CN117058612B - Online examination cheating identification method, electronic equipment and storage medium - Google Patents
Online examination cheating identification method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117058612B CN117058612B CN202310896905.0A CN202310896905A CN117058612B CN 117058612 B CN117058612 B CN 117058612B CN 202310896905 A CN202310896905 A CN 202310896905A CN 117058612 B CN117058612 B CN 117058612B
- Authority
- CN
- China
- Prior art keywords
- identified
- examinee
- cheating
- display screen
- identification model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000006399 behavior Effects 0.000 claims abstract description 96
- 238000001514 detection method Methods 0.000 claims abstract description 34
- 230000002159 abnormal effect Effects 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 230000000007 visual effect Effects 0.000 claims description 112
- 238000012549 training Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 7
- 238000005070 sampling Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 244000144985 peep Species 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 208000008918 voyeurism Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an online examination cheating identification method, electronic equipment and a storage medium, and relates to the technical field of computer vision. The method comprises the following steps: detecting that the deflection angle of the normal of the face of the examinee to be identified exceeds a preset threshold value through a shot image, intercepting a plurality of images of the examinee to be identified in preset time before and after the time point of the shot image, and analyzing the acquired synergy of the operation behaviors of the I/O equipment of the examinee to be identified and the input content; substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model; if the output result of the cheating identification model shows that the behaviors of the examinee to be identified are abnormal, outputting a cheating detection signal by a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behaviors or not according to the output cheating detection signal. Therefore, the capability of identifying and preventing cheating in the on-line examination can be improved, and the fairness and fairness of the on-line examination are further ensured.
Description
Technical Field
The application relates to the technical field of computer vision, in particular to an online examination cheating identification method, electronic equipment and a storage medium.
Background
With the continuous development of education informatization, more and more examinations gradually break through the limitation of regions, and the examination is changed from offline to online. How to identify and prevent cheating in the on-line examination, ensure fairness and fairness of the examination, and provide new challenges for administrators organizing the examination.
In the prior art, a camera is arranged in front of an examiner, the operation behavior of the examiner is monitored in real time through the camera, the real-time monitored content is sent to the background, and the staff monitors the examination picture of the examiner in real time in the background. The examination pictures that the staff needs to monitor are usually many, and examination monitoring pictures are also very limited, so that the mode of manually monitoring examination pictures is very limited, and when the action range of the examiner is small, the examination pictures are not easy to be found by the staff monitored in the background when the head of the examiner peeps the display screens of other examiners in the same field.
Therefore, the ability of identifying and preventing cheating in the on-line examination is improved, and the fairness and fairness of the on-line examination are further ensured.
Disclosure of Invention
In view of the above, the present invention provides an online examination cheating identification method, an electronic device and a storage medium, so as to solve the problem in the prior art that the online examination background staff has poor ability of identifying and preventing examination cheating when monitoring in real time.
In order to solve the above problems, a first aspect of the present invention provides an online examination cheating identification method, which includes:
detecting that the deflection angle of the normal line of the face of the examinee to be identified exceeds a preset threshold value through the shot image, and simultaneously detecting that the visual focus of the examinee to be identified is separated from a display screen in front of the examinee to be identified, and when the visual focus of the examinee to be identified falls into the display screen in front of other examinees, intercepting a plurality of images of the examinee to be identified in preset time before and after the time point of the shot image, and analyzing the acquired synergies of the operation behaviors of the I/O equipment of the examinee to be identified and the input content;
substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model;
if the output result of the cheating identification model shows that the behavior of the examinee to be identified is abnormal, displaying a cheating detection signal on a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behavior or not according to the displayed cheating detection signal;
If yes, intercepting first content of the display screen of the examinee to be identified and second content of the display screen of other examinees in front of which the visual focus of the user falls, judging similarity between the first content and the second content, and if the similarity is higher than a preset threshold, judging that the examinee to be identified has cheating behaviors.
Optionally, the detecting, by the captured image, that the deflection angle of the face normal of the examinee to be identified exceeds a preset threshold includes:
the preset threshold value is a standard angle interval between the normal line of the face of the examinee to be identified when the examinee looks at the display screen and the plane where the camera is located.
Optionally, the detecting that the visual focus of the candidate to be identified is separated from the display screen in front of the candidate to be identified includes:
acquiring a visual fixation angle of a shot image, and acquiring coordinates of a visual focus falling under a coordinate system of a plane expansion of a display screen of an examinee to be identified according to the visual fixation angle;
and if the coordinates of the visual focus falling under the coordinate system of the display screen after the plane expansion are judged not to be in the coordinate range of the real display screen, separating the visual focus of the examinee to be identified from the display screen in front of the display screen.
Optionally, the visual focus of the candidate to be identified falls into the display screen in front of other candidates, including:
if the visual focus of the examinee to be identified is judged to be in the coordinate range of the display screen in front of other examinees in the coordinate system after the plane of the display screen is expanded, the visual focus of the examinee to be identified is judged to be in front of the display screen of other examinees.
Optionally, the operation behavior of the I/O device of the candidate to be identified includes at least one of clicking a mouse operation and keyboard typing operation;
the input content includes input content displayed on the display screen.
Optionally, the pre-trained cheating identification model includes:
preprocessing the photo of the examinee to be identified, and establishing a face feature basic feature library;
recording normal operation behaviors of the to-be-identified examinee by using the I/O equipment, and determining an angle threshold value of a face normal of the to-be-identified examinee in a normal operation state and a coordinate value of a sight gaze angle of the to-be-identified examinee in the normal operation state based on the recorded normal operation behaviors of the to-be-identified examinee;
establishing a cheating identification model based on the face feature basic feature library, the angle threshold value of the face normal and the coordinate value of the sight-line fixation angle;
Selecting an operation behavior of I/O equipment used by an examinee to be identified within a fixed time as a sample training set, and training the cheating identification model to obtain a trained cheating identification model.
Optionally, if the output result of the cheating identification model indicates that the behavior of the candidate to be identified is abnormal, inputting a cheating detection signal to the display screen of the candidate to be identified, and judging whether the candidate to be identified has suspected cheating behavior according to the input cheating detection signal, including:
if the tolerance value of the output result of the cheating identification model exceeds a preset range, indicating that the behavior of the examinee to be identified is abnormal;
after the water ripple cheating detection signal is input to the display screen of the examinee to be identified, the operation behavior of the I/O equipment of the examinee to be identified acquired in the current state is analyzed again to be cooperated with the input content;
substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model, and judging whether the candidate to be identified has suspected cheating behaviors or not.
Optionally, after the cheating behavior of the candidate to be identified is considered, the method further includes:
And exciting an alarm signal, carrying out trace-keeping registration on the lightning and plagiarism parts, and reporting to the test system.
Optionally, the obtaining the photographed image includes:
and obtaining a camera video of the examinee to be identified, and sampling the camera video according to a preset sampling period to obtain a shot image.
A second aspect of the present invention provides an electronic device comprising:
a processor;
a memory;
the memory is used for storing a program of the online examination cheating identification method, and the program performs the following operations when being read and executed by the processor:
detecting that the deflection angle of the normal line of the face of the examinee to be identified exceeds a preset threshold value through the shot image, and simultaneously detecting that the visual focus of the examinee to be identified is separated from a display screen in front of the examinee to be identified, and when the visual focus of the examinee to be identified falls into the display screen in front of other examinees, intercepting a plurality of images of the examinee to be identified in preset time before and after the time point of the shot image, and analyzing the acquired synergies of the operation behaviors of the I/O equipment of the examinee to be identified and the input content;
substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model;
If the output result of the cheating identification model shows that the behavior of the examinee to be identified is abnormal, displaying a cheating detection signal on a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behavior or not according to the displayed cheating detection signal;
if yes, intercepting first content of the display screen of the examinee to be identified and second content of the display screen of other examinees in front of which the visual focus of the user falls, judging similarity between the first content and the second content, and if the similarity is higher than a preset threshold, judging that the examinee to be identified has cheating behaviors.
The third aspect of the present invention also provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, perform the operations of:
detecting that the deflection angle of the normal line of the face of the examinee to be identified exceeds a preset threshold value through the shot image, and simultaneously detecting that the visual focus of the examinee to be identified is separated from a display screen in front of the examinee to be identified, and when the visual focus of the examinee to be identified falls into the display screen in front of other examinees, intercepting a plurality of images of the examinee to be identified in preset time before and after the time point of the shot image, and analyzing the acquired synergies of the operation behaviors of the I/O equipment of the examinee to be identified and the input content;
Substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model;
if the output result of the cheating identification model shows that the behavior of the examinee to be identified is abnormal, displaying a cheating detection signal on a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behavior or not according to the displayed cheating detection signal;
if yes, intercepting first content of the display screen of the examinee to be identified and second content of the display screen of other examinees in front of which the visual focus of the user falls, judging similarity between the first content and the second content, and if the similarity is higher than a preset threshold, judging that the examinee to be identified has cheating behaviors.
According to the technical scheme, the normal line of the face and the visual focus of the examinee to be identified are monitored in real time through the camera in front of the examinee to be identified, when the normal line of the face and the visual focus are abnormal, other images near the time point of the shot images are intercepted, the analysis of the cooperativity of the I/O equipment of the examinee to be identified and the input content is combined, the analysis result is substituted into the cheating identification model to obtain an output result, if the result is abnormal, a cheating detection signal is output to the display screen of the examinee to be identified, whether the cheating behavior exists in the examinee to be identified is judged again, if yes, the content of the display screen of the examinee to be identified and the content of the display screen of the suspected cheating object are intercepted, the similarity of the content of the two display screens is judged, and finally whether the cheating behavior exists in the examinee to be identified is determined. Therefore, through comprehensively analyzing the image shot by the examinee to be identified and the operation behaviors and the input content of the I/O equipment of the examinee to be identified, substituting the image into the cheating identification model under the pre-trained normal operation, when the result is abnormal, the content of the display screen of the examinee to be identified and the content of the display screen of the suspected cheating object can be extracted, whether the cheating behaviors exist or not is judged, the capability of identifying and preventing the cheating of the examination can be improved, and the fairness of the online examination are further ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present invention;
FIG. 2 is a schematic flow chart of an online examination cheating identification method provided by an embodiment of the invention;
FIG. 3-A is a schematic view of detecting a deflection angle of a face normal of a candidate to be identified according to an embodiment of the present invention;
FIG. 3-B is a schematic diagram showing that the normal line of the face of the examinee to be identified is not deflected according to the embodiment of the present invention;
FIG. 4 is a schematic view of a display screen in front of a candidate to be identified according to an embodiment of the present invention;
FIG. 5 is a schematic view of a scene of a display screen of a test taker judging whether a visual focus of the test taker to be identified falls into a seat in front of the seat in an inclined manner according to the embodiment of the present invention;
FIG. 6 is a block diagram of an online examination cheating recognition device provided by an embodiment of the present invention;
Fig. 7 is a schematic logic structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present application, the present application is clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. This application is intended to be limited to the details of the construction set forth in the following description, but it is intended to cover all such modifications and variations as fall within the scope of the present application.
It should be noted that the terms "first," "second," "third," and the like in the claims, specification, and drawings herein are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. The data so used may be interchanged where appropriate to facilitate the embodiments of the present application described herein, and may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and their variants are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Before describing an online examination cheating identification method which is claimed in the embodiment of the invention, the application scene of the invention is introduced.
Along with the continuous development of the related technology of education informatization, more and more traditional paper examination is gradually moved to the line, so that the tissue cost of the examination is reduced, and meanwhile, the examination region limitation is gradually removed.
The on-line examination related to the invention needs to be carried out by the examinee through the unified examination equipment in the unified on-line examination classroom. The examination Device comprises a desktop computer host, an input/output Device (I/O Device) and a camera. Input and output devices to which the present invention relates include, but are not limited to, a keyboard, a mouse, and a display.
Fig. 1 is a schematic diagram of an application scenario in an embodiment of the present invention. As shown in fig. 1, a schematic diagram of an on-line examination classroom is shown. The examinee uses the front computer 101 to answer papers, and the front camera 102 records the operation behaviors of the examinee, so as to further identify whether the examinee has peeping and cheating behaviors.
In order to better promote the on-line examination recognition and the capability of preventing examination cheating, and further ensure the fairness and fairness of the on-line examination, the embodiment of the invention discloses an on-line examination cheating recognition method.
The first embodiment of the invention provides an online examination cheating identification method. Please refer to fig. 2, which is a flowchart illustrating a first embodiment of the present invention.
An online examination cheating recognition method according to a first embodiment of the present invention will be described in detail with reference to fig. 2. It should be noted that the steps illustrated in the flowchart may be performed in a computer system, such as a set of computer-executable instructions, and in some cases, the steps illustrated may be performed in a different logical order than that illustrated in the flowchart.
As shown in fig. 2, the method for identifying cheating in online examination provided by the first embodiment of the present invention includes the following steps:
step S201, detecting that the deflection angle of the normal line of the face of the examinee to be identified exceeds a preset threshold value through the shot image, and simultaneously detecting that the visual focus of the examinee to be identified is separated from the display screen in front of the examinee to be identified, and when the visual focus of the examinee to be identified falls into the display screen in front of other examinees, intercepting a plurality of images of the examinee to be identified in preset time before and after the time point of the shot image, and analyzing the acquired operation behavior of the I/O equipment of the examinee to be identified and the synergy of the input content.
The method comprises the steps of detecting that a deflection angle of a face normal of a to-be-identified examinee exceeds a preset threshold through a shot image, simultaneously detecting that a visual focus of the to-be-identified examinee is separated from a display screen in front of the to-be-identified examinee, and when the visual focus of the to-be-identified examinee falls into the display screen in front of other examinees, intercepting a plurality of images of the to-be-identified examinee in preset time before and after a time point of the shot image, and analyzing the acquired operation behavior of the I/O equipment of the to-be-identified examinee and the synergy of input content.
The obtained photographed image may be a photographed image obtained by sampling the camera video in front of the examinee to be identified according to a preset sampling period. The background can establish a video database for the examinee to be identified, and store the shot images of each examinee to be identified obtained according to the sampling period, wherein the stored contents include, but are not limited to, shot images, numbers of the examinee to be identified, shooting time and the like.
The preset sampling period can be set by an examination organizer according to examination duration, examination requirements and the memory of a background video database. When the examination duration is short or the examination requirement level is high and the memory of the background video database is sufficient, the sampling period can be properly shortened, and the number of shot images is increased so as to improve the accuracy of cheating identification.
Further, the photographed image is detected according to the stored content, and specific detection content includes: detecting the deflection angle of the face normal of the examinee to be identified, and detecting the position of the visual focus of the examinee to be identified. The method comprises the steps of detecting whether the deflection angle of the normal of the face of a to-be-identified examinee exceeds a preset threshold value, and detecting whether the visual focus of the to-be-identified examinee is separated from a display screen in front of the examinee and detecting whether the visual focus of the to-be-identified examinee falls into a display screen in front of other examinees.
The detecting, by the captured image, that the deflection angle of the face normal of the examinee to be identified exceeds a preset threshold value includes:
the preset threshold value is a standard angle interval between the normal line of the face of the examinee to be identified when the examinee looks at the display screen and the plane where the camera is located.
FIG. 3-A is a schematic view showing the deflection angle of the face normal of the examinee to be identified. In the invention, the normal line of the face of the examinee to be identified can be regarded as the central axis of the face of the human body. FIG. 3-B is a schematic illustration of the face normal of the candidate to be identified being undeflected. In a normal state, the central axis of the face of the human body is vertical downwards, and the normal line of the face is considered not to deflect at the moment. The angle beta in fig. 3-a is the angle of deflection of the face normal of the subject to be identified.
We consider that a certain deflection angle may exist for the normal line of the face when a person looks at the display, keyboard or mouse in a normal state. However, when the angle of deflection of the normal line of the face is larger than a certain range, the human sight may be separated from the display screen, keyboard or mouse in front of the human sight, and thus cheating may occur.
Therefore, a preset threshold value of the deflection angle of the face normal can be set, wherein the preset threshold value is a standard angle interval between the face normal of the examinee to be identified and the plane in which the camera is positioned when the examinee gazes at the display screen.
It is conceivable that the above example is an image in a normal state taken when the camera is facing the face. In practical application, the camera can be arranged on one side of the display screen, and the normal position of the face in the normal state and the preset threshold value are set in advance under the angle of the camera.
The detecting that the visual focus of the examinee to be identified is separated from the display screen in front of the examinee to be identified comprises the following steps:
acquiring a visual fixation angle of a shot image, and acquiring coordinates of a visual focus falling under a coordinate system of a plane expansion of a display screen of an examinee to be identified according to the visual fixation angle;
And if the coordinates of the visual focus falling under the coordinate system of the display screen after the plane expansion are judged not to be in the coordinate range of the real display screen, separating the visual focus of the examinee to be identified from the display screen in front of the display screen.
The method comprises the steps of detecting whether a visual focus of an examinee to be identified is separated from a display screen in front of the examinee to be identified, specifically, obtaining a visual gazing angle of a shot image, and obtaining coordinates of the visual focus falling under a coordinate system of the plane of the display screen of the examinee to be identified after expansion according to the visual gazing angle; and if the coordinates of the visual focus falling in the coordinate system of the display screen after the plane expansion are judged not to be in the coordinate range of the real display screen, the visual focus of the examinee to be identified is considered to be separated from the display screen in front of the real display screen.
According to the invention, an infinite virtual display screen is established after the plane of the display screen of the examinee to be identified is expanded, the visual fixation angle of the examinee to be identified can be mapped on the virtual display screen, whether the visual focus of the examinee to be identified is in the coordinate range of the real display screen in front of the examinee per se is judged according to the coordinates of the visual fixation angle mapped on the virtual display screen, and if the visual focus of the examinee to be identified is not in the coordinate range of the real display screen in front of the examinee, the visual focus of the examinee to be identified is separated from the display screen in front.
The visual fixation angle comprises the step of detecting the pupil position by using a camera, so as to obtain the visual fixation angle. The specific manner in which the visual gaze angle is obtained is prior art, and any available technique that can obtain the visual gaze angle is within the scope of the present application and is not limited in this regard.
Before examination, because the heights, the body types and the sitting postures of the examinees to be identified are different, the visual focuses of the examinees to be identified on the edges of the real display screen are different, and then the coordinates of the visual focuses on the set virtual display screen are also different, and the coordinates of the visual focuses on the virtual display screen when the visual focuses on the edges of the real display screen are detected in advance for the examinees to be identified are needed.
Fig. 4 shows a schematic view of a display screen for judging that the visual focus of the examinee to be identified is away from the front of the examinee to be identified. As shown in fig. 4, for the candidate to be identified in 0021, the coordinates of the visual focus of the candidate to be identified on the virtual display screen when the visual focus falls on the edge of the real display screen are identified, for example, the coordinates of the four vertices are a (100, 10), B (100, 50), C (700,50), and D (700,10). When the coordinates of the set infinite virtual display screen of which the visual focus falls in front are (300,30), the visual focus of the examinee to be identified falls into the real display screen; when the visual focus is judged to fall into the coordinates (400,60) of the set infinite virtual display screen in front of the face, the visual focus of the examinee to be identified is separated from the display screen in front of the face if the visual focus of the examinee to be identified is not in the coordinate range of the real display screen.
In some cases, the display screen may be left alone or looking elsewhere even if the visual focus of the subject to be identified is out of front. If the fact that the visual focus of the examinee to be identified is separated from the display screen in front of the examinee is detected to trigger the next analysis operation, a plurality of misjudgment situations are easily increased, and the calculation amount of the background is increased.
Therefore, the invention not only judges whether the visual focus of the examinee to be identified is separated from the display screen in front of the examinee, but also detects whether the visual focus of the examinee to be identified is dropped into the display screen in front of other examinees.
Specifically, detecting the display screen of the candidate to be identified with the visual focus falling in front of other candidates includes:
if the visual focus of the examinee to be identified is judged to be in the coordinate range of the display screen in front of other examinees in the coordinate system after the plane of the display screen is expanded, the visual focus of the examinee to be identified is judged to be in front of the display screen of other examinees.
The method comprises the steps of judging whether the visual focus of the examinee to be identified falls into the display screen in front of other examinees, and judging whether the visual focus of the examinee to be identified falls into the display screen in front of other examinees if the visual focus of the examinee to be identified falls into the coordinate range of the display screen in front of other examinees under the coordinate system after plane expansion of the display screen.
In general, in the case that a plagiarism behavior of an on-line test examinee sitting on a seat is generally that a face deflects and a visual fixation angle changes, a plagiarism is performed on display screens of adjacent examinees and obliquely front examinees.
When whether the visual focus of the examinee to be identified falls into the examinee of the adjacent seat is detected, the examinee to be identified and the examinee of the adjacent seat are on the same horizontal plane, and the set infinite virtual display screen is in the same plane. At this time, the coordinates on the infinite virtual display screen are obtained only when the visual focus of the examinee to be identified falls at the edge of the display screen of the examinee of the adjacent seat. When the visual focus of the examinee to be identified just falls into the coordinate range of the display screen in front of the adjacent seat examinee, the fact that the visual focus of the examinee to be identified at the moment falls into the display screen in front of the adjacent seat examinee is indicated.
Fig. 5 shows a schematic view of a scene of a display screen of a test taker judging whether the visual focus of the test taker to be identified falls into a seat obliquely in front.
When whether the visual focus of the examinee to be identified falls into the examinee of the obliquely front seat is detected, at the moment, the coordinates of the visual focus of the examinee to be identified on the set infinite virtual display screen when the visual focus of the examinee to be identified falls into the display screen of the obliquely front seat can be obtained according to the visual fixation angle. Because the infinite virtual display screen established in front of the examinee to be identified and the virtual display screen at the examinee falling into the seat in front of the oblique direction are not on the same horizontal plane, the coordinates on the virtual display screen at the examinee falling into the seat in front of the oblique direction can be obtained according to translation, and only the distance between the coordinates and the front is needed to be known. The space between the seats of the examinees needs to be fixed when the examination room is set. Therefore, when the visual focus of the examinee to be identified falls within the coordinate range of the display screen in front of the obliquely front seat examinee, the visual focus of the examinee to be identified at this time is indicated to fall into the display screen in front of the obliquely front seat examinee.
When the shot image detects that the examinee to be identified has the three conditions at the same time, a plurality of images of the examinee to be identified in the preset time are intercepted before the time point of the shot image, and the acquired operation behaviors of the I/O equipment of the examinee to be identified are analyzed to be cooperated with the input content.
The operation behaviors of the I/O equipment of the examinee to be identified comprise at least one operation of clicking a mouse and typing by a keyboard; the input content includes input content displayed on the display screen.
That is, when the photographed image detects that the normal line of the face and the visual focus of the examinee to be recognized are abnormal, a plurality of images of the examinee to be recognized are intercepted in a preset time before and after the time point according to the recorded time of the photographed image, if the examinee to be recognized is found that the normal line of the face deflects abnormally and the visual focus is abnormal for a period of time, a certain amount of characters are input suddenly through a keyboard, the time and the angle of each abnormality are approximate, the length of the input characters is approximate, the condition is repeated for a plurality of times, and then the examinee to be recognized is likely to be abnormal.
The specific preset time for intercepting a plurality of images and the number of the images can be set by an examination manager according to the rule of the examination in practice.
Through the step, the shot image is detected, when the shot image is abnormal, other multiple images of the examinee to be identified near the time point of the shot image are intercepted, and meanwhile, the acquired cooperativity of the operation behaviors of the I/O equipment of the examinee to be identified and the input content is analyzed, so that a data basis is provided for analyzing the behaviors of the examinee to be identified.
Step S202, substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model.
The step is used for substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model.
Wherein the pre-trained cheating identification model comprises:
preprocessing the photo of the examinee to be identified, and establishing a face feature basic feature library;
recording normal operation behaviors of the to-be-identified examinee by using the I/O equipment, and determining an angle threshold value of a face normal of the to-be-identified examinee in a normal operation state and a coordinate value of a sight gaze angle of the to-be-identified examinee in the normal operation state based on the recorded normal operation behaviors of the to-be-identified examinee;
Establishing a cheating identification model based on the face feature basic feature library, the angle threshold value of the face normal and the coordinate value of the sight-line fixation angle;
selecting an operation behavior of I/O equipment used by an examinee to be identified within a fixed time as a sample training set, and training the cheating identification model to obtain a trained cheating identification model.
The method is used for training the cheating identification model, and is convenient to detect the behaviors of the examinee to be identified according to the analysis result of the cooperativity.
Specifically, preprocessing photos of an examinee to be identified in a system before an examination starts, and establishing a face feature basic feature library; recording the relevant extremum of the face normal and the sight line gaze angle of the examinee to be identified by using a keyboard, a mouse and a gaze display screen through the relevant detection problem, and determining the face normal threshold of the examinee to be identified in a normal operation state and the coordinate value of the sight line gaze angle of the examinee to be identified in the normal operation state specifically based on the recorded normal operation behavior of the examinee to be identified; then establishing a cheating identification model based on relevant contents such as a face feature basic feature library, an angle threshold value of a face normal, a coordinate value for realizing a fixation angle and the like; and then selecting the operation behaviors of the examinee to be identified in the fixed time at the beginning of the examination, such as using a keyboard, a mouse, a gaze display screen and the like, as sample training, and performing optimization training on the built cheating identification model to finally obtain the trained cheating identification model.
Specifically, before an examination starts, a cheating recognition model is established by setting related problems about habit of an examinee to be recognized for sitting in a normal position, clicking by using a mouse, inputting characters by using a keyboard and watching a display screen at a visual focus, and the fixed time after the examination starts is used as a training period to obtain the trained cheating recognition model. And (3) introducing the collaborative analysis result obtained in the step S201 into a trained cheating identification model to obtain an output result of the cheating identification model.
The step brings the analysis result of the cooperativity into a pre-trained cheating identification model to obtain the output result of the cheating identification model, and provides basis for the follow-up judgment of the cheating behavior of the examinee to be identified.
Step S203, if the output result of the cheating recognition model indicates that the behavior of the candidate to be recognized is abnormal, displaying a cheating detection signal on the display screen of the candidate to be recognized, and judging whether the candidate to be recognized has suspected cheating behavior according to the displayed cheating detection signal.
And if the output result of the cheating identification model indicates that the behavior of the examinee to be identified is abnormal, displaying a cheating detection signal on a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behaviors according to the displayed cheating detection signal.
If the output result of the cheating identification model indicates that the behavior of the candidate to be identified is abnormal, inputting a cheating detection signal to a display screen of the candidate to be identified, and judging whether the candidate to be identified has suspected cheating behavior according to the input cheating detection signal, wherein the method comprises the following steps:
if the tolerance value of the output result of the cheating identification model exceeds a preset range, indicating that the behavior of the examinee to be identified is abnormal;
after the water ripple cheating detection signal is input to the display screen of the examinee to be identified, the operation behavior of the I/O equipment of the examinee to be identified acquired in the current state is analyzed again to be cooperated with the input content;
substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model, and judging whether the candidate to be identified has suspected cheating behaviors or not.
And the output result of the cheating identification model is a specific numerical value, and when the tolerance value of the output result exceeds a preset range which is set and does not generate cheating behaviors, the cheating identification model indicates that the behaviors of the examinee to be identified are normal, and no cheating behaviors are detected. When the tolerance value of the output result exceeds the preset range, the abnormal behavior of the examinee to be identified is indicated, and at the moment, a water ripple detection signal or a mole ripple change is input to a display screen of the examinee to be identified so as to draw attention of the examinee to be identified. At this time, the operation behaviors of the examinees to be identified may change, the cooperativity of the operation behaviors of the I/O devices of the examinees to be identified collected in the current state and the input content is analyzed again, and the analysis result of the cooperativity is brought into a pre-trained cheating identification model to obtain the output result of the cheating identification model, so as to judge whether the examinees to be identified have suspected cheating behaviors.
The manner of re-analysis is the same as that described above, and will not be described in detail here.
The method comprises the steps of giving attention to the examinee to be identified after detecting the abnormal behavior of the examinee to be identified according to the output result of the cheating identification model, secondarily analyzing the behavior of the examinee to be identified in the current state, and judging whether the suspicious cheating behavior exists in the examinee to be identified.
And step S204, if yes, intercepting first contents of the display screen of the examinee to be identified and second contents of the display screen of other examinees in front of which the visual focus of the user falls, judging the similarity between the first contents and the second contents, and if the similarity is higher than a preset threshold, judging that the examinee to be identified has cheating behaviors.
The method comprises the steps of intercepting first content of a display screen of an examinee to be identified and second content of the display screen of other examinees in front of which visual focuses of users fall if the examinee to be identified is judged to have suspected cheating behaviors, judging similarity of the first content and the second content, and considering that the examinee to be identified has the cheating behaviors if the similarity is higher than a preset threshold value.
Judging that the candidate to be identified has suspected cheating behaviors, determining suspected cheating objects of the candidate to be identified, intercepting first content of a display screen of the candidate to be identified and second content of the display screen of the suspected cheating objects at the moment, judging similarity between the first content and the second content, and if the similarity between the first content and the second content is detected to be higher than a preset threshold value, judging that the candidate to be identified is suspected to have the cheating behaviors.
The method for identifying cheating on online examination, which is claimed in the first embodiment of the invention, is introduced, by shooting an image, the deflection angle of the normal line of the face of an examinee to be identified exceeds a preset threshold value, and simultaneously, when the visual focus of the examinee to be identified is detected to be separated from a display screen in front of the examinee to be identified and the visual focus of the examinee to be identified falls into the display screen in front of other examinees, a plurality of images of the examinee to be identified in the preset time before and after the time point of the shot image are intercepted, and the operation behavior of the acquired I/O equipment of the examinee to be identified is analyzed to be cooperated with the input content; substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model; if the output result of the cheating identification model shows that the behaviors of the examinee to be identified are abnormal, displaying cheating detection signals on a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behaviors or not according to the displayed cheating detection signals; if yes, intercepting first content of a display screen of the examinee to be identified and second content of the display screen of the examinee to be identified in front of other examinees with visual focuses falling in, judging similarity of the first content and the second content, and if the similarity is higher than a preset threshold, judging that the examinee to be identified has cheating behaviors. Through the mode, the capability of identifying and preventing cheating of the examination can be improved, and fairness of the online examination are further guaranteed.
The second embodiment of the present invention provides an online examination cheating recognition apparatus, which corresponds to the online examination cheating recognition method provided in the first embodiment of the present invention, and is briefly described herein. Reference may be made to the first embodiment, without any ambiguity in the implementation of this embodiment.
Please refer to fig. 6, which is a block diagram of a device according to a second embodiment of the present invention.
A second embodiment of the present invention provides an online examination cheating recognition apparatus 600, the apparatus comprising: an image capturing unit 601, a model identifying unit 602, a first judging unit 603, and a second judging unit 604.
The image capturing unit 601 is configured to detect, through a captured image, that a deflection angle of a face normal of a candidate to be identified exceeds a preset threshold, and detect that a visual focus of the candidate to be identified is separated from a display screen in front of the candidate to be identified, and when the visual focus of the candidate to be identified falls into a display screen in front of other candidates, capture a plurality of images of the candidate to be identified in preset time before and after a time point of the captured image, and analyze a synergism between an acquired operation behavior of an I/O device of the candidate to be identified and an input content;
The model identification unit 602 is configured to substitute the analysis result of cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model;
a first judging unit 603, configured to display a cheating detection signal on a display screen of the candidate to be identified if the output result of the cheating identification model indicates that the candidate to be identified is abnormal, and judge whether the candidate to be identified has suspected cheating according to the displayed cheating detection signal;
the second judging unit 604 is configured to intercept the first content of the display screen of the candidate to be identified and the second content of the display screen before the other candidate whose visual focus falls in if the candidate to be identified has a suspected cheating behavior, judge the similarity between the first content and the second content, and consider that the candidate to be identified has a cheating behavior if the similarity is higher than a preset threshold.
Referring to fig. 7, a schematic diagram of an electronic device according to a third embodiment of the present invention is shown.
The electronic device includes:
a processor 701;
the memory 702 is used for storing a program of the online examination cheating identification method, and when the program is read and executed by the processor, the program performs the following operations:
Detecting that the deflection angle of the normal line of the face of the examinee to be identified exceeds a preset threshold value through the shot image, and simultaneously detecting that the visual focus of the examinee to be identified is separated from a display screen in front of the examinee to be identified, and when the visual focus of the examinee to be identified falls into the display screen in front of other examinees, intercepting a plurality of images of the examinee to be identified in preset time before and after the time point of the shot image, and analyzing the acquired synergies of the operation behaviors of the I/O equipment of the examinee to be identified and the input content;
substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model;
if the output result of the cheating identification model shows that the behavior of the examinee to be identified is abnormal, outputting a cheating detection signal on a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behaviors or not according to the displayed cheating detection signal;
if yes, intercepting first content of the display screen of the examinee to be identified and second content of the display screen of other examinees in front of which the visual focus of the user falls, judging similarity between the first content and the second content, and if the similarity is higher than a preset threshold, judging that the examinee to be identified has cheating behaviors.
The fourth embodiment of the present invention also provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, perform operations comprising:
detecting that the deflection angle of the normal line of the face of the examinee to be identified exceeds a preset threshold value through the shot image, and simultaneously detecting that the visual focus of the examinee to be identified is separated from a display screen in front of the examinee to be identified, and when the visual focus of the examinee to be identified falls into the display screen in front of other examinees, intercepting a plurality of images of the examinee to be identified in preset time before and after the time point of the shot image, and analyzing the acquired synergies of the operation behaviors of the I/O equipment of the examinee to be identified and the input content;
substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model;
if the output result of the cheating identification model shows that the behavior of the examinee to be identified is abnormal, displaying a cheating detection signal on a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behavior or not according to the displayed cheating detection signal;
If yes, intercepting first content of the display screen of the examinee to be identified and second content of the display screen of other examinees in front of which the visual focus of the user falls, judging similarity between the first content and the second content, and if the similarity is higher than a preset threshold, judging that the examinee to be identified has cheating behaviors.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
1. Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer readable media, as defined herein, does not include non-transitory computer readable media (transmission media), such as modulated data signals and carrier waves.
2. It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Any modification, equivalent replacement, improvement, etc. made in the embodiments of the present invention shall fall within the scope of the present invention, as long as they are within the spirit and principle of the present invention.
Claims (8)
1. An online examination cheating identification method is characterized by comprising the following steps:
detecting that the deflection angle of the normal line of the face of the examinee to be identified exceeds a preset threshold value through the shot image, and simultaneously detecting that the visual focus of the examinee to be identified is separated from a display screen in front of the examinee to be identified, and when the visual focus of the examinee to be identified falls into the display screen in front of other examinees, intercepting a plurality of images of the examinee to be identified in preset time before and after the time point of the shot image, and analyzing the acquired synergies of the operation behaviors of the I/O equipment of the examinee to be identified and the input content;
The operational behavior includes: at least one of clicking mouse operation and keyboard typing operation; the input content includes input content displayed on the display screen;
substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model;
the pre-trained cheating identification model comprises:
preprocessing the photo of the examinee to be identified, and establishing a face feature basic feature library;
recording normal operation behaviors of the to-be-identified examinee by using the I/O equipment, and determining an angle threshold value of a face normal of the to-be-identified examinee in a normal operation state and a coordinate value of a sight gaze angle of the to-be-identified examinee in the normal operation state based on the recorded normal operation behaviors of the to-be-identified examinee;
establishing a cheating identification model based on the face feature basic feature library, the angle threshold value of the face normal and the coordinate value of the sight-line fixation angle;
selecting an examinee to be identified in a fixed time, using the operation behavior of the I/O equipment as a sample training set, and training the cheating identification model to obtain a trained cheating identification model;
If the output result of the cheating identification model shows that the behavior of the examinee to be identified is abnormal, displaying a cheating detection signal on a display screen of the examinee to be identified, and judging whether the examinee to be identified has suspected cheating behavior or not according to the displayed cheating detection signal;
if yes, intercepting first content of the display screen of the examinee to be identified and second content of the display screen of other examinees in front of which the visual focus of the examinee to be identified falls, judging similarity between the first content and the second content, and if the similarity is higher than a preset threshold, judging that the examinee to be identified has cheating behaviors.
2. The method according to claim 1, wherein the detecting, by the photographed image, that the angle of deflection of the face normal of the examinee to be identified exceeds a preset threshold value, comprises:
the preset threshold value is a standard angle interval between the normal line of the face of the examinee to be identified when the examinee looks at the display screen and the plane where the camera is located.
3. A method according to claim 2, wherein said detecting that the visual focus of the candidate to be identified is off the display screen in front of the candidate to be identified comprises:
acquiring a visual fixation angle of a shot image, and acquiring coordinates of a visual focus falling under a coordinate system of a plane expansion of a display screen of an examinee to be identified according to the visual fixation angle;
And if the coordinates of the visual focus falling under the coordinate system of the display screen after the plane expansion are judged not to be in the coordinate range of the real display screen, separating the visual focus of the examinee to be identified from the display screen in front of the display screen.
4. A method according to claim 3, wherein the visual focus of the candidate to be identified falls on a display screen in front of other candidates, comprising:
if the visual focus of the examinee to be identified is judged to be in the coordinate range of the display screen in front of other examinees in the coordinate system after the plane of the display screen is expanded, the visual focus of the examinee to be identified is judged to be in front of the display screen of other examinees.
5. The method according to claim 1, wherein if the output result of the cheating identification model indicates that the behavior of the candidate to be identified is abnormal, inputting a cheating detection signal to the display screen of the candidate to be identified, and determining whether the candidate to be identified has suspected cheating behavior according to the input cheating detection signal, includes:
if the tolerance value of the output result of the cheating identification model exceeds a preset range, indicating that the behavior of the examinee to be identified is abnormal;
after the water ripple cheating detection signal is input to the display screen of the examinee to be identified, the operation behavior of the I/O equipment of the examinee to be identified acquired in the current state is analyzed again to be cooperated with the input content;
Substituting the analysis result of the cooperativity into a pre-trained cheating identification model to obtain an output result of the cheating identification model, and judging whether the candidate to be identified has suspected cheating behaviors or not.
6. The method of claim 5, wherein after said recognizing that the candidate exists in a cheating act, the method further comprises:
and exciting an alarm signal, carrying out trace-keeping registration on the lightning and plagiarism parts, and reporting to the test system.
7. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are for implementing the online test cheating identification method of any of claims 1-6.
8. An electronic device, comprising: a processor, the computer readable storage medium of claim 7, readable and executable by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310896905.0A CN117058612B (en) | 2023-07-20 | 2023-07-20 | Online examination cheating identification method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310896905.0A CN117058612B (en) | 2023-07-20 | 2023-07-20 | Online examination cheating identification method, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117058612A CN117058612A (en) | 2023-11-14 |
| CN117058612B true CN117058612B (en) | 2024-03-29 |
Family
ID=88656304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310896905.0A Active CN117058612B (en) | 2023-07-20 | 2023-07-20 | Online examination cheating identification method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117058612B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105683991A (en) * | 2016-01-07 | 2016-06-15 | 汤美 | Examination anti-cheating system |
| CN106920194A (en) * | 2017-03-07 | 2017-07-04 | 佛山市金蓝领教育科技有限公司 | A kind of anti-cheating remote test method |
| CN106991344A (en) * | 2017-03-10 | 2017-07-28 | 重庆零二四科技有限公司 | Anti-cheating device and its application method |
| CN112070024A (en) * | 2020-09-09 | 2020-12-11 | 常州纺织服装职业技术学院 | Anti-cheating method for paperless examination and invigilating method for paperless examination system |
| CN112102129A (en) * | 2020-09-21 | 2020-12-18 | 南京润北智能环境研究院有限公司 | Intelligent examination cheating identification system based on student terminal data processing |
| CN112464793A (en) * | 2020-11-25 | 2021-03-09 | 大连东软教育科技集团有限公司 | Method, system and storage medium for detecting cheating behaviors in online examination |
| KR102321917B1 (en) * | 2020-07-13 | 2021-11-04 | 주식회사 두두아이티 | System for video remote management and supervision of online test |
| CN113920563A (en) * | 2021-09-29 | 2022-01-11 | 上海浦东发展银行股份有限公司 | Online examination cheating identification method and device, computer equipment and storage medium |
| CN115345761A (en) * | 2022-07-26 | 2022-11-15 | 华中科技大学 | Online examination auxiliary system and online examination monitoring method |
| WO2023041940A1 (en) * | 2021-09-20 | 2023-03-23 | Javadi Amir Homayoun | Gaze-based behavioural monitoring system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230215171A1 (en) * | 2023-03-09 | 2023-07-06 | Daniel Kim | Method for online test cheating detection using deep neural network and habit capture |
-
2023
- 2023-07-20 CN CN202310896905.0A patent/CN117058612B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105683991A (en) * | 2016-01-07 | 2016-06-15 | 汤美 | Examination anti-cheating system |
| CN106920194A (en) * | 2017-03-07 | 2017-07-04 | 佛山市金蓝领教育科技有限公司 | A kind of anti-cheating remote test method |
| CN106991344A (en) * | 2017-03-10 | 2017-07-28 | 重庆零二四科技有限公司 | Anti-cheating device and its application method |
| KR102321917B1 (en) * | 2020-07-13 | 2021-11-04 | 주식회사 두두아이티 | System for video remote management and supervision of online test |
| CN112070024A (en) * | 2020-09-09 | 2020-12-11 | 常州纺织服装职业技术学院 | Anti-cheating method for paperless examination and invigilating method for paperless examination system |
| CN112102129A (en) * | 2020-09-21 | 2020-12-18 | 南京润北智能环境研究院有限公司 | Intelligent examination cheating identification system based on student terminal data processing |
| CN112464793A (en) * | 2020-11-25 | 2021-03-09 | 大连东软教育科技集团有限公司 | Method, system and storage medium for detecting cheating behaviors in online examination |
| WO2023041940A1 (en) * | 2021-09-20 | 2023-03-23 | Javadi Amir Homayoun | Gaze-based behavioural monitoring system |
| CN113920563A (en) * | 2021-09-29 | 2022-01-11 | 上海浦东发展银行股份有限公司 | Online examination cheating identification method and device, computer equipment and storage medium |
| CN115345761A (en) * | 2022-07-26 | 2022-11-15 | 华中科技大学 | Online examination auxiliary system and online examination monitoring method |
Non-Patent Citations (1)
| Title |
|---|
| "基于机器学习的考生异常行为识别研究";李亚;《中国优秀硕士学位论文全文数据库 社会科学Ⅱ辑》;20230715;第H127-28页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117058612A (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elazary et al. | Interesting objects are visually salient | |
| US11106920B2 (en) | People flow estimation device, display control device, people flow estimation method, and recording medium | |
| Fathi et al. | Learning to recognize daily actions using gaze | |
| Foulsham et al. | What can saliency models predict about eye movements? Spatial and sequential aspects of fixations during encoding and recognition | |
| US10984252B2 (en) | Apparatus and method for analyzing people flows in image | |
| CN108229308A (en) | Recongnition of objects method, apparatus, storage medium and electronic equipment | |
| EP3223237A1 (en) | Systems and methods for detecting and tracking a marker | |
| US8805123B2 (en) | System and method for video recognition based on visual image matching | |
| JP2018072240A5 (en) | ||
| US10936472B2 (en) | Screen recording preparation method for evaluating software usability | |
| JP2017188715A (en) | Video display system and video display method | |
| CN107256375A (en) | Human body sitting posture monitoring method before a kind of computer | |
| Mansour et al. | Characterizing visual behaviour in a lineup task | |
| CN117058612B (en) | Online examination cheating identification method, electronic equipment and storage medium | |
| US9501710B2 (en) | Systems, methods, and media for identifying object characteristics based on fixation points | |
| Jayawardena et al. | Automated filtering of eye gaze metrics from dynamic areas of interest | |
| US11961302B2 (en) | Visual analytics tool for proctoring online exams | |
| CN112016509A (en) | Personnel station position abnormity reminding method and device | |
| US20230018693A1 (en) | Method and system for confidence level detection from eye features | |
| Abid et al. | On the usage of visual saliency models for computer generated objects | |
| Fekry et al. | Automatic detection for students behaviors in a group presentation | |
| Das et al. | I Cannot See Students Focusing on My Presentation; Are They Following Me? Continuous Monitoring of Student Engagement through “Stungage” | |
| CN111507282B (en) | Target detection early warning analysis system, method, equipment and medium | |
| CN115116136A (en) | Abnormal behavior detection method, device and medium | |
| KR102213865B1 (en) | Apparatus identifying the object based on observation scope and method therefor, computer readable medium having computer program recorded therefor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |