Proposition person detection and verification method and system for online examination

By obtaining and analyzing the operation behavior data of the question-propositioner, using adaptive sliding window algorithm and dynamic adaptive threshold technology, combined with machine learning model, the problem of inability to monitor and identify abnormal operations in the existing technology in real time is solved, and the identity of the question-propositioner is realized The accurate verification improves the security and accuracy of the system.

CN119004429AInactive Publication Date: 2024-11-22ATA ONLINE (BEIJING) EDUCATION TECH LTD

Patent Information

Application Number
CN202411499142.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-25
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing technology cannot realize real-time monitoring of the operation behavior of the question setter in the computer exam, resulting in the inability to timely discover and prevent unauthorized operations. There is a lack of effective algorithm models to distinguish between normal operations and abnormal operations, which is prone to false alarms and missed reports, which affects System accuracy and reliability.

Method used

By obtaining the operation behavior data of the questioner in the system, using the adaptive sliding window algorithm to calculate the operation frequency and rhythm, calculate the entropy value, and combining the difference between the entropy value and the standard entropy value, the identity of the questioner is judged through dynamic adaptive threshold technology Validity: build a machine learning model for abnormal scores, and judge the validity of the identity of the propositioner.

Benefits of technology

Real-time verification of the identity of the question-setting person is realized, the false positive rate is reduced, the security and user experience of the system are improved, and the security and fairness of the examination content is ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119004429A_ABST
    Figure CN119004429A_ABST
Patent Text Reader

Abstract

The invention provides a proposition person detection and verification method and system for a computer examination, and the method comprises the steps: obtaining the operation behavior data of a proposition person in a computer examination system, the operation behavior data including keyboard input, mouse movement and click event timestamps, and the duration and interval time of each operation behavior data; according to the time interval distribution in the operation behavior data, calculating the operation frequency and the operation rhythm of the proposition in a set time period by using a self-adaptive sliding window algorithm; based on the operation frequency and the operation rhythm, determining an entropy value of the operation behavior data of the proposition person; according to the method, the validity of the proposition person identity is judged by utilizing the difference between the entropy value and the standard entropy value, combining the operation frequency and the operation rhythm and through a dynamic self-adaptive threshold technology, so that the proposition person identity is accurately verified, the false alarm rate is reduced, and the overall safety of the system and the user experience are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of computer-based examinations, and in particular to a method and system for detecting and verifying question setters for computer-based examinations. Background Art

[0002] With the rapid development of online education, computer-based exams have been widely used in various exam scenarios due to their efficiency and convenience. However, with the popularity of online and remote exams, how to ensure the fairness of the exam process has become an important issue. Especially for the question setter, the verification of their identity is particularly important to prevent unauthorized personnel from compiling or modifying the test questions. The following is an introduction to the technical background of the detection and verification of the question setter for computer-based exams: Computer-based exams are widely used in various standardized tests, such as professional qualification certification, academic education exams, language proficiency tests, etc. In particular, in these exams, the question setter needs to log in to the system to compile, review and modify the questions to ensure the quality and confidentiality of the questions.

[0003] With the increase in remote collaboration, test organizers urgently need a set of effective technical means to verify the identity of the question setter to prevent unauthorized personnel from manipulating the test questions. The technical means need to be able to monitor the operation behavior of the question setter in real time and accurately identify unauthorized operations to ensure the security and fairness of the test content.

[0004] Currently, many examination platforms use traditional user authentication methods such as username and password and two-factor authentication to verify the identity of the test setter. These methods mainly rely on static credentials for identity authentication, but have limitations in terms of security.

[0005] Some systems have begun to attempt to monitor behavior by recording the operation logs of the test setters in the system, but most of these methods rely on post-analysis and cannot achieve real-time detection and early warning.

[0006] Existing user authentication methods mainly rely on static credentials, which cannot monitor the operation behavior of the question setter in real time. Once the credentials are stolen, it is impossible to detect and prevent unauthorized operations in time.

[0007] Most existing behavior monitoring methods rely on post-analysis and cannot evaluate whether the behavior of the question setter is abnormal in real time during the operation. In addition, there is a lack of effective algorithm models to distinguish normal operations from potential abnormal operations, and it is impossible to build a behavior baseline model based on behavioral characteristics.

[0008] False positive and false negative issues: Due to the lack of refined behavioral feature extraction and analysis mechanisms, existing solutions are prone to false positives (mistaking normal operations for abnormalities) or false negatives (failure to identify truly abnormal behaviors), which not only affects the accuracy and reliability of the system, but may also lead to improper interference with the test setter's operations.

[0009] In summary, the existing technical solutions have obvious deficiencies in terms of real-time performance, intelligence level, and false alarms and missed alarms. Summary of the invention

[0010] The embodiments of the present application provide a method and system for detecting and verifying the question setter of a computer-based test, so as to solve the problems existing in the above-mentioned background technology.

[0011] In a first aspect, an embodiment of the present application provides a method for detecting and verifying a question setter for a computer-based examination, comprising: obtaining the operational behavior data of the question setter in a computer-based examination system, wherein the operational behavior data includes: event timestamps of keyboard input, mouse movement and click, and the duration and interval time of each operational behavior data; calculating the operational frequency and operational rhythm of the question setter within a set time period using an adaptive sliding window algorithm based on the time interval distribution in the operational behavior data; determining the entropy value of the operational behavior data of the question setter based on the operational frequency and the operational rhythm; utilizing the difference between the entropy value and the standard entropy value, combined with the operational frequency and the operational rhythm, to judge the validity of the identity of the question setter through dynamic adaptive threshold technology.

[0012] Furthermore, the difference between the entropy value and the standard entropy value is utilized, combined with the operation frequency and the operation rhythm, to judge the validity of the identity of the question setter through dynamic adaptive threshold technology, including: calculating the probability of occurrence of each operation behavior data, and based on the occurrence probability, calculating the entropy value corresponding to the operation behavior data; calculating the difference between the entropy value and the standard entropy value; judging the validity of the identity of the question setter based on the difference, the operation frequency, the operation rhythm and the dynamic adaptive threshold technology.

[0013] Further, judging the validity of the identity of the question setter based on the difference, the operation frequency, the operation rhythm and the dynamic adaptive threshold technology includes: defining an adaptive threshold function of the operation frequency, wherein the adaptive threshold function of the operation frequency is , is the mean value of the operating frequency, is the standard deviation of the operating frequency, is the operating frequency in the sliding window The time variation factor of is a constant, is the adaptive coefficient, For sliding window The adaptive threshold value of the operating frequency is defined as follows: an adaptive threshold function of the operating rhythm is defined, wherein the adaptive threshold function of the operating rhythm is: , is the mean of the operation rhythm, is the standard deviation of the operating frequency, For the operation rhythm in the sliding window The time variation factor of is a constant, is the adaptive coefficient, For sliding window The adaptive threshold of the operation rhythm is adopted; the operation frequency, the adaptive threshold function value of the operation frequency, the operation rhythm, the adaptive threshold function of the operation rhythm and the difference are substituted into the comprehensive deviation calculation formula to determine the comprehensive deviation value; if the comprehensive deviation value is greater than the preset threshold, it is determined that the identity of the question setter is invalid.

[0014] Furthermore, the comprehensive deviation calculation formula is: ; in, is the comprehensive deviation value, is the difference between the entropy value and the standard entropy value, is the operating frequency, For the said operation rhythm, is the mean of the operation rhythm, , and is the weight value.

[0015] Furthermore, based on the time interval distribution in the operation behavior data, an adaptive sliding window algorithm is used to calculate the operation frequency and operation rhythm of the question setter within a set time period, including: defining the time length of the sliding window, calculating the ratio between the operation behavior data in the sliding window and the time length, and obtaining the initial operation frequency; calculating the initial operation rhythm based on the initial operation frequencies of adjacent sliding windows; and smoothing the initial operation frequency and the initial operation rhythm using a preset window overlap ratio to obtain the operation frequency and the operation rhythm.

[0016] Furthermore, the expression of the operating frequency is: ,in, For sliding window The initial operating frequency, For sliding window The initial operating frequency, is the preset window overlap ratio; the expression of the operation rhythm is: ,in, For sliding window The initial operation rhythm, For sliding window The initial operation rhythm.

[0017] Furthermore, the difference between the entropy value and the standard entropy value is utilized, combined with the operation frequency and the operation rhythm, to judge the validity of the identity of the question setter through dynamic adaptive threshold technology, including: constructing a machine learning model, wherein the machine learning model is a model trained using historical operation behavior data; the difference between the entropy value and the standard entropy value, the operation frequency and the operation rhythm are input into the machine learning model to obtain an abnormality score; based on the abnormality score and the adaptive threshold of the abnormality score, the validity of the identity of the question setter is judged.

[0018] In the second aspect, an embodiment of the present application provides a system for detecting and verifying the question setter of a computer-based examination, comprising: an acquisition unit, used to acquire the operational behavior data of the question setter in the computer-based examination system, wherein the operational behavior data includes: event timestamps of keyboard input, mouse movement and click, and the duration and interval time of each operational behavior data; a calculation unit, used to calculate the operational frequency and operational rhythm of the question setter within a set time period according to the time interval distribution in the operational behavior data, using an adaptive sliding window algorithm; a determination unit, used to determine the entropy value of the operational behavior data of the question setter based on the operational frequency and the operational rhythm; a judgment unit, used to utilize the difference between the entropy value and the standard entropy value, combined with the operational frequency and the operational rhythm, to judge the validity of the identity of the question setter through dynamic adaptive threshold technology.

[0019] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method described in the first aspect above.

[0020] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements the method described in the first aspect above.

[0021] In an embodiment of the present invention, the operation behavior data of the examiner in the computer-based examination system is obtained, wherein the operation behavior data includes: event timestamps of keyboard input, mouse movement and click, and the duration and interval time of each operation behavior data; according to the time interval distribution in the operation behavior data, an adaptive sliding window algorithm is used to calculate the operation frequency and operation rhythm of the examiner within a set time period; based on the operation frequency and operation rhythm, the entropy value of the examiner's operation behavior data is determined; the difference between the entropy value and the standard entropy value is utilized, combined with the operation frequency and operation rhythm, and the validity of the examiner's identity is judged through dynamic adaptive threshold technology, so as to accurately verify the examiner's identity, while reducing the false alarm rate and improving the overall security and user experience of the system.

[0022] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 A flowchart of a method for detecting and verifying a test setter for a computer-based test provided in an embodiment of the present application; Figure 2 A schematic diagram of a system for detecting and verifying a test setter for a computer-based test provided in an embodiment of the present application; Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Embodiment 1: According to an embodiment of the present invention, an embodiment of a method for detecting and verifying the question setter of a computer-based examination is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] Figure 1 is a flow chart of a method for detecting and verifying a test setter for a computer-based test according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps: Step S102, obtaining the operation behavior data of the test setter in the computer-based test system, wherein the operation behavior data includes: event timestamps of keyboard input, mouse movement and click, and the duration and interval time of each operation behavior data; Step S104, calculating the operation frequency and operation rhythm of the question setter within a set time period using an adaptive sliding window algorithm according to the time interval distribution in the operation behavior data; Step S106, determining the entropy value of the operation behavior data of the question setter based on the operation frequency and the operation rhythm; Step S108, utilizing the difference between the entropy value and the standard entropy value, combined with the operation frequency and the operation rhythm, to determine the validity of the identity of the question setter through dynamic adaptive threshold technology.

[0028] In the embodiment of the present invention, the system needs to collect the operation behavior data of the examiner in the computer-based examination system, which includes the event timestamps of keyboard input, mouse movement and click, as well as the duration and interval of each operation behavior data. This information can provide detailed operation details of the examiner in the system, which is helpful for subsequent analysis and verification.

[0029] For example, the operation behavior data of the test setter in the computer-based test system is as follows: Keyboard input: records the timestamp of each keystroke and its duration; Mouse movement: record the starting position, ending position, timestamp and duration of mouse movement; Mouse Clicks: Records the timestamp of each click and its duration.

[0030] For example, suppose that in a certain operation, the timestamps of keyboard input are [10:00:01, 10:00:03,10:00:06, ...], and the durations are [0.2s, 0.3s, 0.4s, ...] respectively; the timestamps of mouse movement are [10:00:05, 10:00:10, 10:00:15, ...], and the durations are [0.5s, 0.6s, 0.7s, ...] respectively; the timestamps of mouse clicks are [10:00:08, 10:00:13, 10:00:18, ...], and the durations are [0.1s, 0.2s,0.3s, ...] respectively.

[0031] Next, we need to use an adaptive sliding window algorithm to calculate the operator's operation frequency and operation rhythm within a set time period based on the time interval distribution in the operation behavior data. The adaptive sliding window algorithm can dynamically adjust the window size based on the actual operation behavior to better capture the operator's operation pattern.

[0032] Then, it is necessary to determine the entropy value of the operator's operation behavior data based on the operation frequency and operation rhythm. The entropy value is used to quantify the randomness and regularity of the operation behavior. The lower the entropy value, the more regular the operator's operation pattern is.

[0033] Finally, it is necessary to use the difference between the entropy value and the standard entropy value, combined with the operation frequency and operation rhythm, to judge the validity of the identity of the question setter through dynamic adaptive threshold technology. Dynamic adaptive threshold technology can dynamically adjust the judgment standard based on historical data to adapt to individual differences of question setters and changes in the operating environment.

[0034] Through the above steps, the system can evaluate in real time whether the operating behavior of the question setter deviates from the normal range, and improve the accuracy and reliability of identity authentication through dynamic adaptive threshold technology.

[0035] In the embodiment of the present invention, according to the time interval distribution in the operation behavior data, an adaptive sliding window algorithm is used to calculate the operation frequency and operation rhythm of the question setter within a set time period, including: Define the time length of the sliding window, calculate the ratio between the operation behavior data in the sliding window and the time length, and obtain the initial operation frequency; Based on the initial operation frequencies of adjacent sliding windows, an initial operation rhythm is calculated; The initial operation frequency and the initial operation rhythm are smoothed by using a preset window overlap ratio to obtain the operation frequency and the operation rhythm.

[0036] Wherein, the expression of the operating frequency is: ,in, For sliding window The initial operating frequency, For sliding window The initial operating frequency, is the preset window overlap ratio; The expression of the operation rhythm is: ,in, For sliding window The initial operation rhythm, For sliding window The initial operation rhythm.

[0037] In the embodiment of the present invention, an adaptive sliding window algorithm is used to calculate the operation frequency and operation rhythm of the question setter within a set time period. The time length of the sliding window is set to 5 seconds, and the ratio between the operation behavior data in the sliding window and the time length is calculated to obtain the initial operation frequency.

[0038] For example, suppose that within a 5-second sliding window, the question setter performs 10 keyboard input operations. The initial operation frequency is .

[0039] Next, the difference in the initial operating frequencies of adjacent sliding windows is calculated , then the initial operation rhythm .

[0040] If the operation frequency of the next 5-second sliding window If the initial operation rhythm is 3 times / second, .

[0041] Using preset window overlap ratios (e.g. 0.2), smooth the initial operation frequency and initial operation rhythm to obtain the smoothed operation frequency 2.2 times / second, 0.5 times / second.

[0042] In the embodiment of the present invention, the difference between the entropy value and the standard entropy value is used, combined with the operation frequency and the operation rhythm, to determine the validity of the identity of the question setter through a dynamic adaptive threshold technology, including: Calculating the occurrence probability of each operation behavior data, and based on the occurrence probability, calculating the entropy value corresponding to the operation behavior data; Calculating the difference between the entropy value and a standard entropy value; The validity of the identity of the question setter is judged based on the difference, the operation frequency, the operation rhythm and the dynamic adaptive threshold technology.

[0043] Specifically, judging the validity of the identity of the question setter based on the difference, the operation frequency, the operation rhythm and the dynamic adaptive threshold technology includes: Define an adaptive threshold function of the operating frequency, wherein the adaptive threshold function of the operating frequency is , is the mean value of the operating frequency, is the standard deviation of the operating frequency, is the operating frequency in the sliding window The time variation factor of is a constant, is the adaptive coefficient, For sliding window An adaptive threshold value of the operating frequency; Define the adaptive threshold function of the operation rhythm, wherein the adaptive threshold function of the operation rhythm is , is the mean of the operation rhythm, is the standard deviation of the operating frequency, For the operation rhythm in the sliding window The time variation factor of is a constant, is the adaptive coefficient, For sliding window Adaptive threshold of operation rhythm; Substituting the operating frequency, the adaptive threshold function value of the operating frequency, the operating rhythm, the adaptive threshold function of the operating rhythm and the difference into a comprehensive deviation calculation formula to determine a comprehensive deviation value; If the comprehensive deviation value is greater than a preset threshold, it is determined that the identity of the question setter is invalid.

[0044] The comprehensive deviation calculation formula is: ; in, is the comprehensive deviation value, is the difference between the entropy value and the standard entropy value, is the operating frequency, For the said operation rhythm, is the mean of the operation rhythm, , and is the weight value.

[0045] In the embodiment of the present invention, the probability of occurrence of each operation behavior data in the operation sequence of the question setter is calculated. , then the entropy value is .

[0046] Substitute the above calculated value into the comprehensive deviation calculation formula to obtain the comprehensive deviation value. When the comprehensive deviation value is greater than the preset threshold, it is determined that the identity of the question setter is invalid.

[0047] In the embodiment of the present invention, the difference between the entropy value and the standard entropy value is used, combined with the operation frequency and the operation rhythm, to determine the validity of the identity of the question setter through a dynamic adaptive threshold technology, including: Constructing a machine learning model, wherein the machine learning model is a model trained using historical operation behavior data; Inputting the difference between the entropy value and the standard entropy value, the operation frequency, and the operation rhythm into the machine learning model to obtain an abnormality score; Based on the anomaly score and an adaptive threshold of the anomaly score, the validity of the identity of the question setter is determined.

[0048] In an embodiment of the present invention, a machine learning model is constructed to evaluate the abnormality of the operation behavior of the question setter. The machine learning model is trained using historical operation behavior data to identify the difference between normal operation behavior and potential abnormal operation behavior. The specific steps include constructing a machine learning model, inputting entropy value difference, operation frequency and operation rhythm into the model to obtain an abnormality score, and judging the validity of the identity of the question setter based on the abnormality score and adaptive threshold.

[0049] Specifically, historical operation behavior data is collected, including normal operation behavior data and abnormal operation behavior data. Assume that 1000 pieces of normal operation behavior data and 200 pieces of abnormal operation behavior data are collected.

[0050] Features are extracted from historical data, including the difference between the entropy value and the standard entropy value, the operation frequency, and the operation rhythm. For example, for normal operation behavior, the entropy value difference may range from 0.01 to 0.1, the operation frequency may range from 2 times / second to 3 times / second, and the operation rhythm may range from 0.3 times / second to 0.5 times / second.

[0051] Choose a suitable machine learning model for training, such as Support Vector Machine (SVM), Random Forest (RF) or Neural Network (NN).

[0052] The above features are used to train the machine learning model so that it can distinguish between normal and abnormal operation behaviors. Assuming that the support vector machine model is selected for training, the model can identify which operation behaviors are normal and which are abnormal.

[0053] The entropy value difference, operation frequency and operation rhythm of the current question setter are used as input features and input into the trained machine learning model.

[0054] Anomaly score: The output of a machine learning model that quantifies the degree of abnormality of an operational behavior.

[0055] Assume that the entropy value difference of the current question setter is 0.05, the operation frequency is 2.5 times / second, and the operation rhythm is 0.4 times / second.

[0056] These features are input into the trained support vector machine model to obtain an anomaly score of 0.7 (assuming the score ranges from 0 to 1, a higher score indicates a higher degree of anomaly).

[0057] If the adaptive threshold of the abnormal score obtained by historical data analysis is 0.6.

[0058] Because the current question setter's abnormality score is 0.7, which exceeds the adaptive threshold of 0.6, the question setter's identity is judged to be invalid.

[0059] If the anomaly score of the current question setter is 0.5, which is lower than the adaptive threshold of 0.6, the identity of the question setter is judged to be valid.

[0060] Through the above steps, the system can more accurately evaluate whether the questioner's operating behavior is abnormal through machine learning models, and improve the accuracy and reliability of identity authentication through dynamic adaptive threshold technology.

[0061] Embodiment 2: An embodiment of the present invention also provides a system for detecting and verifying the question setter of a computer-based examination. The system for detecting and verifying the question setter of a computer-based examination is used to execute the method for detecting and verifying the question setter of a computer-based examination provided in the above content of the embodiment of the present invention. The following is a specific introduction to the system for detecting and verifying the question setter of a computer-based examination provided in the embodiment of the present invention.

[0062] like Figure 2 As shown, Figure 2 The schematic diagram of the above-mentioned computer test question setter detection and verification system is as follows: The acquisition unit 10 is used to acquire the operation behavior data of the test setter in the computer-based test system, wherein the operation behavior data includes: event timestamps of keyboard input, mouse movement and click, and the duration and interval time of each operation behavior data; A calculation unit 20, for calculating the operation frequency and operation rhythm of the question setter within a set time period using an adaptive sliding window algorithm according to the time interval distribution in the operation behavior data; A determination unit 30, configured to determine an entropy value of the operation behavior data of the question setter based on the operation frequency and the operation rhythm; The judgment unit is used to utilize the difference between the entropy value and the standard entropy value, combined with the operation frequency and the operation rhythm, to judge the validity of the identity of the question setter through dynamic adaptive threshold technology.

[0063] Embodiment three: The embodiment of the present invention further provides a computing device for executing a program of the method described in the first embodiment, such as Figure 3 As shown, the computing device may include a storage component 41 and a processing component 42; The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 42 .

[0064] The processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps in the method of embodiment 1. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0065] The storage component 41 is configured to store various types of data to support operations at the terminal. The storage component 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.

[0066] The display component 43 may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.

[0067] Of course, a computing device may also include other components, such as input / output interfaces, communication components, etc.

[0068] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0069] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0070] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0071] Embodiment 4: The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The method of the illustrated embodiment.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0073] The device embodiments described above are merely illustrative, 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. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0074] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including 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 described in each embodiment or some parts of the embodiments.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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 application.

Claims

1. A method for detecting and verifying a test setter for a computer-based test, characterized in that: include: Acquire the operation behavior data of the test setter in the computer-based test system, wherein the operation behavior data includes: event timestamps of keyboard input, mouse movement and click, and the duration and interval time of each operation behavior data; According to the time interval distribution in the operation behavior data, an adaptive sliding window algorithm is used to calculate the operation frequency and operation rhythm of the question setter within a set time period; Based on the operation frequency and the operation rhythm, determining the entropy value of the operation behavior data of the question setter; The difference between the entropy value and the standard entropy value is utilized, combined with the operation frequency and the operation rhythm, to judge the validity of the identity of the question setter through dynamic adaptive threshold technology.

2. The method according to claim 1, characterized in that: The difference between the entropy value and the standard entropy value is used, combined with the operation frequency and the operation rhythm, to determine the validity of the identity of the question setter through a dynamic adaptive threshold technology, including: Calculating the occurrence probability of each operation behavior data, and based on the occurrence probability, calculating the entropy value corresponding to the operation behavior data; Calculating the difference between the entropy value and a standard entropy value; The validity of the identity of the question setter is judged based on the difference, the operation frequency, the operation rhythm and the dynamic adaptive threshold technology.

3. The method according to claim 2, characterized in that Judging the validity of the identity of the question setter based on the difference, the operation frequency, the operation rhythm and the dynamic adaptive threshold technology includes: Define an adaptive threshold function of the operating frequency, wherein the adaptive threshold function of the operating frequency is , is the mean value of the operating frequency, is the standard deviation of the operating frequency, The operating frequency in the sliding window The time variation factor, is a constant, is the adaptive coefficient, For sliding window An adaptive threshold value of the operating frequency; Define the adaptive threshold function of the operation rhythm, wherein the adaptive threshold function of the operation rhythm is , is the mean of the operation rhythm, is the standard deviation of the operating frequency, For the operation rhythm in the sliding window The time variation factor, is a constant, is the adaptive coefficient, For sliding window Adaptive threshold of operation rhythm; Substituting the operating frequency, the adaptive threshold function value of the operating frequency, the operating rhythm, the adaptive threshold function of the operating rhythm and the difference into a comprehensive deviation calculation formula to determine a comprehensive deviation value; If the comprehensive deviation value is greater than a preset threshold, it is determined that the identity of the question setter is invalid.

4. The method according to claim 3, characterized in that The comprehensive deviation calculation formula is: ; in, is the comprehensive deviation value, is the difference between the entropy value and the standard entropy value, is the operating frequency, For the operation rhythm, is the mean of the operation rhythm, , and is the weight value.

5. The method according to claim 1, characterized in that According to the time interval distribution in the operation behavior data, an adaptive sliding window algorithm is used to calculate the operation frequency and operation rhythm of the question setter within a set time period, including: Define the time length of the sliding window, calculate the ratio between the operation behavior data in the sliding window and the time length, and obtain the initial operation frequency; Based on the initial operation frequencies of adjacent sliding windows, an initial operation rhythm is calculated; The initial operation frequency and the initial operation rhythm are smoothed by using a preset window overlap ratio to obtain the operation frequency and the operation rhythm.

6. The method according to claim 5, characterized in that The expression of the operating frequency is: ,in, For sliding window The initial operating frequency, For sliding window The initial operating frequency, is the preset window overlap ratio; The expression of the operation rhythm is: ,in, For sliding window The initial operation rhythm, For sliding window The initial operation rhythm.

7. The method according to claim 1, characterized in that The difference between the entropy value and the standard entropy value is used, combined with the operation frequency and the operation rhythm, to determine the validity of the identity of the question setter through a dynamic adaptive threshold technology, including: Constructing a machine learning model, wherein the machine learning model is a model trained using historical operation behavior data; Inputting the difference between the entropy value and the standard entropy value, the operation frequency, and the operation rhythm into the machine learning model to obtain an abnormality score; Based on the anomaly score and an adaptive threshold of the anomaly score, the validity of the identity of the question setter is determined.

8. A system for detecting and verifying the test setter of a computer-based test, characterized in that: include: An acquisition unit is used to acquire the operation behavior data of the test setter in the computer-based test system, wherein the operation behavior data includes: event timestamps of keyboard input, mouse movement and click, and the duration and interval time of each operation behavior data; A calculation unit, used to calculate the operation frequency and operation rhythm of the question setter within a set time period using an adaptive sliding window algorithm according to the time interval distribution in the operation behavior data; A determination unit, configured to determine an entropy value of the operation behavior data of the question setter based on the operation frequency and the operation rhythm; The judgment unit is used to utilize the difference between the entropy value and the standard entropy value, combined with the operation frequency and the operation rhythm, to judge the validity of the identity of the question setter through dynamic adaptive threshold technology.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Identity authentication method based on mouse behaviors of user

    CN103530546A

  • Multi-scene subject recognition method based on keystroke dynamics and mouse dynamics

    CN113722685A

  • Intelligent terminal implicit identity authentication method fusing clicking, sliding and keystroke features

    CN115640559A

  • Continuous identity authentication method, device, equipment and medium

    CN117407847A

  • Authentication system based on artificial intelligence

    CN118153016A

Cited By

  • Network attack security detection method

    CN120238361A

  • A method for network attack security detection

    CN120238361B