Video anti-brushing method, system, electronic device and medium for online learning

By collecting and analyzing video playback behavior data, combining deep learning algorithms to identify class brushing behavior and adopting anti-brushing strategies, the problem that existing technology cannot effectively prevent class brushing is solved, and the accurate identification and prevention of class brushing behavior is achieved to ensure that videos are ensured. Real viewing of the content.

CN117834995BActive Publication Date: 2024-11-08BEIJING WUYOU CHUANGXIANG INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410019065.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-05
Publication Date
2024-11-08
Estimated Expiration
2044-01-05

AI Technical Summary

Technical Problem

The existing technology cannot effectively monitor and resist lesson swiping behavior on online education and video sharing platforms in real time. Traditional methods such as IP address restrictions and verification code verification are not enough to prevent users from quickly skipping video content through abnormal means or manipulating fraudulent system records. The purpose of watching the video.

Method used

By collecting user's video playback behavior data, including video viewing duration, playback speed, mouse click track and progress bar clicking, combined with deep learning algorithms and neural network models, determine the lesson swiping score, and judge whether there is a swiping based on the score and threshold comparison. In class behavior, anti-cheating prompts, video playback speed limits or viewing time limits are adopted in real time.

Benefits of technology

It realizes accurate identification and prevention of class brushing behavior, improves the intelligence and effectiveness of video brushing prevention, and ensures that users can truly watch video content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117834995B_ABST
    Figure CN117834995B_ABST
Patent Text Reader

Abstract

The present invention discloses a video anti-brushing method for online learning, including collecting video playback behavior data of users; based on video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight and preset average viewing speed weight, determine the brushing score, the fast-forward times are determined by the video playback speed, the track position when the mouse clicks the screen and the video progress bar click situation, and the average viewing speed is determined by the video viewing time and the total video time; compare the brushing score with the brushing score threshold, and judge whether there is a brushing behavior based on the comparison result; when it is judged that there is a brushing behavior, the user is given an anti-cheating prompt, video playback speed limit or viewing time limit to prevent the brushing behavior. The present application can comprehensively, quickly and accurately judge whether the user has a brushing behavior, and effectively resist the brushing behavior.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of online education, and in particular relates to a video anti-brushing method, system, electronic device and medium for online learning. Background Art

[0002] In the current field of online education and video sharing platforms, cheating has become a serious problem. This behavior refers to users using abnormal means, such as quickly skipping video content, manually operating clicks, etc., to deceive the system record and achieve the purpose of watching videos. Traditional video anti-brushing methods, such as IP address restrictions, verification code verification, etc., have become ineffective. Traditional video anti-brushing methods cannot monitor user behavior in real time when watching videos, and cannot effectively resist cheating. Therefore, more intelligent and accurate solutions are needed to resist cheating. Summary of the invention

[0003] The purpose of the present invention is to provide a video anti-brushing method for online learning, so as to solve the problem of resisting the behavior of brushing.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] The present invention provides a video anti-brushing method for online learning, comprising:

[0006] Collecting the user's video playback behavior data, wherein the video playback behavior data at least includes the video viewing time, the video playback speed, the track position when the mouse clicks the screen, and the video progress bar click situation;

[0007] Determine the course review score based on the video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight and preset average viewing speed weight. The fast-forward times are determined by the video playback speed, the track position when the mouse clicks the screen and the video progress bar clicks. The average viewing speed is determined by the video viewing time and the total video time.

[0008] Compare the cheating score with the cheating score threshold, and determine whether cheating behavior exists based on the comparison result;

[0009] When cheating is detected, users will be given anti-cheating prompts, video playback speed restrictions or viewing time restrictions to prevent cheating.

[0010] In some embodiments, after collecting the user's video playback behavior data, the process further includes:

[0011] The video playback behavior data is cleaned and normalized to obtain a behavior data sample, wherein the data cleaning includes removing noise data, processing missing data, and processing abnormal data.

[0012] In some embodiments, after obtaining the behavior data sample, the method further includes:

[0013] Identify and classify behavioral data samples through deep learning algorithms and neural network models;

[0014] The identified and classified behavior data samples are trained through convolutional neural network and recurrent neural network models to obtain a high-precision and robust video anti-brushing model.

[0015] Analyze the viewing behavior of users when playing videos in real time according to the video anti-brushing model, and determine whether there is brushing behavior based on the playback behavior;

[0016] When cheating is detected, users will be given anti-cheating prompts, video playback speed restrictions, or viewing time restrictions to prevent cheating.

[0017] In some embodiments, the video anti-brushing model is used to analyze the viewing behavior of users during video playback in real time, and to determine whether there is any brushing behavior based on the playback behavior, including:

[0018] Based on the video anti-brushing model, streaming data processing and real-time analysis technology are used to detect in real time the video playback speed, video viewing time, mouse click trajectory and video progress bar click status when the user is learning online, so as to determine whether the user has brusqueezing behavior.

[0019] In some embodiments, based on the user's video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight, and preset average viewing speed weight, the course brushing score is determined according to the following formula:

[0020] Q= w1xduration + w2xfast_forward_count + w3x average_speed

[0021] Among them, Q is the course score, w1 is the preset viewing time weight, w2 is the preset fast-forward number weight, w3 is the preset average viewing speed weight, duration is the video viewing time, fast_forward_count is the fast-forward number, and average_speed is the average viewing speed.

[0022] In some embodiments, after collecting the user's video playback behavior data, the process further includes:

[0023] Perform video content relevance detection, user behavior pattern change detection, and user identity verification;

[0024] Determine whether there is cheating based on the video content relevance detection results, user behavior pattern change detection results, and user identity verification results;

[0025] Among them, the video content relevance detection is to analyze the correlation between the user's video viewing behavior and the video content, and detect whether there is frequent video switching behavior based on the correlation, and the user behavior pattern change detection is to monitor in real time whether the video clips are played in a loop.

[0026] In some embodiments, judging whether there is cheating behavior based on the video content relevance detection result, the user behavior pattern change detection result and the user identity verification result includes:

[0027] When users frequently switch videos, play video clips in a loop, or their identity information is abnormal, it is determined that they are cheating on the course.

[0028] Accordingly, the present application also proposes a video anti-brushing system for online learning, comprising:

[0029] A behavior data collection module is used to collect the user's video playback behavior data, wherein the video playback behavior data at least includes the video viewing time, the video playback speed, the track position when the mouse clicks the screen, and the video progress bar click situation;

[0030] A determination module is used to determine the course review score based on the user's video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight and preset average viewing speed weight. The fast-forward times are determined by the video playback speed, the track position when the mouse clicks the screen and the video progress bar click situation. The average viewing speed is determined by the video viewing time and the total video time.

[0031] A judgment module, used for comparing the cheating score with a cheating score threshold, and judging whether cheating behavior exists based on the comparison result;

[0032] The anti-cheating strategy module is used to provide users with anti-cheating prompts, video playback speed restrictions or viewing time restrictions when cheating behavior is detected to prevent cheating behavior.

[0033] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the method are implemented when the processor executes the computer program.

[0034] A non-transitory computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0035] Beneficial effects:

[0036] The present invention proposes a video anti-brushing system and method for solving the problem of video brushing on online education and video sharing platforms. The system is based on deep learning technology to analyze and identify user behavior data in real time to determine whether there is video brushing behavior. When video brushing behavior is identified, an anti-brushing strategy is adopted. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0038] Figure 1 A flowchart of a video anti-brushing method for online learning provided in an embodiment of the present application;

[0039] Figure 2 A flowchart of another video anti-brushing method for online learning provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of a video anti-brushing system for online learning provided in an embodiment of the present application;

[0041] Figure 4 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0043] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0044] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0045] Embodiment 1:

[0046] like Figure 1 The figure is a flow chart of a video anti-brushing method for online learning proposed by an embodiment of the present invention, including:

[0047] S201, collecting user's video playback behavior data.

[0048] Specifically, the video playback behavior data of the user is collected through the server, and the video playback behavior data at least includes the video viewing time, video playback speed, the track position when the mouse clicks the screen, and the video progress bar click situation. These data will be used to establish the user behavior model.

[0049] In order to more accurately and quickly determine whether a user has cheated in a class, in a preferred embodiment of this solution, after collecting the user's video playback behavior data, the following steps are also included:

[0050] The video playback behavior data is cleaned and normalized to obtain a behavior data sample, wherein the data cleaning includes removing noise data, processing missing data, and processing abnormal data.

[0051] Specifically, the video playback behavior data is cleaned and normalized to obtain high-quality behavior data samples (which can improve the accuracy and reliability of the model) for subsequent model training. The data cleaning includes removing noise data, processing missing data, and processing abnormal data.

[0052] In order to obtain a video anti-brushing model, in a preferred embodiment of the present solution, after obtaining the behavior data sample, the following steps are further included:

[0053] Identify and classify behavioral data samples through deep learning algorithms and neural network models;

[0054] The identified and classified behavior data samples are trained through convolutional neural network and recurrent neural network models to obtain a high-precision and robust video anti-brushing model.

[0055] Analyze the viewing behavior of users when playing videos in real time according to the video anti-brushing model, and determine whether there is brushing behavior based on the playback behavior;

[0056] When cheating is detected, users will be given anti-cheating prompts, video playback speed restrictions, or viewing time restrictions to prevent cheating.

[0057] Specifically, high-quality behavioral data samples are identified and classified through deep learning algorithms and neural network models, and the identified and classified behavioral data samples are trained through convolutional neural network and recurrent neural network models to obtain a high-precision and robust video anti-brushing model; based on the video anti-brushing model, the video playback speed, video viewing time, mouse click trajectory position and video progress bar click status of users in online learning are detected in real time through streaming data processing and real-time analysis technology to determine whether the user has cheated in the class. The cheating behavior determined by the video anti-brushing model is more accurate and faster. When cheating behavior is detected, the anti-brushing strategy is implemented, which includes anti-cheating prompts to users, video playback speed restrictions or viewing time restrictions to prevent cheating behavior.

[0058] The anti-brushing strategy is to use multiple anti-brushing strategies combined with the results of brushing behavior identification to restrict or prompt suspicious users, thereby effectively preventing brushing behavior. These strategies include but are not limited to: 1. Video playback speed limit: limit the video playback speed to prevent users from swiping through videos quickly. 2. Viewing time limit: set a minimum viewing time requirement to ensure that users actually watch the video. 3. Anti-cheating prompts: when users trigger suspicious behavior, provide anti-cheating prompts to guide users to standardize behavior.

[0059] In addition to limiting the playback speed and setting a viewing time limit, other anti-spam strategies are also set. In the preferred embodiment of this solution, after collecting the user's video playback behavior data, it also includes:

[0060] Perform video content relevance detection, user behavior pattern change detection, and user identity verification;

[0061] Determine whether there is cheating based on the video content relevance detection results, user behavior pattern change detection results, and user identity verification results;

[0062] Among them, the video content relevance detection is to analyze the relevance between the user's video viewing behavior and the video content, and detect whether there is frequent video switching based on the relevance, and the user behavior pattern change detection is to monitor in real time whether the video clips are played in a loop.

[0063] Specifically, based on the identification results of cheating behavior, a variety of anti-cheating strategies are adopted to effectively prevent cheating behavior. In addition to limiting the playback speed and setting a viewing time limit, the following strategies are also included:

[0064] 1. Perform video content relevance detection: By analyzing the relevance between user viewing behavior and video content, detect whether there is frequent video switching. If the user frequently switches videos, it is judged that there is cheating behavior.

[0065] 2. User behavior pattern change detection: Monitor changes in user viewing behavior patterns, such as quickly skipping video content, repeatedly playing a certain clip, etc., to identify abnormal behavior. When a user plays a video clip in a loop, abnormal behavior is identified, and it is determined that there is cheating behavior.

[0066] 3. User identity verification: Combine user account information and other authentication mechanisms to ensure the authenticity of viewing behavior and prevent cheating.

[0067] Once the system detects cheating, it will immediately take corresponding restrictive measures against the user to protect the interests of the platform. For example, pausing video playback, popping up verification codes, reminding users to regulate their viewing behavior, etc., to effectively curb the occurrence of cheating.

[0068] S202, determine the course review score based on the video viewing time, the number of fast-forward times, the average viewing speed, the preset viewing time weight, the preset fast-forward times weight and the preset average viewing speed weight, wherein the fast-forward times are determined by the video playback speed, the trajectory position when the mouse clicks the screen and the video progress bar clicks, and the average viewing speed is determined by the video viewing time and the total video time.

[0069] In order to accurately obtain the score for cheating, in a preferred embodiment of this solution, based on the user's video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight and preset average viewing speed weight, the score for cheating is determined according to the following formula:

[0070] Q= w1xduration + w2xfast_forward_count + w3xaverage_speed

[0071] Among them, Q is the score of the course, w1 is the preset viewing time weight, w2 is the preset fast-forward number weight, w3 is the preset average viewing speed weight, duration is the video viewing time, fast_forward_count is the fast-forward number, and average_speed is the average viewing speed. By weighted summing these indicators, a course score can be obtained.

[0072] S203, comparing the course cheating score with a course cheating score threshold, and determining whether there is course cheating behavior based on the comparison result.

[0073] Specifically, a cheating score is obtained according to the formula. When the cheating score exceeds the cheating score threshold, the system determines that the user has cheated in the course and takes corresponding anti-cheating measures.

[0074] S204, when it is determined that cheating occurs, anti-cheating prompts, video playback speed restrictions or viewing time restrictions are provided to the user to prevent cheating.

[0075] Example 2

[0076] like Figure 2 The figure shows another method for preventing video cheating in online learning. The user behavior model is established by collecting the user's video playback behavior data. The video playback behavior data at least includes the video viewing time, video playback speed, mouse click trajectory position and video progress bar click situation. Based on the user behavior model, it can be determined whether the user has cheated in the class:

[0077] Step 1: Determine whether there is cheating behavior:

[0078] Course score = w1x duration + w2xfast_forward_count + w3x average_speed

[0079] Among them, w1, w2 and w3 respectively represent the weight of viewing time, the weight of fast-forward times and the weight of average viewing speed, which are coefficients used to adjust the importance of each indicator in the calculation. Duration represents the total time the user watches the video, in seconds. Fast_forward_count represents the number of times the user fast-forwards during the viewing process, which can be used as one of the indicators of cheating. Each fast forward may mean that the user skipped a section of video content. Average_speed represents the average speed at which the user watches the video, which is calculated by dividing the video viewing time by the video length. A faster viewing speed may suggest that the user quickly browses the video content. By weighted summing these indicators, a cheating score can be obtained. When the cheating score exceeds a certain threshold, the system can determine that the user has cheated in class and take corresponding anti-cheating measures. The present application can determine whether there is cheating in class through step 1, and the cheating behavior determined by step 2 is more accurate and faster.

[0080] Step 2: Identification of swiping behavior: Use deep learning algorithms and neural network models to identify and classify user video playback behavior data. By using models such as convolutional neural networks (CNN) and recurrent neural networks (RNN), we can automatically learn and identify swiping behaviors through training sample data. For example, abnormally fast video playback speeds and short viewing times may be identified as swiping behaviors.

[0081] Step 3: Implementation of anti-brushing strategies: Based on the results of the identification of brushing behaviors, various anti-brushing strategies are adopted to effectively prevent brushing behaviors. In addition to limiting the playback speed and setting a viewing time limit, the following strategies are also included:

[0082] 1. Perform video content relevance detection: By analyzing the relevance between user viewing behavior and video content, detect whether there is frequent video switching. If the user frequently switches videos, it is judged that there is cheating behavior.

[0083] 2. User behavior pattern change detection: Monitor changes in user viewing behavior patterns, such as quickly skipping video content, repeatedly playing a certain clip, etc., to identify abnormal behavior. When a user plays a video clip in a loop, abnormal behavior is identified, and it is determined that there is cheating behavior.

[0084] 3. User identity verification: Combine user account information and other authentication mechanisms to ensure the authenticity of viewing behavior and prevent cheating.

[0085] Once the system detects cheating, it will immediately take corresponding restrictive measures against the user to protect the interests of the platform. For example, pausing video playback, popping up verification codes, reminding users to regulate their viewing behavior, etc., to effectively curb the occurrence of cheating.

[0086] Figure 3 A schematic diagram of a video anti-brushing system for online learning provided by the present invention includes:

[0087] The behavior data collection module 10 is used to collect the user's video playback behavior data, and the video playback behavior data at least includes the video viewing time, the video playback speed, the track position when the mouse clicks the screen, and the video progress bar click situation;

[0088] Determination module 20, for determining the course brushing score based on the user's video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight and preset average viewing speed weight, the fast-forward times are determined by the video playback speed, the track position when the mouse clicks the screen and the video progress bar click situation, and the average viewing speed is determined by the video viewing time and the total video time;

[0089] A judgment module 30 is used to compare the cheating score with a cheating score threshold, and judge whether there is cheating behavior based on the comparison result;

[0090] The anti-cheating strategy module 40 is used to provide anti-cheating prompts, video playback speed restrictions or viewing time restrictions to users when it is determined that cheating behavior exists, so as to prevent cheating behavior.

[0091] Figure 4 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 4 As shown, the electronic device 60 includes: a processor 601 (processor), a memory 602 (memory) and a bus 603;

[0092] The processor 601 and the memory 602 communicate with each other via the bus 603;

[0093] The processor 601 is used to call the program instructions in the memory 602 to execute the methods provided by the above-mentioned method embodiments. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative labor.

[0094] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0096] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A video anti-brushing method for online learning, characterized in that: include: Collecting the user's video playback behavior data, wherein the video playback behavior data at least includes the video viewing time, the video playback speed, the track position when the mouse clicks the screen, and the video progress bar click situation; Determine the course review score based on the video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight and preset average viewing speed weight. The fast-forward times are determined by the video playback speed, the track position when the mouse clicks the screen and the video progress bar clicks. The average viewing speed is determined by the video viewing time and the total video time. Compare the cheating score with the cheating score threshold, and determine whether cheating behavior exists based on the comparison result; When cheating is detected, users will be given anti-cheating tips, video playback speed restrictions, or viewing time restrictions to prevent cheating; The course score is determined based on the user's video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight and preset average viewing speed weight, and is determined according to the following formula: Q= w1xduration + w2xfast_forward_count + w3xaverage_speed Among them, Q is the course score, w1 is the preset viewing time weight, w2 is the preset fast-forward number weight, w3 is the preset average viewing speed weight, duration is the video viewing time, fast_forward_count is the fast-forward number, and average_speed is the average viewing speed.

2. The method according to claim 1, characterized in that: After collecting the user's video playback behavior data, it also includes: The video playback behavior data is cleaned and normalized to obtain a behavior data sample, wherein the data cleaning includes removing noise data, processing missing data, and processing abnormal data.

3. The method according to claim 2, characterized in that After obtaining the behavioral data sample, it also includes: Identify and classify behavioral data samples through deep learning algorithms and neural network models; The identified and classified behavior data samples are trained through convolutional neural network and recurrent neural network models to obtain a high-precision and robust video anti-brushing model. Analyze the user's video playback behavior data in real time according to the video anti-brushing model, and determine whether there is brushing behavior based on the video playback behavior data; When cheating is detected, users will be given anti-cheating prompts, video playback speed restrictions, or viewing time restrictions to prevent cheating.

4. The method according to claim 3, characterized in that Analyze the user's video playback behavior data in real time according to the video anti-brushing model, and determine whether there is a brushing behavior according to the video playback behavior data, including: Based on the video anti-brushing model, streaming data processing and real-time analysis technology are used to detect in real time the video playback speed, video viewing time, mouse click trajectory and video progress bar click status of users during online learning, so as to determine whether the user has brusqueezing behavior.

5. The method according to claim 1, characterized in that After collecting the user's video playback behavior data, it also includes: Perform video content relevance detection, user behavior pattern change detection, and user identity verification; Determine whether there is cheating based on the video content relevance detection results, user behavior pattern change detection results, and user identity verification results; Among them, the video content relevance detection is to analyze the relevance between the user's video playback behavior and the video content, and detect whether there is frequent video switching behavior based on the relevance, and the user behavior pattern change detection is to monitor in real time whether the video clips are played in a loop.

6. The method according to claim 5, characterized in that Based on the video content relevance detection results, user behavior pattern change detection results and user identity verification results, determine whether there is cheating behavior, including: When a user frequently switches videos, plays video clips in a loop, or the user's identity information is abnormal, it is judged that cheating has occurred.

7. A video anti-brushing system for online learning, characterized in that: include: A behavior data collection module is used to collect the user's video playback behavior data, wherein the video playback behavior data at least includes the video viewing time, the video playback speed, the track position when the mouse clicks the screen, and the video progress bar click situation; The determination module is used to determine the course score based on the user's video viewing time, fast-forward times, average viewing speed, preset viewing time weight, preset fast-forward times weight and preset average viewing speed weight, which is determined according to the following formula: Q= w1xduration + w2xfast_forward_count + w3xaverage_speed Among them, Q is the score of the course, w1 is the preset viewing time weight, w2 is the preset fast-forward number weight, w3 is the preset average viewing speed weight, duration is the video viewing time, fast_forward_count is the fast-forward number, and average_speed is the average viewing speed; The number of fast forwards is determined by the video playback speed, the track position when the mouse clicks the screen, and the video progress bar click situation, and the average viewing speed is determined by the video viewing time and the total video time; A judgment module, used for comparing the cheating score with a cheating score threshold, and judging whether cheating behavior exists based on the comparison result; The anti-cheating strategy module is used to provide users with anti-cheating prompts, video playback speed restrictions or viewing time restrictions when cheating behavior is detected to prevent cheating behavior.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.