 10 transmits the pre-authentication screen of the webpage accessed from the examinee terminal 20, in this case the online examination site 12S, to the examinee terminal 20 (S12). The control unit 21 of the examinee terminal 20 receives the pre-authentication screen from the server 10 and displays it on the display unit 25 (S13). Figure 6 shows an example of the pre-authentication screen, which displays the examination type, examination period, examinee's name, and date of birth. This information is, for example, information registered in the examinee DB 12a of the server 10 when the examinee applies for the online examination. If there is information not registered in the examinee DB 12a, an input field for that information may be provided on the screen in Figure 6, and the input may be accepted at this point and registered in the examinee DB 12a. The screen in Figure 6 also has input fields R1 for an image of a photograph of a public identification document taken from the front in a plan view, input field R2 for an image of the public identification document taken from an oblique angle, and input field R3 for an image of the examinee's face.

[0035] For example, the examinee operates input field R1 on the pre-authentication screen to activate camera 26 and take a frontal image of their official identification document, and operates input field R2 to activate camera 26 and take an oblique image of their official identification document. The examinee also operates input field R3 on the pre-authentication screen to activate camera 26 and take a frontal image of their own face. The control unit 21 of the examinee terminal 20 takes images with camera 26 according to the examinee's operations as described above, and acquires the frontal and oblique images of the official identification document (first image data) and the image of the examinee (second image data) as examinee authentication data (S14). The control unit 21 determines whether or not the authentication button on the pre-authentication screen has been operated (S15). If it determines that it has not been operated (S15: NO), it returns to step S14 and continues to acquire examinee authentication data. If it determines that the authentication button has been operated (S15: YES), the control unit 21 sends the acquired examinee authentication data to the server 10 (S16). At this time, the control unit 21 transmits the test type and the test taker's name, along with test taker authentication data.

[0036] The control unit 11 of the server 10 acquires examinee authentication data from the examinee terminal 20 and stores it in the examinee DB 12a as pre-information (S17). Specifically, the control unit 11 stores the photograph of the official identification document and the photograph of the examinee in the pre-information column corresponding to the examinee ID in the examinee DB 12a corresponding to the examination ID and examination period according to the examination type. The control unit 11 sends the photograph of the official identification document and the photograph of the examinee (examinee authentication data) to the authentication server 30 and requests the execution of examinee authentication (S18).

[0037] The control unit of the authentication server 30 obtains examinee authentication data from the server 10 and, according to the authentication program, performs examinee authentication (identity verification) based on the image of the examinee's official identification document and the image of the examinee (S19), and sends the authentication result to the server 10 (S20). The control unit 11 of the server 10 obtains the authentication result from the authentication server 30 and stores it in the examinee DB 12a as the authentication result of the pre-information (S21). For example, if authenticated, "Authenticated" is stored, and if not authenticated, "Authentication Failed" is stored. The control unit 11 allows the examinee to take the exam by storing "Authenticated" in the authentication result. The control unit 11 then sends the authentication result to the examinee terminal 20 (S22), and the control unit 21 of the examinee terminal 20 obtains the authentication result from the server 10 and displays it on the display unit 25 (S23). The control unit 11 also notifies the examinee of the authentication result by generating a screen corresponding to the authentication result and sending it to the examinee terminal 20. For example, the control unit 11 generates a screen notifying authenticated examinees that examinee authentication is complete and they are permitted to take the exam, and generates a screen notifying unauthenticated examinees that authentication using a public certificate failed. Examinees who are notified of authentication failure are allowed to re-attempt examinee authentication using a public certificate, and if authentication is successful, they are permitted to take the exam.

[0038] Through the process described above, it is possible to verify that the applicant is the person listed on the official identification document before taking the online exam, by using the applicant's official identification document for authentication. By using the image of the authenticated applicant in this way for applicant authentication before the start of the exam, it becomes possible to verify the applicant's identity at the start of the exam and detect impersonation at that time. Alternatively, the image of the authenticated applicant may also be used for applicant authentication based on the applicant's image taken during the exam, in which case it becomes possible to verify the applicant's identity during the exam.

[0039] Figures 7 and 8 are flowcharts showing an example of the online examination processing procedure, and Figures 9 and 10 are explanatory diagrams showing example screens on the examinee terminal 20. In Figures 7 and 8, the processing performed by the examinee terminal 20 is shown on the left, and the processing performed by the server 10 is shown on the right. In the system of this embodiment, after applying for the online examination, or after being authenticated through prior examinee authentication, examinees receive an examination URL from the examination administration company via an examination guidance email or the like. On any examination day (online examination day) within the designated examination period, examinees take the online examination by accessing the online examination site 12S using the examination URL. Before taking the online examination (before the start of the examination on the day of the online examination), examinees take a picture of their face and send it to the server 10. The server 10 verifies that the examinee is the examinee who was authenticated through prior examinee authentication based on the captured image, and if identity verification is successful, the examinee can take the examination.

[0040] The control unit 21 of the examinee terminal 20 accesses the online examination site 12S according to the operation input from the examinee via the input unit 24 (S31). Here, the control unit 21 launches the browser 22B and accesses the online examination site 12S based on the examination URL. The control unit 11 of the server 10 sends the web page accessed from the examinee terminal 20, in this case the pre-examination authentication screen of the online examination site 12S, to the examinee terminal 20 (S32). The control unit 21 of the examinee terminal 20 receives the pre-examination authentication screen from the server 10 and displays it on the display unit 25 (S33). Figure 9 shows an example of the pre-examination authentication screen, which displays the examination type, examination period and examination date, examinee's name and date of birth. In addition to being displayed on the pre-examination authentication screen, the examinee's name and date of birth may also be entered by the examinee in the input fields provided on the pre-examination authentication screen. The screen in Figure 9 also has input fields R4 for a photograph of the examinee's face and input fields R5 for a photograph of the examination environment.

[0041] For example, the examinee activates the camera 26 by operating input field R4 on the pre-examination authentication screen and takes a frontal image of their face. The examinee also activates the camera 26 by operating input field R5 on the pre-examination authentication screen and takes video of the desk used for the exam, both above and below, as well as the room. If the examinee's terminal 20 is a portable device such as a notebook computer or tablet, the examinee takes pictures of the exam environment by changing the shooting direction of the camera 26 built into the terminal 20. If the examinee's terminal 20 is a desktop computer, and the camera 26 is an external camera attached to the terminal 20, the examinee takes pictures of the exam environment by changing the shooting direction of the camera 26. If the shooting direction of the camera 26 cannot be changed, the examinee may use a different portable examinee terminal 20 than the one used for the exam to take pictures of the exam environment and send them to the server 10. When using a different portable examinee terminal 20 to take pictures of the exam environment, the pictures may be taken before the start of the online exam or after the end of the online exam.

[0042] The control unit 21 of the examinee terminal 20 takes a photograph with the camera 26 in accordance with the examinee's operations as described above, and acquires the examinee's photographed image (third photographic data) and the photographed video of the examination environment (fourth photographic data) as data for immediate authentication (S34). The control unit 21 determines whether or not the authentication button on the immediate authentication screen has been operated (S35). If it determines that it has not been operated (S35: NO), it returns to step S34 and continues to acquire the data for immediate authentication. If it determines that the authentication button has been operated (S35: YES), the control unit 21 sends the acquired data for immediate authentication to the server 10 (S36). At this time, the control unit 21 sends the data for immediate authentication along with the examination type and the examinee's name. If the immediate authentication screen has input fields for the examinee's name and date of birth, the control unit 21 accepts the examinee's name and date of birth through the input fields and sends the entered name and date of birth, along with the examination type and the data for immediate authentication, to the server 10. In this case, server 10 can verify the identity of the examinee using the examinee's name and date of birth entered by the examinee, and the pre-examination authentication data (the examinee's photograph).

[0043] The control unit 11 of the server 10 acquires pre-examination authentication data from the examinee terminal 20 and stores it in the examinee DB 12a as pre-examination information (S37). Specifically, the control unit 11 stores the examinee's photographed image and the photographed video of the examination environment in the pre-examination information column corresponding to the examinee ID in the examinee DB 12a corresponding to the examination ID and examination period according to the examination type. Next, the control unit 11 performs examinee authentication (identity verification) based on the examinee's photographed image stored in the examinee DB 12a (S38). For example, the control unit 11 authenticates whether the person taking the exam is an examinee who has been authenticated in advance, based on the examinee's photographed image in the pre-examination information and the photographed image of the official document or the examinee's photograph in the prior information. Specifically, the control unit 11 extracts the facial feature quantities of the examinee from the examinee's photographed image in the pre-examination information and the photographed image of the official document or the examinee's photograph in the prior information, calculates the similarity of the extracted feature quantities, and authenticates that the examinee is an examinee who has been authenticated in advance if the similarity is above a predetermined value. Similarity can be measured using, for example, the correlation coefficient or cosine similarity, or a machine learning model can be used to estimate the similarity between two images. For example, a machine learning model consisting of a Convolutional Neural Network (CNN) can be used, which is trained to output the similarity between two images or a determination of whether the person in the image is the same person or not, when two images are input.

[0044] The control unit 11 stores the authentication result in the examinee DB 12a as the authentication result of the immediately preceding information (S39). The control unit 11 then determines whether authentication was successful or not (S40). If it determines that authentication was unsuccessful (S40: NO), it sends an authentication failure screen to the examinee terminal 20 (S41). The control unit 21 of the examinee terminal 20 retrieves the authentication failure screen from the server 10 and displays it on the display unit 25 (S42). Figure 10A shows an example of an authentication failure screen, which has a "Retry Authentication" button to notify the examinee that authentication has failed and instruct them to try authentication again, and a "Cancel" button to cancel the examination.

[0045] The control unit 21 of the examinee terminal 20 determines whether the "Retry Authentication" button has been pressed (S43). If it determines that the button has been pressed (S43: YES), it returns to step S33. The control unit 21 then displays the previous authentication screen again, as shown in Figure 9 (S33), and repeats the process from step S34 onwards to perform examinee authentication immediately before the exam. If the control unit 21 determines that the "Retry Authentication" button has not been pressed (S43: NO), i.e., if the "Cancel" button has been pressed, it displays a screen notifying the examinee that the exam has been canceled, and then terminates the process.

[0046] If the control unit 11 of the server 10 determines that authentication has been successful based on the examinee authentication performed immediately before the exam (S40: YES), it sends the exam start screen to the examinee terminal 20 (S44). The control unit 21 of the examinee terminal 20 retrieves the exam start screen from the server 10 and displays it on the display unit 25 (S45). Figure 10B shows an example of the exam start screen, which notifies the examinee that authentication has been successful and displays instructions for the exam. During the exam, the examinee's face (from the chest up) will be photographed, so the examinee should position the camera 26 of the examinee terminal 20 in a position where it can photograph their face. The control unit 21 may also activate the camera 26 and display the image captured by the camera 26 on the exam start screen in Figure 10B, allowing the examinee to confirm that the camera 26 is positioned correctly based on the image displayed on the exam start screen.

[0047] The control unit 21 of the examinee terminal 20 determines whether the "Start Exam" button has been pressed (S46). If it determines that the button has not been pressed (S46: NO), it waits. If the control unit 21 determines that the "Start Exam" button has been pressed (S46: YES), it starts displaying the exam screen (S47) and starts accepting answer input via the exam screen (S48). Figure 10C shows an example of an exam screen, which displays multiple questions and answer choices for each question, with checkboxes provided for each choice. In addition to multiple-choice questions like those in Figure 10C, the exam screen may also have questions that require input of text or numerical values. The screen in Figure 10C also displays images captured by the camera 26. Information on the exam screen may be transmitted (downloaded) from the server 10 to the examinee terminal 20 along with the exam start screen. In this case, the control unit 21 stores the information on the exam screen obtained from the server 10 in the storage unit 22 and displays it sequentially on the display unit 25 according to the answer input by the examinee. Furthermore, the information on the test screen may be transmitted from the server 10 to the test-taker terminal 20 according to the test-taker's input of answers. In this case, the control unit 21 retrieves the information for the next page from the server 10 and displays it on the display unit 25 each time the test-taker inputs the answers for one page.

[0048] When the online exam begins (when the exam screen is displayed), the control unit 21 starts counting down the remaining exam time using a counter (S49). The control unit 21 also starts recording video of the examinee using the camera 26 and acquiring room audio using the microphone 27 (S50). Furthermore, the control unit 21 starts acquiring the position of the cursor operated by the pointing device 24a on the exam screen (S51). The video of the examinee recorded here may be, for example, video data of one to several frames per second, and the room audio may be acquired at a predetermined sampling period (for example, the same sampling period as the recorded video). The cursor position may also be acquired at a predetermined sampling period. The control unit 21 stores the recorded video of the examinee (video data), room audio data, and cursor position data in the storage unit 22. Through the above processing, the control unit 21 can acquire in-exam data (in-exam recording data) that captures the examinee's examination situation during the exam. The control unit 21 may also acquire screen data including the recorded video data of the examinee, room audio data, and cursor position data. For example, as shown in Figure 10C, the control unit 21 may acquire screen data of a screen that displays the captured image of the examinee, a recorded video including the room's audio, and the cursor position on the examination screen.

[0049] When the control unit 21 acquires the cursor position at a predetermined sampling period, it determines whether the cursor is within the test screen based on the acquired cursor position and the test screen displayed on the display unit 25 (S52). If the control unit 21 determines that the cursor is not within the test screen (S52: NO), i.e., the cursor has moved outside the test screen, it measures the time during which the cursor has been outside the test screen (S53). In other words, the control unit 21 measures the time the cursor is outside the test screen. If the control unit 21 determines that the cursor is within the test screen (S52: YES), it skips step S53.

[0050] The control unit 21 determines whether or not to terminate the online exam (S54). If it determines not to terminate the exam (S54: NO), it returns to step S52. Based on the sequentially acquired cursor position, the control unit 21 continues to determine whether the cursor is within the exam screen and, if it determines that the cursor is outside the exam screen, continues to measure the time the cursor has been outside the exam screen. The control unit 21 determines to terminate the online exam when the remaining exam time, which is being counted down, reaches 0, or when the "End Exam" button on the exam screen is pressed. The control unit 21 may also determine to terminate the online exam if a predetermined amount of time has elapsed while the cursor has been outside the exam screen, on the grounds that cheating by the examinee has occurred.

[0051] If the control unit 21 determines that the test is over (S54: YES), it displays a screen notifying the test that the test has ended and terminates the test, then sends the answer data entered via the test screen, the test taker's video data, the room's audio data, and cursor position data (test data) acquired during the test to the server 10 (S55). Note that the test data may include the time measured when the cursor leaves the test screen. The control unit 21 sends the answer data and test data along with the test type, the test taker's name, and the test date. The control unit 11 of the server 10 acquires the answer data and test data from the test taker terminal 20 and stores them in the test taker DB 12a as test information or test information (S56). Specifically, in the test taker DB 12a, the control unit 11 stores the test taker's video data, the room's audio data, and the cursor position data in the test information column corresponding to the test taker ID. The control unit 11 also stores the test date and answer data in the test information column corresponding to the test taker ID.

[0052] Through the process described above, a facial image of the examinee is taken again immediately before taking the online exam, and examinee authentication is performed based on the obtained image, thereby confirming that the examinee attempting to take the exam is a pre-authenticated examinee. Therefore, impersonation by another person can be detected at the start of the exam. In addition to examinee authentication based on the examinee's image obtained from the examinee terminal 20, the server 10 may also perform a process to determine whether the examination environment conforms to the rules based on video footage of the examination environment. For example, the control unit 11 may detect items on the desk based on video footage of the desk, determine whether the detected items are used during the exam, and notify the examinee that the examination environment is unsuitable if they are not used during the exam. The control unit 11 may also detect the presence of items that could potentially lead to cheating or other fraudulent activities based on video footage of the area under the desk and the room, and if items that could potentially lead to cheating are detected, notify the examinee that the examination environment is unsuitable. Examinees who receive such a notification repeat the process of taking photos of the examination environment and the server 10's determination process until the server 10 determines that the examination environment is appropriate. If an online exam becomes available after it has been determined that the testing environment is suitable, the candidate will be able to take the online exam in that suitable environment.

[0053] Furthermore, by acquiring images of the examinee, audio data from the room, and cursor position data during the online exam, it is possible to determine whether or not the examinee cheated during the exam using the acquired data. Therefore, it is possible to detect the occurrence of cheating or other fraudulent activities by the examinee. The control unit 11 of the server 10 scores the answer data acquired from the examinee terminal 20 to determine whether the examinee passed or failed, and stores the pass / fail result in the examinee DB 12a.

[0054] The following describes the process by which server 10 determines whether or not a test-taker has cheated, based on the test-taker's in-test information after they have finished taking the exam. Figure 11 is a flowchart showing an example of the cheating detection process, and Figure 12 is an explanatory diagram showing an example screen on operator terminal 40. In Figure 11, the processes performed by server 10 are shown on the left, and the processes performed by operator terminal 40 are shown on the right.

[0055] The control unit 11 of server 10 performs a determination process to determine whether or not cheating or other dishonest conduct occurred during an online exam for examinees who have completed the exam and whose exam data (examinee's recorded video data, room audio data, cursor position data) is stored in examinee DB 12a. The control unit 11 reads the exam data of one examinee from examinee DB 12a (S61). Based on the read exam data, the control unit 11 determines whether or not the examinee committed any dishonest conduct (S62). Here, the control unit 11 inputs the examinee's recorded video data, room audio data, and cursor position data included in the exam data into the learning model 12M, and obtains the presence or absence and type of dishonest conduct as output values ​​from the learning model 12M. Alternatively, if the control unit 11 obtains screen data including the examinee's recorded video data, room audio data, and cursor position data, it may input the screen data into the learning model 12Ma, and obtain the presence or absence and type of dishonest conduct as output values ​​from the learning model 12Ma.

[0056] Furthermore, the process for determining whether or not cheating has occurred is not limited to processing using the learning model 12M. For example, for cheating caused by cursor position based on cursor position data, rule-based processing may be used. For example, if the time the cursor is outside the test screen exceeds a predetermined time, it may be determined that cheating has occurred due to the cursor position. Alternatively, if the number of times the cursor is outside the test screen exceeds a predetermined number, it may be determined that cheating has occurred due to the cursor position. In addition, the examinee's gaze direction may be tracked based on the examinee's recorded video, and the presence or absence of cheating may be determined based on the trajectory of the gaze direction. Moreover, the presence or absence of speech from someone other than the examinee may be detected based on the room's audio data, and the presence or absence of cheating may be determined according to the presence or absence of speech from someone other than the examinee.

[0057] The control unit 11 stores the result of the determination of whether or not cheating occurred in the examinee DB 12a, associating it with the examinee's examinee ID (S63). The control unit 11 determines whether or not the determination process has been completed for all examinees subject to determination (S64). If it determines that it has not been completed (S64: NO), it returns to step S61 and performs steps S61 to S63 for the unprocessed examinees. As a result, for each examinee subject to determination, the presence or absence of cheating is determined based on the in-test data, and the determination result is stored in the examinee DB 12a. Alternatively, the presence or absence of cheating may be determined only for examinees who passed. In this case, the control unit 11 reads the in-test data of the examinees who passed in step S61 and performs steps S62 to S63, and then performs step S64 with the passed examinees as the subjects of determination. If the control unit 11 determines that the above process has been completed for all examinees subject to determination (S64: YES), it generates a list of examinees determined to have cheated (cheating list) (S65).

[0058] Figure 12 shows an example of a cheating list. The list in Figure 12 displays information for candidates who were found to have cheated, including the exam date, candidate ID, type of cheating (details of cheating), and confidence level, for both successful and unsuccessful candidates. The confidence level can be, for example, the confidence level output from the learning model 12M. The list in Figure 12 also displays thumbnail images of the candidate's video recordings included in the exam data, and a play button is provided to instruct playback of the exam data. The thumbnail image may be, for example, the first image from the time period in the candidate's video recording where cheating was determined, or an image from a predetermined time before that time period. In step S62, the control unit 11 determines whether or not cheating occurred and identifies the time period in which cheating was determined, and can generate a thumbnail image based on the image from the identified time period. The play button is set to links to the candidate's video recordings, room audio data, and cursor position data included in the exam data, and by operating the play button, the candidate's video recordings, room audio, and cursor position can be viewed. Furthermore, the system may be configured to allow playback of all video footage, room audio data, and cursor position data collected during the test, or to allow playback of video footage, room audio data, and cursor position data for the time period in which cheating was determined. In addition, the list in Figure 12 is provided with "Cheating detected" and "No cheating detected" buttons for the operator to input the results of their confirmation of whether or not cheating occurred. In this embodiment, as shown in Figure 12, information on examinees suspected of cheating is notified to the operator not only for those who passed but also for those who failed, but the system may be configured to notify only those examinees suspected of cheating. In this case, in step S65, the control unit 11 generates a list of examinees who passed but were determined to have cheated, based on the test results stored in the examinee DB 12a, and sends it to the operator terminal 40. The server 10 may be configured to notify the operator terminal 40 only of those who passed but were determined to have cheated, or of all examinees who were determined to have cheated.

[0059] The control unit 11 transmits the generated cheating list (detection result) to the operator terminal 40 (S66), and the control unit of the operator terminal 40 retrieves the cheating list from the server 10 and displays it on the display unit (S67). The operator checks the in-test data of each examinee in the cheating list to determine whether or not cheating occurred, and inputs the confirmation result by operating the "Cheating Found" button or "Cheating Not Found" button. The control unit of the operator terminal 40 receives the input of the confirmation result of whether or not cheating occurred through the operator's operation via the input unit (S68), and after receiving the confirmation result for each examinee, transmits the confirmation result of whether or not cheating occurred for each examinee to the server 10 (S69). When the control unit 11 of the server 10 obtains the confirmation result of whether or not cheating occurred for each examinee from the operator terminal 40, it stores the operator's confirmation result in the examinee DB 12a, associating it with each examinee's examinee ID (S70). This allows the operator to verify the appropriateness of the determination of whether or not fraudulent activity has occurred, which is made using the learning model 12M on the server 10, and to associate the operator's judgment with the verification result.

[0060] Furthermore, the operator terminal 40 may send the operator's confirmation results to the server 10 only for examinees whose determination of whether or not cheating occurred differs from the operator's confirmation results. Since the server 10 notifies the operator terminal 40 of the information of examinees that it has determined to have cheated, the operator terminal 40 may send confirmation results only for examinees that the operator has determined not to have cheated. In this case, the control unit 11 of the server 10 obtains from the operator terminal 40 the examinee ID of the examinee that the server 10 has notified it to have cheated, but which the operator has determined not to have cheated, and the confirmation result that no cheating occurred for that examinee. The server 10 then stores "no cheating occurred" as the operator confirmation result corresponding to the obtained examinee ID.

[0061] Through the process described above, in this embodiment, it is possible to determine whether or not a test-taker has cheated using the data acquired during the online examination. Furthermore, by displaying a list of test-takers suspected of cheating on the operator terminal 40, the online examination operating company can be notified. The online examination operating company can then have the operator review each test-taker's data during the exam, reconfirm whether or not they cheated, and register the confirmation results in the server 10 (test-taker DB 12a). The online examination operating company can then take further action based on the operator's confirmation results. For example, they can revoke the passing grade of a test-taker who is confirmed to have cheated, and confirm the passing grade of a test-taker who is confirmed not to have cheated.

[0062] In this embodiment, identity verification is performed in advance using official identification documents, and then again using a photograph taken immediately before the start of the exam, thereby preventing impersonation by others. Furthermore, cheating can be detected using data collected during the exam, thus preventing candidates from passing due to cheating.

[0063] In this embodiment, the system uses a learning model 12M to determine whether or not cheating is occurring due to gaze direction, room audio, or cursor position, based on the examinee's video recording, room audio data, and cursor position data acquired during the online exam. Alternatively, for example, server 10 may perform gaze direction tracking based on the examinee's video recording and determine whether or not cheating is occurring due to gaze direction based on the movement of the eyes. Furthermore, by recording the examinee's speech in advance or before the start of the online exam, the system may determine whether or not cheating is occurring due to room audio based on whether or not the room audio data acquired during the online exam includes speech from someone other than the examinee. Various methods and systems may be used to determine whether or not cheating is occurring due to gaze direction, room audio, or cursor position.

[0064] (Embodiment 2) This section describes an online examination system that determines whether or not a test-taker has cheated during the online examination. Since the online examination system of this embodiment can be implemented using the same equipment as the online examination system of Embodiment 1, a description of its configuration will be omitted.

[0065] Figure 13 is a flowchart showing an example of the processing procedure for an online examination in Embodiment 2. In Figure 13, the processing performed by the examinee terminal 20 is shown on the left, the processing performed by the server 10 is shown in the center, and the processing performed by the operator terminal 40 is shown on the right. The processing shown in Figure 13 is the same as the processing shown in Figures 7 and 8, but with steps S81 to S94 added instead of steps S52 to S56. The explanation of the same steps as in Figures 7 and 8 is omitted. Also, in Figure 13, the illustration of steps S31 to S46 in Figures 7 and 8 is omitted.

[0066] In this embodiment, after processing in step S51, the control unit 21 of the examinee terminal 20 transmits the examinee's recorded video data, room audio data, and cursor position data (exam data) acquired after the start of the online exam to the server 10 (S81). The control unit 21 transmits the exam data along with the exam type and the examinee's name. The control unit 21 is configured to transmit the exam data acquired sequentially during the examinee's exam to the server 10 at predetermined time intervals. It determines whether a predetermined time has elapsed since the exam data was transmitted to the server 10 (S82). If it determines that the predetermined time has elapsed (S82:YES), it returns to step S81 and transmits the exam data accumulated since the previous transmission process to the server 10 (S81). If the control unit 11 determines that the predetermined time has not elapsed (S82:NO), it determines whether to terminate the online exam (S83). If it determines not to terminate the exam (S83:NO), it returns to step S82. Therefore, each time a predetermined amount of time has elapsed, the control unit 11 repeats the process of sending the test data accumulated since the previous transmission process to the server 10.

[0067] The control unit 11 of the server 10 acquires test data from the examinee terminal 20 and stores it in the examinee DB 12a as test information (S84). Specifically, the control unit 11 stores the examinee's recorded video, room audio data, and cursor position data in the test information column corresponding to the examinee ID in the examinee DB 12a. Based on the test data stored in the examinee DB 12a, the control unit 11 determines whether or not the examinee has cheated (S85). The process in step S85 can be the same as the process in step S62 in Figure 11. The control unit 11 stores the result of the determination of whether or not cheating occurred in the examinee DB 12a, associated with the examinee's examinee ID (S86). The control unit 11 may store the determination result (cheating occurred) only if it determines that cheating occurred, or it may store the determination result associated with the date and time the determination process was performed.

[0068] The control unit 11 determines whether or not cheating occurred in the judgment process in step S85 (S87). If it determines that cheating occurred (S87: YES), it transmits the examinee's examinee ID, the details of the cheating (details of the cheating), the degree of confidence, the examinee's test data, etc., to the operator terminal 40 to notify it of the occurrence of cheating (S88). When the control unit of the operator terminal 40 obtains information on the examinee who has been determined to have cheated from the server 10, it adds the obtained examinee's information (information on the cheater) to a cheating list, for example, as shown in Figure 12, and displays it on the display unit (S89). This allows the operator to be notified of the examinee suspected of cheating via the operator terminal 40. If the operator terminal 40 is equipped with a warning lamp or a speaker that outputs a warning sound, the control unit may notify the operator by lighting or flashing the lamp, or by outputting a warning message from the speaker, etc., when it is notified by the server 10 of the occurrence of cheating.

[0069] The operator checks the in-test data of the notified examinee to determine whether or not cheating occurred and inputs the confirmation result. The control unit of the operator terminal 40 receives the input of the confirmation result of whether or not cheating occurred (S90) and sends the received confirmation result to the server 10 (S91). The control unit 11 of the server 10 obtains the confirmation result from the operator terminal 40 for the examinee notified in step S88 and stores the operator's confirmation result in the examinee DB 12a, associating it with the examinee's examinee ID (S92). This makes it possible to associate the confirmation result determined by the operator with the determination result of whether or not cheating occurred, which was determined using the learning model 12M. If the control unit 11 of the server 10 determines that there was no cheating (S87: NO), it skips steps S88 and S92. If the control unit 11 obtains a confirmation result of cheating from the operator terminal 40, it may be configured to terminate (cancel) the examinee's examination at this point, or it may be configured to send a warning message to the examinee's examinee terminal 20.

[0070] If the control unit 21 of the examinee terminal 20 determines that the exam is over (S83: YES), it terminates the exam and sends the answer data entered via the exam screen to the server 10 (S93). The control unit 21 sends the answer data along with the exam type, the examinee's name, and the exam date. The control unit 11 of the server 10 retrieves the answer data from the examinee terminal 20 and stores it in the examinee DB 12a as exam information (S94). Here, the control unit 11 stores the exam date and answer data in the exam information column corresponding to the examinee ID in the examinee DB 12a. After that, the control unit 11 may score each examinee's answer data to determine pass or fail and store the pass / fail result in the examinee DB 12a.

[0071] Through the process described above, in this embodiment, the presence or absence of cheating by examinees is automatically determined during the online exam, allowing operators to identify examinees who should be checked for cheating in real time. When cheating or other cheating is suspected, the operator is notified, so the operator only needs to check the exam data of the examinee suspected of cheating. Furthermore, when the operator confirms that an examinee has cheated, the server 10 is notified, enabling the online exam operator to take prompt action against the examinee who has cheated.

[0072] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of this disclosure is indicated by the claims, not in the sense described above, and all modifications within the sense and scope equivalent to the claims are intended.

[0073] The matters described in each embodiment can be combined with each other. Furthermore, the independent and dependent claims described in the claims can be combined with each other in any combination, regardless of the form of reference. In addition, the claims use a form in which claims referencing two or more other claims (multi-claim form), but are not limited to this. A form in which multi-claims referencing at least one multi-claim (multi-multi-claim) may also be used. [Explanation of symbols]

[0074] 10 servers 11 Control Unit 12 Storage section 13 Communications Department 20 Examinee terminals 21 Control Unit 22 Memory section 23 Communications Department 24 Input section 24a Pointing device 25 Display section 26 cameras 27 Mike 30 Authentication Server 40 Operator terminals

Claims

1. Prior to the online exam date, we obtain two sets of photographic data: a first set of photographs of the applicant's official photo ID and a second set of photographs of the applicant. If the applicant's identity is verified based on the first and second photographic data, permission to take the online examination will be granted. Obtain third-party photographic data of the aforementioned test takers who were permitted to take the online exam on the day of the exam. An information processing method in which a computer performs the processing.

2. The examinee is authenticated based on the third photographic data and the first or second photographic data. The authentication result is stored in the memory unit in association with the identification information that identifies the examinee. The information processing method according to claim 1, wherein the processing is performed by the computer.

3. Before the start of the online exam on the day of the exam, a fourth set of photographic data will be acquired, capturing images of the examinee's desk (both above and below it) and the room. The information processing method according to claim 1 or 2, wherein the computer performs the processing.

4. During the online examination, the camera installed on the examinee's terminal device captures the examinee's examination status and acquires in-test photographic data. The information processing method according to claim 1 or 2, wherein the computer performs the processing.

5. By inputting the aforementioned in-test photography data into a trained model that has been trained to output information regarding cheating when photography data is input, information regarding the examinee's cheating in the aforementioned in-test photography data is obtained. Based on the information obtained regarding the aforementioned misconduct, the presence or absence of misconduct by the examinee is detected. The detection results are output to the operator's terminal device. The information processing method according to claim 4, wherein the computer performs the processing.

6. When cheating by the examinee is detected, the operator's terminal device outputs information regarding the cheating, the in-test photographic data in which the cheating was detected, and identification information to identify the examinee, in association with each other. The information processing method according to claim 5, wherein the computer performs the processing.

7. The operator's terminal device outputs the in-test photography data of each examinee, along with the information regarding the cheating activity obtained based on the in-test photography data, in association with identification information that identifies each of the multiple examinees. The information processing method according to claim 5, wherein the computer performs the processing.

8. The learning model outputs information indicating one of the following: that there is no cheating by the examinee in the input photographic data; that cheating is suspected due to the examinee's gaze direction; that cheating is suspected due to the position indicated by the pointing device operated by the examinee; or that cheating is suspected due to the sound in the room. The information processing method according to claim 5.

9. Prior to the online exam date, we obtain two sets of photographic data: a first set of photographs of the applicant's official photo ID and a second set of photographs of the applicant. If the applicant's identity is verified based on the first and second photographic data, permission to take the online examination will be granted. Obtain third-party photographic data of the aforementioned test takers who were permitted to take the online exam on the day of the exam. A program that instructs a computer to perform a process.

10. In an information processing device having a control unit, The control unit, Prior to the online exam date, we obtain two sets of photographic data: a first set of photographs of the applicant's official photo ID and a second set of photographs of the applicant. If the applicant's identity is verified based on the first and second photographic data, permission to take the online examination will be granted. Obtain third-party photographic data of the aforementioned test takers who were permitted to take the online exam on the day of the exam. Information processing device.

Images