Remote proctoring method, device, medium and electronic equipment

Abstract

The present disclosure provides a remote proctoring method, device, medium and electronic device, the method comprising: obtaining multiple proctoring video images taken in all directions at the same time point for the target proctoring object in the examination seat; extracting the key morphological images of each preset body part of the target proctoring object based on the multiple proctoring video images; performing abnormal analysis on each key morphological image, respectively obtaining the alarm evaluation value of the corresponding key morphological image; generating alarm information in response to all alarm evaluation values ​​satisfying the preset alarm conditions. Through intelligent means, the examinees are no longer able to cheat, the occurrence of cheating is avoided, unmanned proctoring is realized, and the efficiency and accuracy of proctoring are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing, and in particular to a remote proctoring method, device, medium and electronic device. Background Art

[0002] Examinations are a means for schools to test teaching effectiveness and understand students' knowledge mastery. Usually, one or two invigilators will be arranged in the examination room to supervise the students through patrolling to prevent cheating in the examination.

[0003] However, this invigilation method cannot guarantee that the teachers present can invigilate with high coordination and without blind spots, and candidates can always find loopholes to cheat, so the invigilation effect is not ideal.

[0004] Therefore, the present disclosure provides a remote proctoring method to solve one of the above technical problems. Summary of the invention

[0005] The purpose of the present disclosure is to provide a remote proctoring method, device, medium and electronic device, which can solve at least one of the above-mentioned technical problems. The specific solution is as follows:

[0006] According to a specific embodiment of the present disclosure, in a first aspect, the present disclosure provides a remote proctoring method, comprising:

[0007] For the target invigilator in the examination seat, multiple invigilator video images shot in all directions at the same time point are obtained;

[0008] Extracting key morphological images of each preset body part of the target proctor based on a plurality of proctoring video images;

[0009] Performing abnormal analysis on each key morphological image to obtain the alarm evaluation value of the corresponding key morphological image;

[0010] In response to all alarm evaluation values ​​satisfying preset alarm conditions, an alarm message is generated.

[0011] According to a specific embodiment of the present disclosure, in a second aspect, the present disclosure provides a remote proctoring device, comprising:

[0012] An acquisition unit is used to acquire a plurality of invigilation video images taken in all directions at the same time point for a target invigilator in the examination seat;

[0013] An extraction unit, configured to extract a key morphological image of each preset body part of the target proctor based on a plurality of proctoring video images;

[0014] An evaluation unit, used for performing abnormal analysis on each key morphological image, and obtaining an alarm evaluation value of the corresponding key morphological image;

[0015] The alarm unit is used to generate alarm information in response to all alarm evaluation values ​​satisfying preset alarm conditions.

[0016] According to a specific implementation of the present disclosure, in a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the remote proctoring method as described in any one of the above items.

[0017] According to the specific implementation of the present disclosure, in a fourth aspect, the present disclosure provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the remote proctoring method as described in any one of the above items.

[0018] Compared with the prior art, the above solution of the embodiment of the present disclosure has at least the following beneficial effects:

[0019] The present invention provides a remote proctoring method, device, medium and electronic device. The present invention uses video to take all-round shots of the target proctoring object in each examination seat, obtains the key morphological image of each target proctoring object, obtains the alarm evaluation value by abnormal analysis of the key morphological image, and generates alarm information when all the alarm evaluation values ​​meet the preset alarm conditions. Through intelligent means, there is no room for cheating for examinees, cheating is avoided, unmanned proctoring is realized, and the efficiency and accuracy of proctoring are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flowchart of a remote proctoring method according to an embodiment of the present disclosure is shown;

[0021] Figure 2 A schematic diagram showing the time difference of the remote proctoring method according to an embodiment of the present disclosure is shown;

[0022] Figure 3 A unit block diagram of a remote proctoring device according to an embodiment of the present disclosure is shown;

[0023] Figure 4 A schematic diagram of a connection structure of an electronic device provided according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0025] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0026] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0027] It should be understood that although the terms first, second, third, etc. may be used to describe in the disclosed embodiments, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the disclosed embodiments, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0028] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0029] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0030] It should be particularly noted that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.

[0031] The optional embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0032] Example 1

[0033] The embodiment provided by the present disclosure is an embodiment of a remote proctoring method.

[0034] Combine the following Figure 1 The embodiments of the present disclosure are described in detail.

[0035] Step S101, for a target invigilator in an examination seat, a plurality of invigilator video images shot in all directions at the same time point are obtained.

[0036] The disclosed embodiments are mainly applied to unmanned examination halls, and realize intelligent joint supervision of multiple locations and examination halls through remote supervision.

[0037] The target invigilator refers to a person who is sitting in an examination seat in the examination room and taking an examination. In the disclosed embodiment, multiple cameras are arranged in the examination room to capture each target invigilator in the examination room in all directions, so as to avoid blind spots for the target invigilator, resulting in the loss of key morphological information of the target invigilator, and thus making it impossible to effectively invigilate. For example, a number of regional cameras are evenly arranged in the examination room based on the size of the space, and are used to jointly capture the target invigilators in multiple examination seats in the invigilation area, so as to compensate for the loss of key morphological images of the target invigilators after a single camera is blocked.

[0038] In the same examination room, all videos captured by cameras are time-synchronized to prevent candidates from cheating by taking advantage of the time difference between videos. Figure 2 As shown, the video S1 collected by camera A and the video S2 collected by camera B; camera A and camera B are not timed before collecting the video. When the two cameras are at the actual time point T1, camera A marks the video image a1 of video S1 as time point T1, camera B marks the video image a2 of video S2 as time point T2, and the subsequent video image b2 of video S2 is marked as time point T1; if the key morphological image in the video image a1 at time point T1 is the left-hand image, the key morphological image in the video image b2 is the right-hand image; because the video image a1 and the video image b2 are not images collected at the same actual time point, but are collected at two different time points, there is a time difference; when the graphic analysis is performed based on the video image a1 and the video image b2, it is easy to produce misjudgment, thereby providing space for cheating. Therefore, the disclosed embodiment obtains multiple invigilation video images taken in all directions at the same time point from the video after time synchronization, avoids the time difference between the multiple invigilation video images obtained, reduces misjudgment, and ensures that the morphological information of each target invigilation object can be accurately identified.

[0039] Step S102: extracting key morphological images of each preset body part of the target proctor based on a plurality of proctoring video images.

[0040] The disclosed embodiment designs a preset body part for each target proctor, and by performing abnormal analysis on the image of the preset body part, it is possible to identify whether there is cheating in the exam. If the image of the preset body part is abnormal, an alarm message is generated to prompt the remote proctor. The preset body parts include: left hand part, right hand part and / or eye part.

[0041] The key morphological image is an image that is extracted from multiple invigilation video images and is the only image that represents a preset body part. It can be understood that the key morphological image refers to a morphological image that represents a preset body part and can meet the preset preferred conditions. The key morphological image should be the morphological image that shows the richest information about the preset body part in multiple invigilation video images. For example, there are morphological images of the left hand part of the target invigilator in multiple invigilation video images, including multiple morphological images that only show a part of the left hand part and one morphological image that shows the entire left hand part, then the key morphological image of the left hand part is determined to be the morphological image that shows the entire left hand part; or, the morphological image of the left hand part includes multiple morphologically blurred images and one morphologically clear image, then the key morphological image of the left hand part is determined to be the morphologically clear image.

[0042] In some specific embodiments, the step of acquiring a key morphological image of each preset body part of the target proctor based on a plurality of proctoring video images comprises the following steps:

[0043] Step S102-1: extracting at least one morphological image of each preset body part of the target proctor based on a plurality of proctoring video images.

[0044] Since the target proctor is photographed in all directions, each preset body part of the target proctor can be guaranteed to extract at least one morphological image from the proctor video image. Of course, if multiple proctor video images all have morphological images of preset body parts, the morphological images of all preset body parts can also be extracted.

[0045] Step S102-2: input each morphological image into the trained morphological recognition model to at least obtain the corresponding morphological complete information.

[0046] The morphological recognition model can be obtained based on previous historical morphological images, for example, the morphological recognition model is trained using historical morphological images as training samples. The process of performing morphological integrity recognition and / or morphological warning on the morphological image according to the morphological recognition model is not described in detail in this embodiment, and can be implemented with reference to various implementation methods in the prior art.

[0047] The morphological integrity information includes a morphological integrity value, which can be represented by multiple dimensions, including: the percentage of the contour area in the complete area, or the percentage of the contour area in the complete area after removing the abnormal light area (such as the spot area).

[0048] Step S102-3, determining, from the morphological images of the preset body parts, a morphological image whose morphological complete information meets a preset optimization condition as a key morphological image.

[0049] The preset optimization condition can be understood as selecting a morphological image from the preset morphological images of the body parts as the key morphological image. For example, the preset morphological images of the body parts include: P1, P2, P3 and P4, if the morphological integrity value of P1 is 30%, the morphological integrity value of P2 is 40%, the morphological integrity value of P3 is 80%, and the morphological integrity value of P4 is 95%; the preset optimization condition is: the key morphological image is the morphological image with the largest morphological integrity value, then P4 is determined to be the key morphological image.

[0050] Step S103 , performing an abnormality analysis on each key morphology image to obtain an alarm evaluation value corresponding to the key morphology image.

[0051] Continuing with the previous specific example, in response to inputting each morphological image into the trained morphological recognition model, a corresponding morphological warning value is also obtained.

[0052] That is to say, each morphological image is input into the trained morphological recognition model to obtain the corresponding complete morphological information and morphological warning value.

[0053] Accordingly, performing abnormal analysis on each key morphological image to obtain the alarm evaluation value of the corresponding key morphological image includes:

[0054] Step S103 - 1 , generating a corresponding heat map based on each key morphological image.

[0055] The heat map displays the value of each pixel in the key morphology image in a special highlighted form. It can be understood that the value of each pixel in the key morphology image is converted into a highlighted pixel value according to a preset rule. The process of generating a heat map from a key morphology image is not described in detail in this embodiment, and can be implemented with reference to various implementation methods in the prior art.

[0056] The morphological warning value is obtained by performing morphological analysis on the morphological image through the morphological recognition model. However, the morphological recognition model has the problem of accuracy in recognizing the morphological image. That is, the morphological warning value obtained after the morphological recognition model analyzes the morphological image is still inaccurate. Based on this, the embodiment of the present disclosure provides a heat map to further enhance the accuracy of the recognition result.

[0057] Optionally, generating a corresponding heat map based on each key morphological image comprises the following steps:

[0058] Step S103-1-1, extracting a body surface area image corresponding to each key morphological image from each key morphological image.

[0059] Step S103 - 1 - 2 , generating a thermal map corresponding to each key morphological image based on the body surface area image of each key morphological image.

[0060] This optional embodiment generates a thermal map using a surface area image of a preset body part so that the thermal map can fully reflect changes in the surface of the body part.

[0061] Step S103 - 2 , based on the heat map of each key morphological image and the morphological warning value and preset weight value related to the key morphological image, respectively obtain the alarm evaluation value of the corresponding key morphological image.

[0062] The preset weight value of each preset body part is used to indicate the importance of each preset body part in the evaluation. For example, the preset weight values ​​of the left hand and the right hand are both 0.4, and the preset weight value of the eye is 0.2.

[0063] In some specific embodiments, the step of obtaining the alarm evaluation value of the corresponding key morphological image based on the heat map of each key morphological image and the morphological warning value and the preset weight value related to the key morphological image comprises the following steps:

[0064] Step S103-2-1, based on the first pixel average value of the heat map of each key morphological image and the second pixel average value of the reference heat map related to the key morphological image, calculate and obtain the difference value of the corresponding key morphological image.

[0065] Wherein, the reference thermodynamic map and the thermodynamic map are both thermodynamic maps related to the same preset body part.

[0066] The reference heat map is a reference heat map for detecting changes in the heat map of the key morphological image. Usually, the reference heat map is acquired in advance, for example, before the exam, when the examinee logs into the exam system.

[0067] Step S103-2-2, based on the difference of each key morphological image and the morphological warning value and preset weight value related to the key morphological image, respectively obtain the alarm evaluation value of the corresponding key morphological image.

[0068] Since the target proctor is often nervous when cheating, the surface image of the preset body part often shows a different color from the normal image. For example, the hand will show a color change different from the normal image. The disclosed embodiment shows the color through a thermal map, and the difference shows the color change value. The color change value is used to further determine whether the target proctor is cheating, thereby further improving the accuracy of the alarm evaluation value. For example, the alarm evaluation value of the key morphological image is equal to the product of the difference of the key morphological image and the morphological warning value and the preset weight value.

[0069] Step S104: in response to all alarm evaluation values ​​satisfying preset alarm conditions, generate alarm information.

[0070] All alarm evaluation values ​​are summarized to determine whether cheating occurs. For example, when the sum of all alarm evaluation values ​​is greater than or equal to a preset alarm evaluation threshold, an alarm message is generated.

[0071] At the remote proctoring terminal, the cheating behavior of the target proctor is recorded and prompted according to the alarm information. Thus, the purpose of remote all-round proctoring is achieved without interference, eliminating the space for candidates to cheat.

[0072] With respect to the above-mentioned benchmark heat map, the method further includes the following steps:

[0073] Step S100-1, pre-acquire a reference image of each preset body part of the target invigilator.

[0074] Step S100 - 2 : Generate a corresponding reference heat map based on each reference image.

[0075] For example, before the exam officially begins, when the target proctor logs into the exam system, each benchmark image of the target proctor is obtained through multiple video images taken in all directions; then a benchmark heat map is generated based on the benchmark image. Since the target proctor's nervousness before the exam is moderate and cannot be compared with the nervousness during cheating, generating a benchmark heat map of each preset body part at this time can more objectively reflect the basic situation of the target proctor.

[0076] The disclosed embodiment uses video to take all-round shots of the target proctor in each examination seat, obtains the key morphological image of each target proctor, obtains the alarm evaluation value by abnormal analysis of the key morphological image, and generates alarm information when all the alarm evaluation values ​​meet the preset alarm conditions. Through intelligent methods, the examinees no longer have room for cheating, avoid the occurrence of cheating, realize unmanned proctoring, and improve the efficiency and accuracy of proctoring.

[0077] Example 2

[0078] The present disclosure also provides an apparatus embodiment that is consistent with the above-mentioned embodiment, and is used to implement the method steps described in the above-mentioned embodiment. The explanation based on the same name meaning is the same as that of the above-mentioned embodiment, and has the same technical effect as that of the above-mentioned embodiment, and will not be repeated here.

[0079] like Figure 3 As shown, the present disclosure provides a remote proctoring device 300, comprising:

[0080] The acquisition unit 301 is used to acquire a plurality of invigilation video images taken in all directions at the same time point for a target invigilator in the examination seat;

[0081] An extraction unit 302 is used to extract a key morphological image of each preset body part of the target proctor based on a plurality of proctoring video images;

[0082] An evaluation unit 303 is used to perform abnormal analysis on each key morphological image and obtain an alarm evaluation value of the corresponding key morphological image;

[0083] The alarm unit 304 is configured to generate an alarm message in response to all alarm evaluation values ​​satisfying a preset alarm condition.

[0084] Optionally, the extraction unit 302 includes:

[0085] A first extraction subunit is used to extract at least one morphological image of each preset body part of the target proctor based on a plurality of proctoring video images;

[0086] A first obtaining subunit is used to input each morphological image into a trained morphological recognition model to at least obtain corresponding morphological complete information;

[0087] The first determining subunit is used to determine, from the morphological images of the preset body parts, a morphological image whose morphological complete information meets a preset preferred condition as a key morphological image.

[0088] Optionally, the first obtaining subunit includes:

[0089] a second obtaining subunit, for obtaining a corresponding morphological warning value in response to inputting each morphological image into the trained morphological recognition model;

[0090] Accordingly, the evaluation unit 303 includes:

[0091] A first generating subunit, configured to generate a corresponding heat map based on each key morphological image;

[0092] The third obtaining subunit is used to obtain the alarm evaluation value of the corresponding key morphological image based on the thermal map of each key morphological image and the morphological warning value and preset weight value related to the key morphological image.

[0093] Optionally, the first generating subunit includes:

[0094] A second extraction subunit is used to extract a body surface area image corresponding to each key morphological image from each key morphological image;

[0095] The second generating subunit is used to generate a thermal map corresponding to each key morphological image based on the body surface area image of each key morphological image.

[0096] Optionally, the third obtaining subunit includes:

[0097] a difference calculation subunit, configured to calculate a difference of the corresponding key morphological image based on a first pixel average value of the heat map of each key morphological image and a second pixel average value of a reference heat map associated with the key morphological image, wherein the reference heat map and the heat map are both heat maps associated with the same preset body part;

[0098] The fourth obtaining subunit is used to obtain the alarm evaluation value of the corresponding key morphological image based on the difference value of each key morphological image and the morphological warning value and the preset weight value related to the key morphological image.

[0099] Optionally, the device further comprises an initial unit;

[0100] The initial unit comprises:

[0101] A pre-acquisition subunit, used for pre-acquiring a reference image of each preset body part of the target invigilator;

[0102] A subunit is pre-generated, and is used to generate a corresponding reference heat map based on each reference image.

[0103] Optionally, the preset body parts include: left hand part, right hand part and / or eyes.

[0104] The disclosed embodiment uses video to take all-round shots of the target proctor in each examination seat, obtains the key morphological image of each target proctor, obtains the alarm evaluation value by abnormal analysis of the key morphological image, and generates alarm information when all the alarm evaluation values ​​meet the preset alarm conditions. Through intelligent methods, the examinees no longer have room for cheating, avoid the occurrence of cheating, realize unmanned proctoring, and improve the efficiency and accuracy of proctoring.

[0105] Example 3

[0106] like Figure 4As shown, this embodiment provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method steps described in the above embodiment.

[0107] Example 4

[0108] An embodiment of the present disclosure provides a non-volatile computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the method steps described in the above embodiment.

[0109] Example 5

[0110] Reference below Figure 4 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0111] like Figure 4 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. In RAM 403, various programs and data required for the operation of the electronic device are also stored. The processing device 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0112] Typically, the following devices may be connected to the I / O interface 405: input devices 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 405 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 409. The communication devices 409 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0113] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0114] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0115] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0116] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0117] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0118] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

Claims

1. A remote proctoring method, characterized in that: include: For the target invigilator in the examination seat, multiple invigilator video images shot in all directions at the same time point are obtained; Extracting key morphological images of each preset body part of the target proctor based on multiple proctoring video images; the preset body parts include: left hand part, right hand part and / or eye part; Performing abnormal analysis on each key morphological image to obtain the alarm evaluation value of the corresponding key morphological image; In response to all alarm evaluation values ​​satisfying preset alarm conditions, generating alarm information; The step of acquiring a key morphological image of each preset body part of the target proctor based on a plurality of proctoring video images comprises: Extracting at least one morphological image of each preset body part of the target proctored subject based on a plurality of proctored video images; Input each morphological image into the trained morphological recognition model to at least obtain the corresponding morphological complete information; From the morphological images of the preset body parts, a morphological image whose morphological complete information meets the preset optimization condition is determined as the key morphological image.

2. The method according to claim 1, characterized in that The step of inputting each morphological image into the trained morphological recognition model to obtain at least the corresponding morphological complete information includes: In response to inputting each morphological image into the trained morphological recognition model, a corresponding morphological warning value is also obtained; Accordingly, performing abnormal analysis on each key morphological image to obtain the alarm evaluation value of the corresponding key morphological image includes: Generate a corresponding heat map based on each key morphological image; Based on the heat map of each key morphological image and the morphological warning value and preset weight value related to the key morphological image, the alarm evaluation value of the corresponding key morphological image is obtained respectively; the preset weight value of each preset body part is used to indicate the importance of each preset body part in the evaluation.

3. The method according to claim 2, characterized in that The step of generating a corresponding heat map based on each key morphological image comprises: Extracting a body surface region image corresponding to each key morphological image from each key morphological image; A heat map corresponding to each key morphology image is generated based on the body surface area image of each key morphology image.

4. The method according to claim 2, characterized in that: The step of obtaining the alarm evaluation value of the corresponding key morphological image based on the heat map of each key morphological image and the morphological warning value and the preset weight value related to the key morphological image comprises: Calculating a difference between the corresponding key morphological images based on a first pixel average value of the heat map of each key morphological image and a second pixel average value of a reference heat map associated with the key morphological image, wherein the reference heat map and the heat map are both heat maps associated with the same preset body part; Based on the difference value of each key morphological image and the morphological warning value and the preset weight value related to the key morphological image, the alarm evaluation value of the corresponding key morphological image is obtained respectively.

5. The method according to claim 4, characterized in that The method further comprises: Acquire in advance a reference image of each preset body part of the target invigilator; A corresponding benchmark heat map is generated based on each benchmark image.

6. A remote proctoring device, characterized in that: include: An acquisition unit is used to acquire multiple invigilation video images taken in all directions at the same time point for a target invigilator in the examination seat; An extraction unit, configured to extract a key morphological image of each preset body part of the target proctor based on a plurality of proctoring video images; The preset body parts include: left hand parts, right hand parts and / or eyes; the step of obtaining the key morphological images of each preset body part of the target proctor based on multiple proctoring video images includes: extracting at least one morphological image of each preset body part of the target proctor based on multiple proctoring video images; inputting each morphological image into a trained morphological recognition model to at least obtain corresponding morphological complete information; and determining, from the morphological images of the preset body parts, a morphological image whose morphological complete information meets a preset preferred condition as a key morphological image; An evaluation unit, used for performing abnormal analysis on each key morphological image, and obtaining an alarm evaluation value of the corresponding key morphological image; The alarm unit is used to generate alarm information in response to all alarm evaluation values ​​satisfying preset alarm conditions.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

8. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method according to any one of claims 1 to 5.

Images