Data processing method and device, equipment, medium and program product

Abstract

The invention provides a data processing method and device, equipment, a medium and a program product, and relates to the technical field of big data. The method comprises the following steps: receiving a first to-do task starting request sent by client equipment; acquiring real-time video information of at least one target examination person from monitoring equipment according to the first to-do task starting request; based on the real-time video information of each target examination person, determining examination cheating information of each target examination person; responding to a received second to-do task starting instruction, and obtaining answer information of each target examination person; correcting the answer information of each target examination person by adopting a first preset answer correction model and a second preset answer correction model to obtain an initial examination result of each target examination person; determining a target examination result of each target examination person based on the initial examination result of each target examination person and the examination cheating information; and sending the target examination result to the client device.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a data processing method, device, equipment, medium and program product. Background Art

[0002] With the rapid development of information technology, online examinations have gradually become an important form of examination in the field of education due to their convenience and efficiency. Online examinations allow examinees to take the examinations through the Internet at any location, greatly improving the flexibility and accessibility of the examinations, and obtaining the examinees' examination status by connecting to the examination equipment camera.

[0003] At present, in general online examinations, invigilators supervise the behavior of candidates through video surveillance, and the examinees mark the papers after the examination. Invigilation and marking are treated as two independent links, which results in low efficiency of the entire examination monitoring and marking process and increased labor costs. Summary of the invention

[0004] The present application provides a data processing method, apparatus, equipment, medium and program product, which are used to solve the problem that in the prior art, in an online examination, an invigilator monitors the behavior of examinees through video surveillance, and after the examination, the examiners correct the examination papers, and the invigilation and correction are processed as two independent links, which results in low efficiency of the entire examination monitoring and correction link and increases labor costs.

[0005] In a first aspect, the present application provides a data processing method, comprising:

[0006] Receiving a first to-do task start request sent by a client device, where the first to-do task start request is triggered by a user through a user interface of the client device;

[0007] According to the first pending task start request, real-time video information of at least one target examinee is obtained from the monitoring device; the first pending task is a monitoring task for starting the examination;

[0008] Determine the cheating information of each target examinee based on the real-time video information of each target examinee;

[0009] In response to receiving the start instruction of the second pending task, obtaining the answer information of each of the target examinees; the second pending task is a task of correcting the answer information of each of the target examinees;

[0010] Using the first preset answer correction model and the second preset answer correction model to correct the answer information of each target test taker, respectively, to obtain the initial test results of each target test taker;

[0011] Determine the target test result of each target test taker based on the initial test result and test cheating information of each target test taker;

[0012] The target test result is sent to a client device.

[0013] In a possible design, determining the cheating information of each target examinee based on the real-time video information of each target examinee includes:

[0014] Determine the facial region information of each target examinee based on the real-time video information of each target examinee and using a face detection algorithm;

[0015] Using a preset feature extraction algorithm to extract the action features of the target examinees in the real-time video information of each of the target examinees, so as to obtain the action feature information of each of the target examinees;

[0016] The examination cheating information of each target examiner is determined based on the facial area information and action feature information of each target examiner.

[0017] In a possible design, the determining of the examination cheating information of each target examinee based on the facial region information and action feature information of each target examinee includes:

[0018] Calculating the facial tilt angle based on the facial region information of each target examinee and using a preset facial key point detection algorithm to obtain the facial tilt angle of each target examinee;

[0019] Comparing the facial tilt angle and action feature information of each target examinee with a preset facial tilt angle threshold and a preset action, respectively, to obtain a comparison result;

[0020] In response to the comparison result that the facial inclination angle of the target examinee is greater than a preset facial inclination angle threshold and / or the action feature information of the target examinee is consistent with the preset action, generating cheating identification information in the test cheating information of the target examinee;

[0021] In response to the comparison result that the facial inclination angle of the target examinee is less than or equal to the preset facial inclination angle threshold and the action feature information of the target examinee is inconsistent with the preset action, non-cheating identification information is generated in the test cheating information of the target examinee.

[0022] In a possible design, the answer information of the target examinee includes subjective answer information;

[0023] The first preset answer correction model and the second preset answer correction model are used to correct the answer information of each target test taker respectively to obtain the initial test result of each target test taker, including:

[0024] Using a first preset answer correction model to extract the score points in the subjective answer information of each target test-taker, and compare them with the preset score points to obtain a score point comparison result;

[0025] Using a second preset answer correction model to extract keywords from the subjective answer information of each target test-taker, and matching them with preset keywords to obtain keyword matching results;

[0026] Determine first score information according to the score point comparison result;

[0027] Determine second score information according to the keyword matching result;

[0028] An initial test result of each of the target test takers is determined based on the first score information and the second score information.

[0029] In a possible design, determining the initial test result of each target test taker based on the first score information and the second score information includes:

[0030] averaging the first score information and the second score information of each of the target test takers to obtain averaged score information;

[0031] The averaged score information corresponding to each of the target test takers is determined as the initial test result of each of the target test takers.

[0032] In a possible design, determining the target test result of each target test taker based on the initial test result and test cheating information of each target test taker includes:

[0033] If the cheating information contains the cheating identification information, subtract the initial test result of the corresponding target test taker from the preset value, and use the result as the target test result of the target test taker;

[0034] If the cheating identification information is not included in the examination cheating information, the initial examination result of the corresponding target examinee is used as the target examination result of the target examinee.

[0035] In a possible design, in response to receiving the second to-be-done task start instruction, before obtaining the answer information of each target test taker, the steps include:

[0036] If in response to receiving a question correction request, obtaining identification information of a target question; the target question is the question in which an error occurs; the identification information of the target question is identification information that uniquely marks the target question;

[0037] Creating a third to-do task based on the identification information of the target topic; the third to-do task is a correction task of the target topic;

[0038] After the first preset answer correction model and the second preset answer correction model are used to correct the answer information of each target test taker to obtain the initial test result of each target test taker, the method further includes:

[0039] In response to receiving the start instruction of the third to-do task, obtaining the score information of the target question corresponding to the target question in the initial test results of each of the target test takers based on the identification information of the target question, and uniformly modifying the score information of the target question to a preset fixed value, and recalculating the initial test results of each of the target test takers based on the modified score information of the target question, so as to obtain the modified initial test results of each of the target test takers;

[0040] The initial test results of each of the target test takers are updated to the modified initial test results of each of the target test takers.

[0041] In a second aspect, the present application provides a data processing device, comprising: a receiving module, used to receive a first to-do task start request sent by a client device; an acquisition module, used to acquire real-time video information of at least one target examinee from a monitoring device according to the first to-do task start request; a determination module, used to determine the examination cheating information of each target examinee based on the real-time video information of each target examinee; the acquisition module, also used to acquire the answer information of each target examinee in response to receiving a second to-do task start instruction; a correction module, used to use a first preset answer correction model and a second preset answer correction model to correct the answer information of each target examinee respectively, so as to obtain the initial examination result of each target examinee; a determination module, used to determine the target examination result of each target examinee based on the initial examination result and examination cheating information of each target examinee; a sending module, used to send the target examination result to the client device.

[0042] In a third aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the data processing method described in the first aspect and various possible designs of the first aspect.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the data processing method described in the first aspect and various possible designs of the first aspect is implemented.

[0044] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the data processing method described in the first aspect and various possible designs of the first aspect.

[0045] The data processing method, apparatus, device, medium and program product provided by the present application receive a first to-do task start request sent by a client device, wherein the first to-do task start request is triggered by a user through a user interface of the client device; according to the first to-do task start request, real-time video information of at least one target examinee is obtained from a monitoring device; the first to-do task is a monitoring task for starting an examination; based on the real-time video information of each target examinee, the examination cheating information of each target examinee is determined; in response to receiving a second to-do task start instruction, the answer information of each target examinee is obtained; the second to-do task is a task for correcting the answer information of each target examinee; the answer information of each target examinee is corrected using a first preset answer correction model and a second preset answer correction model respectively to obtain an initial examination result of each target examinee; the target examination result of each target examinee is determined based on the initial examination result and examination cheating information of each target examinee; and the target examination result is sent to the client device. Since the first pending task is a monitoring task for starting an exam, after receiving the first pending task start request triggered by the user through the user interface of the client device, the real-time video information of at least one target examinee is obtained from the monitoring device. The real-time video information is a real-time record of the exam status of the target examinee, so that the cheating of each target examinee can be determined according to the real-time video information of each target examinee, and the cheating of each target examinee is saved in the exam cheating information. In order to realize the automatic monitoring of the exam and the correction of the answer information of the target examinee after the exam, a batch processing mechanism is adopted to automatically perform the exam monitoring and the correction of the answer information of the target examinee by presetting the pending tasks and the execution order. The second pending task is a task for correcting the answer information of each target examinee, so that after the second pending task is automatically triggered and the start instruction of the second pending task is received, the answer information of each target examinee is obtained, and the answer information of each target examinee is corrected by using the first preset answer correction model and the second preset answer correction model, so as to obtain the initial exam results of each target examinee. To ensure the fairness of the exam, the target exam results of each target examinee will be obtained by combining their initial exam results and cheating information. After determining the target exam results of each target examinee, the target exam results will be sent to the client device. Compared with human proctoring and grading, the preset to-do tasks and batch processing mechanism improve the efficiency of the entire exam and grading process and reduce labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] Figure 1 This is an application scenario diagram of the data processing method applicable to the embodiment of the present application;

[0048] Figure 2 A flowchart of a data processing method provided in one embodiment of the present application;

[0049] Figure 3 A flowchart of a data processing method provided by another embodiment of the present application;

[0050] Figure 4 A schematic diagram of the structure of a data processing device provided in one embodiment of the present application;

[0051] Figure 5 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0052] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0054] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of information such as financial data or user data involved shall comply with the provisions of relevant laws and regulations and shall not violate public order and good morals.

[0055] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0056] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail.

[0057] At present, the invigilation of online exams is mainly done by displaying the real-time monitoring videos of all examinees on a large screen, and the invigilator observes the status of each examinee in the real-time monitoring video to determine whether the examinee is cheating. After the exam is completed, the examinee's answer information is generally graded by manual correction. Therefore, the entire exam monitoring and correction process requires a lot of manpower investment, which increases the investment in manpower costs, and the efficiency of the entire exam monitoring and correction process is low.

[0058] In view of the above technical problems, the present application proposes the following technical concept: instead of manually completing the examination monitoring and grading process, the examination monitoring and grading process is automatically triggered in the form of preset to-do tasks and preset execution order. Specifically, by triggering the first to-do task on the client device, the user starts the examination monitoring task, and then automatically obtains the real-time video information of at least one target examinee, and the examination cheating information of each target examinee can be obtained through the real-time video information of each target examinee. Further, in the examination grading process, by automatically triggering the second to-do task to start the task of correcting the answer information of each target examinee, the answer information of each target examinee is automatically obtained, so that the first preset answer correction model and the second preset answer correction model are used to correct the answer information of each target examinee respectively, so as to obtain the initial examination results of each target examinee. And in order to ensure the fairness of the examination, the target examination results of each target examinee are finally determined according to the initial examination results and examination cheating information of each target examinee, and the target examination results are sent to the client device. By automatically monitoring the exams and correcting the answers of each target examinee, the efficiency of the entire exam and correction process is improved and labor costs are reduced.

[0059] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0060] Figure 1 is an application scenario diagram of the data processing method applicable to the embodiment of the present application, such as Figure 1As shown. The system corresponding to the data processing method in the embodiment of the present application may include: a client device 11, a server device 12, and a monitoring device 13. The user triggers the start of the first pending task through the user interface of the client device 11, and the client device 11 sends the first pending task start request to the server device 12. The first pending task is a monitoring task for starting an exam. In response to receiving the first pending task start request, the server device 12 obtains the real-time video information of at least one target examinee from the monitoring device 13. The exam cheating information of each target examinee is determined according to the real-time video information of each target examinee. When the server device 12 detects that the first pending task is completed, the second pending task will be automatically triggered according to the preset batch processing mechanism. Among them, the second pending task is a task for correcting the answer information of each target examinee. In response to receiving the second pending task start instruction, the server device 12 obtains the answer information of each target examinee, and uses the first preset answer correction model and the second preset answer correction model to correct the answer information of each target examinee, thereby obtaining the initial exam results of each target examinee. Furthermore, the server device determines the target test result of each target test taker based on the test cheating information of each target test taker and the initial test result. The server device 12 sends the target test result of each target test taker to the client device 11, which can then be displayed on the user interface of the client device.

[0061] Figure 2 A flowchart of a data processing method provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the execution subject of this embodiment is a data processing device, which can be implemented by a computer program or a medium storing relevant computer programs, such as a USB flash drive and / or an optical disk, etc.; or, it can also be implemented by a physical device integrated or installed with relevant computer programs, such as a chip, an electronic device, etc. The data processing method provided in this embodiment includes the following steps:

[0062] S201, receiving a first to-do task start request sent by a client device.

[0063] Among them, the first task to be done is the monitoring task of starting the exam.

[0064] Specifically, in this embodiment, the user triggers the start of the first to-do task through the user interface of the client device, and the client device sends a first to-do task start request to the server device.

[0065] S202, according to the start request of the first to-be-done task, obtaining real-time video information of at least one target examinee from a monitoring device.

[0066] The target examinee is a person who takes the exam, and the real-time video information is real-time monitoring video information of the target examinee when taking the exam.

[0067] Specifically, in this embodiment, after receiving the first to-be-done task start request, the server device responds by acquiring real-time video information of at least one target examinee through a pre-connected monitoring device.

[0068] It is understandable that the server device and the monitoring device establish a connection through a preset method and can exchange data.

[0069] Optionally, the preset manner may be an interface connection or other manners, which is not limited in this embodiment.

[0070] S203: Determine the cheating information of each target examinee based on the real-time video information of each target examinee.

[0071] Among them, the exam cheating information is information that marks whether the target examinee cheated.

[0072] Specifically, in this embodiment, the server-side device uses a preset detection algorithm to detect whether non-target examinees appear in the real-time video information corresponding to each target examinee and whether each target examinee exhibits preset behaviors. When the target examinee performs at least one of the preset behaviors or the non-target examinee appears in the real-time video, a corresponding cheating mark is generated in the exam cheating information of the corresponding target examinee. When the target examinee does not perform the preset behavior and the non-target examinee does not appear in the real-time video, a non-cheating mark is generated in the exam cheating information of the corresponding target examinee.

[0073] Furthermore, when it is determined that the target examinee has performed a preset behavior or at least any one of the non-target examinees appears in the real-time video, the server device quickly saves the current status of the target examinee and the question identification information corresponding to the current answer page of the target examinee, and stores it in the exam cheating information of the target examinee.

[0074] The title identification information is information for identifying the title, and may be the title number or the like.

[0075] Optionally, the preset behavior may be the action of holding a mobile phone or turning a book, etc., which is not limited in this embodiment.

[0076] Optionally, the preset detection algorithm may be a face recognition algorithm or an image processing algorithm, etc., which is not limited in this embodiment.

[0077] S204, in response to receiving the second to-be-done task start instruction, obtaining answer information of each target test-taker.

[0078] The second pending task is to correct the answer information of each target examinee. The examination information is the answer information of the target examinee corresponding to the examination answer sheet.

[0079] Specifically, in this embodiment, after the first to-be-done task is completed, the server-side device automatically triggers the start of the second to-be-done task according to a preset batch processing mechanism.

[0080] It is understood that batch processing is a computer processing method that allows a series of tasks to be combined into a batch in sequence, and then the computer system executes these tasks in sequence without human intervention. When the user triggers the first to-do task, the subsequent to-do tasks do not need to be triggered by the user, and the to-do tasks are automatically triggered and executed in a preset order.

[0081] S205: Use the first preset answer correction model and the second preset answer correction model to correct the answer information of each target test taker respectively to obtain the initial test result of each target test taker.

[0082] The first preset answer correction model is a model for correction based on the score points in the answer information of the target examinee. The second preset answer correction model is a model for correction based on the keywords in the answer information of the target examinee. The initial test result is the score after the answer information of the target examinee is corrected.

[0083] Specifically, in this embodiment, the server-side device uses the first preset answer correction model to correct the scoring points in the answer information of each target examinee, uses the first preset answer correction model to correct the keywords in the answer information of each target examinee, and obtains the initial test results of each target examinee according to the preset score calculation algorithm.

[0084] S206, determining the target test result of each target test taker based on the initial test result and test cheating information of each target test taker.

[0085] Among them, the target test result is the final test result of the target test taker.

[0086] Specifically, in this embodiment, the server device determines the target examinee with cheating identification information based on the exam cheating information of each target examinee and obtains the corresponding question identification information when cheating, thereby changing the score of the corresponding question identification information in the initial exam result of the target examinee with cheating identification information to 0, and recalculates the score as the target exam result of the target examinee with cheating identification information. For the target examinee whose exam cheating information does not have cheating identification information, the target exam result is equal to the initial exam result.

[0087] S207, sending the target test result to the client device.

[0088] Specifically, in this embodiment, after determining the target test result, the server device sends the target test result to the client device. The target test result can be displayed in the user interface of the client device.

[0089] The data processing method provided by the present application includes: receiving a first pending task start request sent by a client device, the first pending task start request is triggered by a user through a user interface of the client device; according to the first pending task start request, obtaining real-time video information of at least one target examinee from a monitoring device. Determine the cheating information of each target examinee based on the real-time video information of each target examinee. In response to receiving a second pending task start instruction, obtain the answer information of each target examinee. Use a first preset answer correction model and a second preset answer correction model to correct the answer information of each target examinee respectively to obtain the initial test results of each target examinee. Determine the target test results of each target examinee based on the initial test results and the cheating information of each target examinee; and send the target test results to the client device. Since the first pending task is a monitoring task for starting an exam, after receiving the first pending task start request triggered by the user through the user interface of the client device, obtain the real-time video information of at least one target examinee from the monitoring device. The real-time video information is a real-time record of the test status of the target examinee, so that the cheating situation of each target examinee can be determined according to the real-time video information of each target examinee, and the cheating situation of each target examinee is saved in the test cheating information. In order to realize the automatic monitoring of the test and the correction of the answer information of the target examinee after the test, a batch processing mechanism is adopted to automatically perform the test monitoring and the correction of the answer information of the target examinee by presetting the to-do tasks and the execution order. The second to-do task is the task of correcting the answer information of each target examinee, so that after the second to-do task is automatically triggered and the start instruction of the second to-do task is received, the answer information of each target examinee is obtained, and the answer information of each target examinee is corrected by using the first preset answer correction model and the second preset answer correction model, so as to obtain the initial test results of each target examinee. And in order to ensure the fairness of the test, the target test results of each target examinee will be obtained by combining the initial test results of each target examinee and the cheating information of the test. After determining the target test results of each target test taker, the target test results are sent to the client device. Compared with human proctoring and grading, the preset to-do tasks and batch processing mechanism improve the efficiency of the entire test and grading process and reduce labor costs.

[0090] As an optional implementation manner, based on the above embodiment, the examination cheating information of each target examinee is determined based on the real-time video information of each target examinee, including:

[0091] Based on the real-time video information of each target examinee and using a face detection algorithm, the facial region information of each target examinee is determined;

[0092] Using a preset feature extraction algorithm to extract the motion features of the target examinees in the real-time video information of each target examinee, so as to obtain the motion feature information of each target examinee;

[0093] The examination cheating information of each target examinee is determined based on the facial area information and action feature information of each target examinee.

[0094] The target examinee's facial region information is feature information of the target examinee's facial region. The target examinee's action feature information is feature information of the target examinee's behavior in the real-time video information.

[0095] Specifically, in this embodiment, the server device uses a preset video decoder to decode the real-time video information of each target examinee and convert it into the form of video frames, and uses a face detection algorithm to perform face detection on each frame image in the real-time video information of each target examinee to obtain the facial area information of each target examinee, and uses a preset feature extraction algorithm to capture the dynamic changes of the target examinee from each frame image corresponding to the real-time video information of each target examinee, thereby extracting the motion features of the target examinee, and then obtaining the motion feature information of each target examinee. The server device judges whether each target examinee cheats according to the facial area information and motion feature information of the target examinee according to the preset judgment algorithm. If the facial area information and motion feature information of the target examinee are judged to be cheating, a corresponding cheating mark is generated in the exam cheating information of the corresponding target examinee, and if the facial area information and motion feature information of the target examinee are judged to be non-cheating, a corresponding non-cheating mark is generated in the exam cheating information of the corresponding target examinee.

[0096] Optionally, the preset face detection algorithm may be an MTCNN algorithm or other face detection algorithms, which is not limited in this embodiment. The preset feature extraction algorithm may be a long short-term memory neural network or other feature extraction algorithms, which is not limited in this embodiment.

[0097] Among them, MTCNN (Multi-task Convolutional Neural Network) is a multi-task convolutional neural network, mainly used for face detection and facial key point location. LSTM (Long Short-Term Memory) is a special type of recurrent neural network (RNN) that has the ability to process long-term dependencies in sequence data and can be used for feature extraction.

[0098] It is understandable that video decoding is to restore real-time video information to frame images. The preset decoder can be a video decoder custom-written according to the algorithm in the video coding standard. The video coding standard is a set of technical specifications for guiding video data compression and decompression.

[0099] The data processing method provided by the present application determines the cheating information of each target examinee based on the real-time video information of each target examinee, including: determining the facial area information of each target examinee based on the real-time video information of each target examinee and using a face detection algorithm; extracting the motion features of the target examinee in the real-time video information of each target examinee using a preset feature extraction algorithm to obtain the motion feature information of each target examinee; determining the cheating information of each target examinee based on the facial area information and motion feature information of each target examinee. Since the facial area of ​​each target examinee can be accurately identified in the real-time video information by using a face detection algorithm, and the motion changes of the target examinee can be captured by using a preset feature extraction algorithm, the server-side device can judge whether each target examinee has cheated more comprehensively and accurately based on the facial area information and motion feature information of each target examinee, thereby improving the fairness of the examination and reducing labor costs.

[0100] As an optional implementation, based on the above embodiment, the examination cheating information of each target examinee is determined based on the facial region information and action feature information of each target examinee, including:

[0101] The facial tilt angle is calculated based on the facial region information of each target examinee and by using a preset facial key point detection algorithm to obtain the facial tilt angle of each target examinee;

[0102] The facial tilt angle and motion feature information of each target examinee are respectively compared with the preset facial tilt angle threshold and the preset motion to obtain a comparison result;

[0103] In response to the comparison result that the facial inclination angle of the target examinee is greater than a preset facial inclination angle threshold and / or the action feature information of the target examinee is consistent with the preset action, cheating identification information in the test cheating information of the target examinee is generated;

[0104] In response to the comparison result that the facial inclination angle of the target examinee is less than or equal to the preset facial inclination angle threshold and the action feature information of the target examinee is inconsistent with the preset action, non-cheating identification information is generated in the test cheating information of the target examinee.

[0105] Specifically, in this embodiment, the server device uses a preset facial key point detection algorithm and locates the facial key points of each target examinee based on the facial region information of each target examinee, and calculates the facial inclination angle by geometry based on the detected facial key points. Further, the calculated facial inclination angle is compared with the preset facial inclination angle threshold, and the action feature information of each target examinee is feature-compared with the preset action to obtain the corresponding comparison result. When the comparison result includes at least one of the following: the facial inclination angle of the target examinee is greater than the preset facial inclination angle threshold, and the action feature information of the target examinee is consistent with the preset action, the corresponding target examinee is considered to have cheated, and cheating identification information in the exam cheating information of the target examinee is generated. When the comparison result includes that the facial inclination angle of the target examinee is less than or equal to the preset facial inclination angle threshold, and the action feature information of the target examinee is inconsistent with the preset action, the corresponding target examinee is considered not to have cheated, and non-cheating identification information in the exam cheating information of the target examinee is generated.

[0106] When calculating the facial inclination angle by geometry, the facial inclination angle of the target examinee may be obtained by calculating the angle between the vectors between preset key points in the facial area information of the target examinee and the preset reference direction.

[0107] The data processing method provided by the present application determines the cheating information of each target examinee based on the facial area information and motion feature information of each target examinee, including: calculating the facial inclination angle based on the facial area information of each target examinee and using a preset facial key point detection algorithm to obtain the facial inclination angle of each target examinee; comparing the facial inclination angle and motion feature information of each target examinee with a preset facial inclination angle threshold and a preset action respectively to obtain a comparison result; in response to the comparison result that the facial inclination angle of the target examinee is greater than the preset facial inclination angle threshold and / or the motion feature information of the target examinee is consistent with the preset action, generating cheating identification information in the cheating information of the target examinee; in response to the comparison result that the facial inclination angle of the target examinee is less than or equal to the preset facial inclination angle threshold and the motion feature information of the target examinee is inconsistent with the preset action, generating non-cheating identification information in the cheating information of the target examinee. Since the preset facial key point detection algorithm is used to locate the key points in the facial area information of each target examinee and calculate the facial inclination angle of each target examinee, the head posture of the target examinee is determined in a quantitative manner, and the facial inclination angle and action feature information of each target examinee are compared with the preset facial inclination angle threshold and the preset action respectively, so as to automatically determine whether each target examinee is cheating according to the comparison result and generate corresponding identification information, thereby improving the efficiency of judging whether the target examinee is cheating. And if the target examinee meets any one of the following conditions: the facial inclination angle is greater than the preset facial inclination angle threshold and the action feature information of the target examinee is consistent with the preset action, then it is determined to be cheating. When the target examinee meets the condition that the facial inclination angle is less than or equal to the preset facial inclination angle threshold and the action feature information of the target examinee is inconsistent with the preset action, then it is determined to be not cheating. Through multi-dimensional analysis of the behavior of the target examinee, the accuracy of cheating detection is improved.

[0108] As an optional implementation, based on the above embodiment, the answer information of the target test taker includes subjective answer information;

[0109] The first preset answer correction model and the second preset answer correction model are used to correct the answer information of each target test taker respectively to obtain the initial test results of each target test taker, including:

[0110] The first preset answer correction model is used to extract the score points in the subjective answer information of each target test-taker, and compare them with the preset score points to obtain the score point comparison result;

[0111] The second preset answer correction model is used to extract keywords from the subjective answer information of each target test-taker, and match them with the preset keywords to obtain keyword matching results;

[0112] Determine first score information according to the score point comparison result;

[0113] Determine second score information according to the keyword matching result;

[0114] An initial test result of each target test taker is determined based on the first score information and the second score information.

[0115] Among them, subjective questions are a type of question that requires examinees to demonstrate personal understanding, analysis, evaluation, interpretation or creative thinking. Subjective answer information is the answer information of the target examinee to the subjective question, which may include the answer information of at least one subjective question. Preset keywords are words or phrases that must appear in the corresponding subjective question. Preset scoring points are the scoreable content corresponding to the subjective question.

[0116] Specifically, in this embodiment, the server-side device uses the first preset answer correction model to perform content recognition on the text content corresponding to each subjective question in the subjective answer information of each target examinee and extracts the score points contained in the content based on the preset score points corresponding to each subjective question, and then compares them one by one with the preset score points corresponding to each subjective question, to determine whether the score points of each subjective question in the subjective answer information of each target examinee correspond to the corresponding preset score points, and uses the actual corresponding results of the score points of each subjective question in the subjective answer information of each target examinee and the preset score points as the score point comparison result. Further, the server-side device uses the second preset answer correction model and extracts the corresponding keywords of each subjective question in the subjective answer information of each target examinee based on the preset keywords of each subjective question, matches the extracted keywords of each subjective question with the corresponding preset keywords, and uses the actual matching results of the key points of each subjective question in the subjective answer information of each target examinee and the corresponding preset key points as the keyword matching result. Among them, for the score point comparison result, taking a subjective question as an example, if the score points in the subjective answer information of each target examinee correspond to the preset score points one by one, the corresponding scores of all the score points are added together, and the added score is used as the first score information of the corresponding subjective question of each target examinee. If the score points in the subjective answer information of each target examinee partially correspond to the preset score points, the corresponding scores of the corresponding score points are added together, and the added score is used as the first score information of the corresponding subjective question of each target examinee. The first score information of each target examinee is the score information obtained by adding the first score information of all subjective questions of each target examinee. For the keyword matching results, take a subjective question as an example. If the keywords of the subjective question in the subjective answer information of each target examinee are matched one by one with the preset keywords of the subjective question, the corresponding scores of all keywords are added together, and the summed scores are used as the second score information of the corresponding subjective question of each target examinee. If the keywords of the subjective question in the subjective answer information of each target examinee are partially matched with the preset keywords of the subjective question, the corresponding scores of the corresponding keywords are added together, and the summed scores are used as the second score information of the corresponding subjective question of each target examinee. The second score information of each target examinee is the score information after the second score information of all subjective questions of each target examinee is added together. The first score information and the second score information of each target examinee are calculated according to the preset proportion to determine the initial test results of each target examinee. In addition, the first score information and the second score information of each subjective question of each target examinee can also be saved in the initial test results of each target examinee.

[0117] It can be understood that the test contains at least one subjective question, that is, the answer information of each target test taker contains the answer information of at least one subjective question, and each subjective question has different preset scoring points and preset keywords, so when the first preset answer correction model and the second preset answer correction model are used to correct the answer information of each target test taker respectively, each subjective question is corrected respectively. The first score information and the second score information are respectively the sum of the scores of all subjective questions.

[0118] The data processing method provided by the present application, the answer information of the target test takers includes subjective answer information; the first preset answer correction model and the second preset answer correction model are used to correct the answer information of each target test taker respectively, so as to obtain the initial test results of each target test taker, including: using the first preset answer correction model to extract the score points in the subjective answer information of each target test taker, and compare them with the preset score points to obtain the score point comparison result; using the second preset answer correction model to extract the keywords in the subjective answer information of each target test taker, and match them with the preset keywords to obtain the keyword matching result; determining the first score information according to the score point comparison result; determining the second score information according to the keyword matching result; determining the initial test results of each target test taker based on the first score information and the second score information. Since the first preset answer correction model is used to extract the score points in the subjective answer information of each target test taker and compare them with the preset score points, it can ensure that the scoring is more accurate and improve the correction efficiency. In addition, a second preset answer correction model is used to extract keywords from the subjective answer information of each target examinee and match them with preset keywords, which can enhance the comprehensiveness of the correction. Furthermore, the first score information and the second score information are determined through the corresponding comparison results of the score points and keywords, and the initial test results of each target examinee are determined based on the first score information and the second score information. By combining the correction of the score points and keywords, the comprehensiveness and reliability of the initial test results of each target examinee are improved.

[0119] As an optional implementation manner, based on the above embodiment, determining the initial test result of each target test taker based on the first score information and the second score information includes:

[0120] The first score information and the second score information of each target test taker are averaged to obtain average score information;

[0121] The averaged score information corresponding to each target test taker is determined as the initial test result of each target test taker.

[0122] Specifically, in this embodiment, the first score information and the second score information of each target examinee are obtained, and the first score information and the second score information of each target examinee are added and averaged to obtain the averaged score information, and the averaged score information is used as the initial test result of each target examinee.

[0123] The data processing method provided by the present application determines the initial test results of each target test taker based on the first score information and the second score information, including: averaging the first score information and the second score information of each target test taker to obtain the averaged score information; determining the averaged score information corresponding to each target test taker as the initial test result of each target test taker. Since the first score information and the second score information of each target test taker are averaged and used as the initial test result of each target test taker, the differences between different score information are balanced through the average calculation, thereby obtaining a more accurate and stable initial test result.

[0124] As an optional implementation, based on the above embodiment, the target test result of each target test taker is determined based on the initial test result and test cheating information of each target test taker, including:

[0125] If the cheating information contains cheating identification information, the initial test result of the corresponding target test taker is subtracted from the preset value, and the calculation result is used as the target test result of the target test taker;

[0126] If the examination cheating information does not contain cheating identification information, the initial examination result of the corresponding target examinee will be used as the target examination result of the target examinee.

[0127] Specifically, in this embodiment, when the server device detects that the cheating information of the target examinee contains cheating identification information, the total score of the initial test result of the target examinee is subtracted from the preset value, and the score after subtracting the preset value is used as the target test result of the target examinee. For the target examinee whose cheating information does not contain cheating identification information, the initial test result of the target examinee is directly used as the target test result. Optionally, the preset value can be a positive integer greater than 0 and less than the total score of the test, which is not limited in this embodiment.

[0128] The data processing method provided by the present application determines the target test result of each target test taker based on the initial test result and the test cheating information of each target test taker, including: if the test cheating information contains cheating identification information, the initial test result of the corresponding target test taker is subtracted from a preset value, and the calculation result is used as the target test result of the target test taker; if the test cheating information does not contain cheating identification information, the initial test result of the corresponding target test taker is used as the target test result of the target test taker. Since the test cheating information of the target test taker contains identification information of whether the target test taker cheated, when determining the target test result of each target test taker, the target test result is determined according to the identification information contained in the test cheating information of the target test taker and the initial test result. To ensure the fairness and seriousness of the examination, when the target examinee's cheating identification information contains cheating identification information, the preset value will be subtracted from the corresponding target examinee's initial examination result. When the target examinee's cheating identification information does not contain cheating identification information, the initial examination result will not be modified. Therefore, different processing mechanisms are triggered based on the identification information, which not only effectively punishes cheating behavior, but also protects the interests of honest target examinees, while improving the accuracy and efficiency of the processing process.

[0129] As an optional implementation manner, based on the above embodiment, in response to receiving the second to-do task start instruction, before obtaining the answer information of each target test taker, it includes:

[0130] If in response to receiving a question correction request, obtaining identification information of a target question;

[0131] A third to-do task is created based on the identification information of the target topic.

[0132] After respectively correcting the answer information of each target examinee by using the first preset answer correction model and the second preset answer correction model to obtain the initial test result of each target examinee, the method further includes:

[0133] In response to receiving the start instruction of the third to-do task, the score information of the corresponding target question in the initial test results of each target examinee is obtained based on the identification information of the target question, and the score information of the target question is uniformly modified to a preset fixed value, and the initial test results of each target examinee are recalculated based on the modified score information of the target question to obtain the modified initial test results of each target examinee.

[0134] The initial test results of each target test taker are updated to the revised initial test results of each target test taker.

[0135] The target question is the question in which an error occurs. The identification information of the target question is identification information that uniquely marks the target question. The third to-do task is a task of correcting the target question. The modified initial test result of each target test taker is the test result recalculated after modifying the score information of the target question.

[0136] Specifically, in this embodiment, in response to receiving the second to-do task start instruction, before obtaining the answer information of each target examinee, that is, during the examination, the user triggers the question correction through the client device and sends a question correction request to the server device, which includes the identification information of the target question. After receiving the question correction request, the server device obtains the identification information of the target question. The server device automatically creates a third to-do task and sets the execution start order, and saves the identification information of the target question in the third to-do task. After obtaining the initial examination results of each target examinee, the server device automatically triggers the third to-do task start instruction, and obtains the score information of the corresponding target question in the initial examination results of each target examinee based on the identification information of the target question saved in the third to-do task, and then changes the score information of the corresponding target question of each target examinee to a preset fixed value. Since the score information of the target question is modified, the score information of each question is re-added according to the modified score information of the target question, and the modified initial examination results of each target examinee are obtained, and the initial examination results of each target examinee are updated to the modified initial examination results of each target examinee.

[0137] Optionally, the preset fixed value may be 0, or may be the corresponding score of the target question, or may be other positive integers, which is not limited in this embodiment.

[0138] The data processing method provided by the present application, in response to receiving the second to-do task start instruction, before obtaining the answer information of each target examinee, includes: if in response to receiving a question correction request, obtaining the identification information of the target question; creating a third to-do task based on the identification information of the target question; using the first preset answer correction model and the second preset answer correction model to respectively correct the answer information of each target examinee to obtain the initial test result of each target examinee, and also includes: in response to receiving the third to-do task start instruction, obtaining the score information of the corresponding target question in the initial test result of each target examinee based on the identification information of the target question, and uniformly modifying the score information of the target question to a preset fixed value, and recalculating the initial test result of each target examinee based on the modified score information of the target question to obtain the modified initial test result of each target examinee; updating the initial test result of each target examinee to the modified initial test result of each target examinee. Since a request for error correction of a test question is received, it means that an error has occurred in the test question, which in turn causes the answer to the test question to be inconsistent with the initial answer. Therefore, by obtaining the identification information of the target question and creating a third to-do task, the error correction process is separated from the regular grading, which helps to improve processing efficiency and accuracy. Furthermore, after the grading is completed, the third to-do task is automatically triggered to obtain the score information of the corresponding target question based on the identification information of the target question, and it is uniformly modified to a preset fixed value for processing, simplifying the processing flow, and recalculating based on the modified score information of the target question, and updating the calculated modified initial test results of each target test taker to the initial test results of each target test taker, thereby ensuring data consistency and ensuring the accuracy of the initial test results of each target test taker.

[0139] Figure 3 A flowchart of a data processing method provided in another embodiment of the present application is shown in FIG. Figure 3 As shown, the execution subject of this embodiment is a data processing system. The system includes: a server device and a client device. The data processing method provided in this embodiment includes the following steps:

[0140] S301, a user triggers the start of a first to-do task through a client device, and the client device sends a request to start the first to-do task to a server device.

[0141] S302, the server device obtains real-time video information of at least one target test taker from the monitoring device according to the received first to-do task start request.

[0142] S303, the server device extracts the facial region information and motion features of each target examinee in the real-time video information of each target examinee by adopting a face detection algorithm and a preset feature extraction algorithm to obtain the facial region information and motion feature information of each target examinee.

[0143] S304, the server device determines the facial inclination angle of each target examinee according to the facial area information of each target examinee and adopts a preset facial key point detection algorithm.

[0144] S305, the server device compares the facial inclination angle of each target examinee with a preset facial inclination angle threshold, and compares the action feature information of each target examinee with a preset action to obtain a comparison result.

[0145] S306, the server device determines whether each target examinee cheats based on the comparison result of each target examinee.

[0146] S307, if the comparison result is at least one of the following: the facial inclination angle of the target examinee is greater than the preset facial inclination angle threshold and the action feature information of the target examinee is consistent with the preset action, the server-side device determines that the corresponding target examinee is a cheater, and generates cheating identification information in the target examinee's cheating information.

[0147] S308, if the comparison result is that the facial inclination angle of the target examinee is less than or equal to the preset facial inclination angle threshold and the action feature information of the target examinee is inconsistent with the preset action, the server-side device determines that the corresponding target examinee is not cheating, and generates non-cheating identification information in the target examinee's examination cheating information.

[0148] S309, the server device responds to the completion of the first pending task, the batch processing mechanism automatically triggers the second pending task, and in response to receiving the start instruction of the second pending task, obtains the answer information of each target test taker.

[0149] S310, the server-side device uses the first preset answer correction model and the second preset answer correction model to correct the answer information of each target test taker respectively to obtain the initial test result of each target test taker.

[0150] S311, the server device obtains identification information in the examination cheating information of each target examinee, and if the examination cheating information contains cheating identification information, the initial examination result of the corresponding target examinee is subtracted from a preset value, and the calculation result is used as the target examination result of the target examinee. If the examination cheating information does not contain cheating identification information, the initial examination result of the corresponding target examinee is used as the target examination result of the target examinee.

[0151] S312, the server-side device, based on the target test results of each target test taker and the identification information in the test cheating information of each target test taker, selects the target test takers whose test cheating information does not contain cheating identification information as valid target test result candidates, and selects the valid target test result candidates from high to low according to the preset ratio according to the corresponding scores of the target test results of each target test taker, and selects the valid target test result candidates within the preset ratio as the target test passed candidates.

[0152] Among them, the target test result valid personnel are the target test takers whose test cheating information does not contain cheating identification information. The target test pass personnel are the target test result valid personnel whose target test results are sorted from high to low and selected from the target test result valid personnel included in the preset proportion.

[0153] Optionally, the preset ratio may be 30%, or other ratios, which is not limited in this embodiment.

[0154] The target test result of the last person who passed the target test is used as the target test score line. The target test score line is the dividing line that indicates whether the target test candidates have passed the test.

[0155] S313, the server device sends the determined target test results and test cheating information of each target test taker, as well as the target test result valid candidates, target test passers, and the target test score line to the client device.

[0156] Figure 4 A structural diagram of a data processing device provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the data processing device provided in this embodiment is located in an electronic device, and the data processing device 40 provided in this embodiment includes: a receiving module 41, an acquisition module 42, a correction module 43, a determination module 44, and a sending module 45.

[0157] Among them, the receiving module 41 is used to receive the first to-do task start request sent by the client device; the acquisition module 42 is used to obtain the real-time video information of at least one target examinee from the monitoring device according to the first to-do task start request; the determination module 44 is used to determine the examination cheating information of each target examinee based on the real-time video information of each target examinee; the acquisition module 42 is also used to obtain the answer information of each target examinee in response to receiving the second to-do task start instruction; the correction module 43 is used to use the first preset answer correction model and the second preset answer correction model to correct the answer information of each target examinee respectively, so as to obtain the initial examination result of each target examinee; the determination module 44 determines the target examination result of each target examinee based on the initial examination result and examination cheating information of each target examinee; the sending module 45 is used to send the target examination result to the client device.

[0158] Optionally, the determination module 44, when determining the cheating information of each target examinee based on the real-time video information of each target examinee, is specifically used to: determine the facial area information of each target examinee based on the real-time video information of each target examinee and using a face detection algorithm; extract the motion features of the target examinees in the real-time video information of each target examinee using a preset feature extraction algorithm to obtain the motion feature information of each target examinee; determine the cheating information of each target examinee based on the facial area information and motion feature information of each target examinee.

[0159] Optionally, the determination module 44, when determining the cheating information of each target examinee based on the facial area information and motion feature information of each target examinee, is specifically used to: calculate the facial inclination angle based on the facial area information of each target examinee and using a preset facial key point detection algorithm to obtain the facial inclination angle of each target examinee; compare the facial inclination angle and motion feature information of each target examinee with a preset facial inclination angle threshold and a preset action, respectively, to obtain a comparison result; in response to the comparison result that the facial inclination angle of the target examinee is greater than the preset facial inclination angle threshold and / or the motion feature information of the target examinee is consistent with the preset action, then generate cheating identification information in the cheating information of the target examinee; in response to the comparison result that the facial inclination angle of the target examinee is less than or equal to the preset facial inclination angle threshold and the motion feature information of the target examinee is inconsistent with the preset action, then generate non-cheating identification information in the cheating information of the target examinee.

[0160] Optionally, the answer information of the target test-taker includes subjective answer information.

[0161] Correspondingly, the grading module 43, when adopting the first preset answer grading model and the second preset answer grading model to respectively grade the answer information of each target test taker to obtain the initial test result of each target test taker, is specifically used for: adopting the first preset answer grading model to extract the score points in the subjective answer information of each target test taker, and comparing them with the preset score points to obtain the score point comparison result; adopting the second preset answer grading model to extract the keywords in the subjective answer information of each target test taker, and matching them with the preset keywords to obtain the keyword matching result; determining the first score information according to the score point comparison result; determining the second score information according to the keyword matching result; and determining the initial test result of each target test taker based on the first score information and the second score information.

[0162] Optionally, the determination module 44, when determining the initial test result of each target test taker based on the first score information and the second score information, is specifically used to: average the first score information and the second score information of each target test taker to obtain the averaged score information; and determine the averaged score information corresponding to each target test taker as the initial test result of each target test taker.

[0163] Optionally, the determination module 44, when determining the target examination result of each target examinee based on the initial examination result and examination cheating information of each target examinee, is specifically used to: if the examination cheating information contains cheating identification information, then subtract the initial examination result of the corresponding target examinee from a preset value, and use the calculation result as the target examination result of the target examinee; if the examination cheating information does not contain cheating identification information, then use the initial examination result of the corresponding target examinee as the target examination result of the target examinee.

[0164] Optionally, the data processing device provided in this embodiment further includes: a creation module, a calculation module, and an update module.

[0165] Correspondingly, the acquisition module 42 is also used for obtaining the answer information of each target test taker in response to receiving the second pending task start instruction, and obtaining the answer information of each target test taker, if in response to receiving the question correction request, then obtaining the identification information of the target question; the target question is the question with an error; the identification information of the target question is the identification information that uniquely marks the target question. The creation module is used to create a third pending task based on the identification information of the target question. The third pending task is a correction task for the target question. The acquisition module 41 is also used to use the first preset answer correction model and the second preset answer correction model to respectively correct the answer information of each target test taker, so as to obtain the initial test results of each target test taker, and then, in response to receiving the third pending task start instruction, obtain the score information of the corresponding target question in the initial test results of each target test taker based on the identification information of the target question, and uniformly modify the score information of the target question to a preset fixed value. The calculation module is used to recalculate the initial test results of each target test taker based on the modified score information of the target question to obtain the modified initial test results of each target test taker. The updating module is used to update the initial examination results of each target examinee to the modified initial examination results of each target examinee.

[0166] The data processing device provided in the embodiment of the present application can be used to execute the technical solution of the data processing method in the above embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0167] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or physically separated. Moreover, these modules can be all implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware.

[0168] Figure 5 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 5 As shown, the electronic device 50 may include: a processor 51 and a memory 52.

[0169] The memory 52 stores computer-executable instructions; the processor 51 executes the computer-executable instructions stored in the memory 52 to implement the data processing method provided by any of the above embodiments. The relevant descriptions can be understood by referring to the relevant descriptions and effects corresponding to the steps in the accompanying drawings, and no further details are given here.

[0170] The processor 51 can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0171] The memory 52 is connected to the processor 51 via a system bus and completes communication between them. The memory 52 is used to store computer program instructions.

[0172] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory.

[0173] The electronic device provided in the embodiment of the present application may be the terminal device of the above embodiment.

[0174] An embodiment of the present application also provides a chip for executing instructions, which is used to execute the technical solution of the data processing method in the above embodiment.

[0175] An embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the technical solution of the data processing method of the above embodiment.

[0176] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, it can implement the technical solution of the data processing method in the above embodiment.

[0177] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0178] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0179] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0180] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the methods of various embodiments of the present application.

[0181] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0182] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0183] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0184] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0185] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0186] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0187] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0188] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0189] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0190] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0191] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A data processing method, characterized in that: include: Receiving a first to-do task start request sent by a client device, where the first to-do task start request is triggered by a user through a user interface of the client device; Acquire real-time video information of at least one target examinee from a monitoring device according to the first to-do task start request; The first to-do task is a monitoring task for starting an exam; Determine the examination cheating information of each of the target examinees based on the real-time video information of each of the target examinees; In response to receiving the start instruction of the second pending task, obtaining the answer information of each of the target examinees; the second pending task is a task of correcting the answer information of each of the target examinees; Using the first preset answer correction model and the second preset answer correction model to correct the answer information of each target test taker, respectively, to obtain the initial test results of each target test taker; Determine the target test result of each target test taker based on the initial test result and test cheating information of each target test taker; The target test result is sent to a client device.

2. The method according to claim 1, characterized in that The step of determining the cheating information of each target examinee based on the real-time video information of each target examinee includes: Determine the facial region information of each target examinee based on the real-time video information of each target examinee and using a face detection algorithm; Using a preset feature extraction algorithm to extract the action features of the target examinees in the real-time video information of each of the target examinees, so as to obtain the action feature information of each of the target examinees; The examination cheating information of each target examiner is determined based on the facial area information and action feature information of each target examiner.

3. The method according to claim 2, characterized in that The step of determining the cheating information of each target examinee based on the facial region information and action feature information of each target examinee comprises: Calculating the facial tilt angle based on the facial region information of each target examinee and using a preset facial key point detection algorithm to obtain the facial tilt angle of each target examinee; Comparing the facial tilt angle and action feature information of each target examinee with a preset facial tilt angle threshold and a preset action, respectively, to obtain a comparison result; In response to the comparison result that the facial inclination angle of the target examinee is greater than a preset facial inclination angle threshold and / or the action feature information of the target examinee is consistent with the preset action, generating cheating identification information in the test cheating information of the target examinee; In response to the comparison result that the facial inclination angle of the target examinee is less than or equal to the preset facial inclination angle threshold and the action feature information of the target examinee is inconsistent with the preset action, non-cheating identification information is generated in the test cheating information of the target examinee.

4. The method according to claim 1, characterized in that: The answer information of the target examinee includes subjective answer information; The first preset answer correction model and the second preset answer correction model are used to correct the answer information of each target test taker respectively to obtain the initial test result of each target test taker, including: Using a first preset answer correction model to extract the score points in the subjective answer information of each target test-taker, and compare them with the preset score points to obtain a score point comparison result; Using a second preset answer correction model to extract keywords from the subjective answer information of each target test-taker, and matching them with preset keywords to obtain keyword matching results; Determine first score information according to the score point comparison result; Determine second score information according to the keyword matching result; An initial test result of each of the target test takers is determined based on the first score information and the second score information.

5. The method according to claim 4, characterized in that The determining the initial test result of each of the target test takers based on the first score information and the second score information includes: averaging the first score information and the second score information of each of the target test takers to obtain averaged score information; The averaged score information corresponding to each of the target test takers is determined as the initial test result of each of the target test takers.

6. The method according to claim 1, characterized in that The step of determining the target test result of each target test taker based on the initial test result and the test cheating information of each target test taker comprises: If the cheating information contains the cheating identification information, subtract the initial test result of the corresponding target test taker from the preset value, and use the result as the target test result of the target test taker; If the cheating identification information is not included in the examination cheating information, the initial examination result of the corresponding target examinee is used as the target examination result of the target examinee.

7. The method according to claim 1, characterized in that In response to receiving the second pending task start instruction, before obtaining the answer information of each target test taker, the method includes: If in response to receiving a question correction request, obtaining identification information of a target question; the target question is the question in which an error occurs; the identification information of the target question is identification information that uniquely marks the target question; Creating a third to-do task based on the identification information of the target topic; the third to-do task is a correction task of the target topic; After the first preset answer correction model and the second preset answer correction model are used to correct the answer information of each target test taker to obtain the initial test result of each target test taker, the method further includes: In response to receiving the start instruction of the third to-do task, obtaining the score information of the target question corresponding to the target question in the initial test results of each of the target test takers based on the identification information of the target question, and uniformly modifying the score information of the target question to a preset fixed value, and recalculating the initial test results of each of the target test takers based on the modified score information of the target question, so as to obtain the modified initial test results of each of the target test takers; The initial test results of each of the target test takers are updated to the modified initial test results of each of the target test takers.

8. A data processing device, characterized in that: include: A receiving module, configured to receive a first to-do task start request sent by a client device; An acquisition module, configured to acquire real-time video information of at least one target examinee from a monitoring device according to the start request of the first to-be-done task; A determination module, used to determine the examination cheating information of each target examinee based on the real-time video information of each target examinee; The acquisition module is further used to acquire the answer information of each target test taker in response to receiving the second to-be-done task start instruction; A correction module, used to correct the answer information of each target test taker by using a first preset answer correction model and a second preset answer correction model, so as to obtain an initial test result of each target test taker; A determination module, which determines a target test result of each target test taker based on the initial test result and test cheating information of each target test taker; The sending module is used to send the target test result to the client device.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 7 when being executed by a processor.

Images