An anti-plagiarism management method, system, device and medium for electronic assignments

Abstract

The present invention discloses an anti - plagiarism management method, system, device and medium for electronic homework. The method includes: receiving the original electronic homework through the student operation subsystem to generate an original homework image; calculating the first maximum similarity between the original homework image and all intermediate homework images in the intermediate database, and determining whether it exceeds the first matching threshold; if so, assigning a first plagiarism label to the original electronic homework and storing it in the first database; if not, calculating the second maximum similarity between the original electronic homework and all original electronic homework in the second database, and determining whether it exceeds the second matching threshold; if so, assigning a second plagiarism label to the original electronic homework and storing it in the first database; statistically analyzing the plagiarism behavior habits of all original electronic homework assigned with the first plagiarism label or the second plagiarism label in the first database through the teacher management subsystem to generate a student plagiarism report. The present invention can effectively supervise students' plagiarism behavior.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to an anti-plagiarism management method, system, device and medium for electronic assignments. Background Art

[0002] With the rapid development of network technology, many universities have gradually popularized the use of electronic assignment submission methods. However, this still cannot avoid the objectively existing student plagiarism behavior, resulting in a serious decline in the quality of assignments, and teachers cannot obtain corresponding information feedback through the assignment situation. Traditional plagiarism detection methods often rely on teachers to continuously compare similar assignments to make appropriate judgments. However, when the number of students increases, it will consume the time cost and energy of teachers and cannot maintain the judgment accuracy. Summary of the Invention

[0003] The present invention provides an anti-plagiarism management method, system, device and medium for electronic assignments to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or creation condition.

[0004] In a first aspect, an anti-plagiarism management method for electronic assignments is provided. The method includes:

[0005] Receiving, through a student operation subsystem, the original electronic assignment submitted by a student within a first preset time period, and generating a corresponding original assignment image;

[0006] Calculating a first maximum similarity between the original assignment image and all intermediate assignment images previously stored in an intermediate database, and determining whether it exceeds a first matching threshold;

[0007] If so, assigning a first plagiarism label to the original electronic assignment and then storing it in a first database;

[0008] If not, calculating a second maximum similarity between the original electronic assignment and all original electronic assignments previously stored in a second database, and determining whether it exceeds a second matching threshold;

[0009] If so, assigning a second plagiarism label to the original electronic assignment and then storing it in the first database;

[0010] Statistically analyzing the plagiarism behavior habits of all the original electronic assignments assigned with the first plagiarism label or the second plagiarism label in the first database through a teacher management subsystem, and generating and outputting a student plagiarism report.

[0011] Further, all the intermediate assignment images previously stored in the intermediate database are displayed on the operation interface of the student operation subsystem within the first preset time period.

[0012] Further, the method further includes:

[0013] When the student operation subsystem determines that the second maximum similarity does not exceed the second matching threshold, generating a copy of the original electronic assignment, preprocessing it, and storing it in the intermediate database, and then storing the original electronic assignment in the second database;

[0014] Receiving all target electronic assignments submitted by the teacher through the teacher management subsystem and storing them in the third database, where all the target electronic assignments are obtained by the teacher correcting all the original electronic assignments stored in the second database.

[0015] Further, calculating the first maximum similarity between the original assignment image and all the intermediate assignment images previously stored in the intermediate database includes:

[0016] Using the HOG feature operator to calculate the original feature vector corresponding to the original assignment image and all the to-be-tested feature vectors corresponding to all the intermediate assignment images previously stored in the intermediate database;

[0017] Calculating the Euclidean distance between the original feature vector and each to-be-tested feature vector, and then obtaining the maximum Euclidean distance therefrom and defining it as the first maximum similarity.

[0018] Further, calculating the second maximum similarity between the original electronic assignment and all the original electronic assignments previously stored in the second database includes:

[0019] Extracting a first set of effective sentences from the original electronic assignment, and extracting all corresponding second sets of effective sentences from all the original electronic assignments previously stored in the second database;

[0020] Combining the longest common subsequence algorithm to calculate the similarity measure between the first set of effective sentences and each second set of effective sentences, and obtaining the maximum similarity measure therefrom and defining it as the second maximum similarity.

[0021] Further, the generation process of the student plagiarism report includes:

[0022] The first plagiarism label records the student information with plagiarism behavior and the warning information indicating online plagiarism behavior, and the second plagiarism label records the student information with plagiarism behavior, the student information with being plagiarized behavior, and the warning information indicating offline plagiarism behavior;

[0023] Extracting all the original electronic assignments given the first plagiarism label from the first database, recording all the student information with plagiarism behavior, and statistically generating an online plagiarism statistics table for the current school year;

[0024] Extract all the original electronic assignments with the second plagiarism label from the first database, record all the student information where plagiarism occurs and all the student information where plagiarism is suffered, and statistically generate an offline plagiarism statistics table for the current school year;

[0025] Merge the online plagiarism statistics table and the offline plagiarism statistics table to obtain a student plagiarism report.

[0026] Furthermore, the preprocessing of the original electronic assignment copy includes: performing partial content blurring on the original electronic assignment copy and then converting it into an intermediate assignment image.

[0027] In a second aspect, there is provided an anti-plagiarism management system for electronic assignments, the system comprising:

[0028] A student operation subsystem, configured to receive the original electronic assignments submitted by students within a first preset time period and generate corresponding original assignment images; calculate the first maximum similarity between the original assignment images and all the intermediate assignment images previously stored in the intermediate database; when it is determined that the first maximum similarity exceeds a first matching threshold, assign a first plagiarism label to the original electronic assignment and then store it in the first database; when it is determined that the first maximum similarity does not exceed the first matching threshold, calculate the second maximum similarity between the original electronic assignment and all the original electronic assignments previously stored in the second database; when it is determined that the second maximum similarity exceeds a second matching threshold, assign a second plagiarism label to the original electronic assignment and then store it in the first database; when it is determined that the second maximum similarity does not exceed the second matching threshold, generate a copy of the original electronic assignment, perform preprocessing on it and then store it in the intermediate database, and then store the original electronic assignment in the second database;

[0029] A teacher management subsystem, configured to perform plagiarism behavior habit statistics on all the original electronic assignments with the first plagiarism label or the second plagiarism label in the first database, generate and output a student plagiarism report; and receive all the target electronic assignments submitted by teachers and store them in a third database, where all the target electronic assignments are obtained by teachers correcting all the original electronic assignments stored in the second database;

[0030] A data storage subsystem, configured to store the intermediate database, the first database, the second database, and the third database.

[0031] In a third aspect, there is provided a computer device, comprising:

[0032] At least one memory;

[0033] At least one processor;

[0034] The memory stores a computer program, and the processor executes the computer program to implement the anti-plagiarism management method for electronic homework as described in the first aspect.

[0035] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the anti-plagiarism management method for electronic homework as described in the first aspect.

[0036] The present invention has at least the following beneficial effects: By performing similarity detection on the original homework image obtained by converting the original electronic homework, the online plagiarism habits of students can be monitored, and by performing similarity detection on the original electronic homework, the offline plagiarism habits of students can be monitored. At the same time, it is beneficial to more accurately complete the task of detecting students' homework plagiarism, saving the time cost and energy of teachers. By formulating a student plagiarism report, it is convenient for teachers to take corresponding measures against students with plagiarism behaviors in a targeted manner, and it is also convenient for teachers to give reminders to students who provide plagiarism conditions in a targeted manner, thereby gradually reducing the occurrence of homework plagiarism. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings are used to provide a further understanding of the technical solutions of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solutions of the present invention, and do not constitute a limitation to the technical solutions of the present invention.

[0038] Figure 1 It is a flowchart of an anti-plagiarism management method for electronic homework in an embodiment of the present invention;

[0039] Figure 2 It is a structural composition diagram of an anti-plagiarism management system for electronic homework in an embodiment of the present invention;

[0040] Figure 3 It is a schematic hardware structure diagram of a computer device in an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0042] It should be noted that although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the system or the flowchart. Terms such as "first" and "second" in the specification, claims and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence.

[0043] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an anti - plagiarism management method for electronic homework provided by an embodiment of the present invention. The method includes the following:

[0044] Step S110: Receive the original electronic homework submitted by students within a first preset time period through the student operation subsystem, and generate a corresponding original homework image;

[0045] Step S120: Calculate the first maximum similarity between the original homework image and all the intermediate homework images previously stored in the intermediate database through the student operation subsystem, and determine whether it exceeds a first matching threshold; if so, continue to execute Step S130; if not, jump to execute Step S140;

[0046] Step S130: Store the original electronic homework in the first database after assigning a first plagiarism label to it through the student operation subsystem;

[0047] Step S140: Calculate the second maximum similarity between the original electronic homework and all the original electronic homework previously stored in the second database through the student operation subsystem, and determine whether it exceeds a second matching threshold; if not, continue to execute Step S150; if so, jump to execute Step S160.

[0048] Step S150: Generate a copy of the original electronic homework through the student operation subsystem, pre - process it, and then store it in the intermediate database, and store the original electronic homework in the second database;

[0049] Step S160: Store the original electronic homework in the first database after assigning a second plagiarism label to it through the student operation subsystem;

[0050] Step S170: Statistically analyze the plagiarism behavior habits of all the original electronic homework assigned with the first plagiarism label or the second plagiarism label in the first database through the teacher management subsystem, and generate and output a student plagiarism report.

[0051] In an embodiment of the present invention, the first preset time period mentioned in the above step S110 is actually the time limit for the student operation subsystem to allow students to submit electronic homework. The electronic homework includes an electronic test report made by the student after completing a certain test operation, and the electronic homework is uploaded to the student operation subsystem in the form of Word. More importantly, all the intermediate homework images originally stored in the intermediate database will be displayed on the operation interface provided by the student operation subsystem within this time limit, which can facilitate students to learn from the homework formats of others and can also facilitate the monitoring of students' online plagiarism behavior. It should be noted that after exceeding this time limit, the intermediate database will automatically perform the operation of clearing the data in the library to save storage space.

[0052] In an embodiment of the present invention, the specific implementation process of the above step S120 is as follows:

[0053] Step S121: Based on the HOG feature operator, parse the corresponding original feature vector from the original homework image. Among them, the full English name of HOG is Histogram of oriented gradient, which is translated as Histogram of Oriented Gradients.

[0054] Step S122: The intermediate database originally stores N intermediate homework images internally, where N is a positive integer and N>0. Based on the HOG feature operator, parse the corresponding feature vectors to be tested from each intermediate homework image, and then N feature vectors to be tested can be obtained.

[0055] Step S123: According to the existing Euclidean distance solution formula, calculate the Euclidean distance between the original feature vector and each feature vector to be tested, and then N corresponding Euclidean distances can be obtained.

[0056] Step S124: Extract the maximum result from the N Euclidean distances through a conventional numerical comparison method, and then directly determine this maximum result as the first maximum similarity.

[0057] Step S125: Obtain the first matching threshold set by the user according to their own needs, and determine whether it is true that the first maximum similarity is greater than the first matching threshold. If it is true, it means that the original homework image has borrowed most of the relevant content from one of the intermediate homework images in the intermediate database and there is a suspicion of online plagiarism. If it is not true, it means that there are significant differences in most of the content between the original homework image and any intermediate homework image in the intermediate database.

[0058] In the above step S121, first, the original homework image is segmented to obtain the corresponding segmented image, and then the gamma space and color space in the segmented image are normalized to obtain the normalized image; then, the gradient of the normalized image is solved to obtain the first gradient value in the horizontal coordinate direction and the second gradient value in the vertical coordinate direction, and the histogram of oriented gradients is determined by combining the first gradient value and the second gradient value; finally, the segmented image is normalized in regions by using the histogram of oriented gradients to generate the original feature vector.

[0059] It should be noted that the method for obtaining any one of the to-be-tested feature vectors in the above step S122 is the same as the method for obtaining the original feature vector in the step S121, and will not be elaborated here.

[0060] In the embodiment of the present invention, the specific implementation process of the above step S130 is as follows: First, the student information associated with the original electronic homework is obtained, and the student information includes class, student number, and name. At the same time, the corresponding warning information is generated to record that the current plagiarism behavior of the student belongs to online plagiarism behavior; secondly, the student information with plagiarism behavior, the warning information, and the first maximum similarity obtained by solving through the above step S124 are encapsulated to form the first plagiarism label; finally, the original electronic homework is associated and bundled with the first plagiarism label and then transmitted to the first database for storage.

[0061] In the embodiment of the present invention, the specific implementation process of the above step S140 includes the following:

[0062] Step S141: Segment the original electronic homework and extract part-of-speech features to obtain the corresponding first set of valid sentences;

[0063] Step S142: There are originally M original electronic homework stored in the second database, which are re-denoted as M to-be-tested original electronic homework for differential description. M is a positive integer and M>0. Each to-be-tested original electronic homework is segmented and part-of-speech features are extracted to obtain the corresponding second set of valid sentences, and then M second sets of valid sentences can be obtained;

[0064] Step S143: Use the longest common subsequence algorithm to calculate the similarity measure between the first set of valid sentences and each second set of valid sentences, and then M corresponding similarity measures can be obtained;

[0065] Step S144: Extract the maximum result from the M similarity measures through a conventional numerical comparison method, and directly determine the maximum result as the second maximum similarity, and at the same time obtain the to-be-tested original electronic homework associated with the maximum result;

[0066] Step S145: Obtain the second matching threshold set by the user according to their own needs, and determine whether it holds that the second maximum similarity is greater than the second matching threshold; if it holds, it indicates that most of the relevant content of the original electronic assignment is borrowed from a certain original electronic assignment to be tested inside the second database, and there is a suspicion of offline plagiarism; if it does not hold, it indicates that there are significant differences in most of the content between the original electronic assignment and any original electronic assignment to be tested inside the second database.

[0067] In the embodiment of the present invention, the specific implementation process of the above step S141 includes: First, use a period, a question mark, and an exclamation mark as the sentence segmentation criteria to segment the original electronic assignment to obtain a first initial sentence set; then obtain a preset length threshold, delete all sentences in the first initial sentence set whose length is less than the length threshold, and thus obtain a first updated sentence set; secondly, call an existing dictionary-based word segmentation method to perform word segmentation on each sentence in the first updated sentence set and remove the stop words in the sentence to obtain the corresponding word segmentation sequence, that is, the first updated sentence set has now been updated to be composed of the word segmentation sequences corresponding to each sentence therein; finally, obtain a preset quantity threshold, delete all word segmentation sequences in the first updated sentence set after the word segmentation update whose word segmentation quantity is less than the quantity threshold, and thus obtain a first effective sentence set.

[0068] It should be noted that the method for obtaining any second effective sentence set in the above step S142 is the same as the method for obtaining the first effective sentence set in the above step S141, and will not be elaborated here.

[0069] In the above step S143, taking the example of obtaining the similarity measure between the first effective sentence set and any second effective sentence set for illustration, the specific process is as follows:

[0070] Step A1: Obtain a first word segmentation sequence from the first effective sentence set, record the number of word segments included in the first word segmentation sequence as n, and then denote the first word segmentation sequence as X = {x1, x2, x3,..., x n};

[0071] Step A2: Obtain a second word segmentation sequence from the second effective sentence set, record the number of word segments included in the second word segmentation sequence as m, and then denote the second word segmentation sequence as Y = {y1, y2, y3,..., y m};

[0072] Step A3: Calculate the longest common subsequence shared between the first word segmentation sequence and the second word segmentation sequence, obtain the number of word segments included in the longest common subsequence and denote it as k, and then calculate the similarity measure between the first word segmentation sequence and the second word segmentation sequence as s = 2k / (n + m);

[0073] Step A4: Since the number of first word segmentation sequences included in the first set of valid sentences is N1, and the number of second word segmentation sequences included in the second set of valid sentences is N2, by repeating the above steps A1 to A3 for N1×N2 times, N1×N2 similarity measures can be obtained;

[0074] Step A5: Obtain a preset measurement threshold, extract all similarity measures greater than the measurement threshold from the N1×N2 similarity measures through a conventional numerical comparison method, and count the number of all similarity measures as p. Furthermore, the similarity measure between the first set of valid sentences and the second set of valid sentences can be calculated as: sim = p / min(N1, N2).

[0075] In an embodiment of the present invention, the specific implementation process of the above step S160 is as follows: First, obtain the student information associated with the original electronic assignment, and at the same time generate corresponding warning information to record that the current plagiarism behavior of this student belongs to offline plagiarism behavior; Second, obtain the student information associated with the to-be-tested original electronic assignment obtained through the above step S144, and define it as the student information of the plagiarized student. Then, package the student information of the plagiarizing student, the warning information, and the second maximum similarity solved through the above step S144 to form a second plagiarism label; Finally, associate and bundle the original electronic assignment with the second plagiarism label and transmit it to the first database for storage; It should be noted that the above-mentioned two pieces of student information both include class, student number, and name.

[0076] In an embodiment of the present invention, the specific implementation process of the above step S170 includes the following:

[0077] Step S171: Divide all the original electronic assignments in the first database into sets according to the label types, and obtain a first assignment set associated and bundled with the first plagiarism label and a second assignment set associated and bundled with the second plagiarism label;

[0078] Step S172: Extract all the first plagiarism labels from the first assignment set, obtain all the student information of the students with plagiarism behavior according to all the first plagiarism labels, and only count the number of online plagiarism occurrences when each student submits all the electronic assignment tasks completed in the current academic year, thereby forming a corresponding online plagiarism statistics table;

[0079] Step S173: Extract all second plagiarism tags from the second assignment set, obtain the information of all students with plagiarism behaviors according to all the second plagiarism tags, and only count the number of offline plagiarism occurrences when each student has completed all electronic assignment submission tasks in the current academic year;

[0080] Step S174: On the basis of completing step S173 above, continue to obtain the information of all students with being plagiarized behaviors according to all the second plagiarism tags, and only count the number of offline being plagiarized occurrences when each student has completed all electronic assignment submission tasks in the current academic year, and then jointly form a corresponding offline plagiarism statistical table;

[0081] Step S175: Merge the online plagiarism statistical table and the offline plagiarism statistical table to obtain a final student plagiarism report.

[0082] In the embodiment of the present invention, the specific implementation process of the above step S150 includes: First, copy the original electronic assignment through the student operation subsystem to generate a copy of the original electronic assignment; Secondly, since most of the original electronic assignments are electronic test reports saved in Word format, obtain all paragraphs containing specific numerical values by performing numerical queries on the copy of the original electronic assignment, and then perform conventional fuzzification processing on all the paragraphs; Finally, convert the format of the processed copy of the original electronic assignment to obtain a corresponding intermediate assignment image, and transmit the intermediate assignment image to the intermediate database for storage, and at the same time transmit the original electronic assignment to the second database for storage; By introducing the above preprocessing method of paragraph fuzzification in the embodiment of the present invention, the labor achievements of each student can be protected to the greatest extent.

[0083] In the embodiment of the present invention, after executing the above step S150, it further includes: Automatically open the teacher marking permission through the teacher management subsystem after detecting that the first preset time period has expired, so that the teacher can log in to the teacher management subsystem to correct and submit all the original electronic assignments currently stored in the second database one by one to obtain corresponding all target electronic assignments, and each target electronic assignment retains the teacher's marking traces and the final score; Then receive all the target electronic assignments through the teacher management subsystem and store them in the third database; Finally, display all the target electronic assignments stored in the third database on the operation interface provided by the student operation subsystem within the second preset time period, which can facilitate each student to query and check the scores.

[0084] It should be noted that the second preset time period is actually the time limit for students to check their scores allowed by the student operation subsystem. It can be set before the student operation subsystem executes the next electronic homework submission task. After exceeding the second preset time period, both the second database and the third database will automatically clear the data in the database to save their respective storage spaces.

[0085] In the embodiment of the present invention, since all the intermediate homework images stored in the intermediate database are obtained through special processing, and all the original electronic homework stored in the second database has not been processed. For the intermediate database, a relatively simple image matching task is completed using the HOG feature operator, while for the second database, a relatively complex and reliable text matching task is completed by combining the part-of-speech feature extraction method and the longest common subsequence algorithm, which can save the time cost of the student operation subsystem to verify the plagiarism behavior of each submitted original electronic homework to the greatest extent.

[0086] In the embodiment of the present invention, by detecting the similarity of the original homework images converted from the original electronic homework, the online plagiarism habits of students can be monitored, and by detecting the similarity of the original electronic homework, the offline plagiarism habits of students can be monitored. At the same time, it is beneficial to more accurately complete the task of detecting students' homework plagiarism, saving the time cost and energy of teachers. By formulating a student plagiarism report, it is convenient for teachers to take corresponding measures against students with plagiarism behaviors, and it is also convenient for teachers to remind students who provide plagiarism conditions, thereby gradually reducing the occurrence of homework plagiarism.

[0087] Please refer to Figure 2 , Figure 2 is a schematic diagram of the composition of an anti-plagiarism management system for electronic homework provided by the embodiment of the present invention. The system includes a student operation subsystem 210, a data storage subsystem 220, and a teacher management subsystem 230, where:

[0088] The student operation subsystem 210 is used to perform the following functions: receive the original electronic homework submitted by students within a first preset time period, and simultaneously obtain the original homework image corresponding to the original electronic homework; calculate the first maximum similarity between the original homework image and all the intermediate homework images previously stored in the intermediate database; after determining that the first maximum similarity is greater than the first matching threshold, associate and bundle the first plagiarism label with the original electronic homework and store it in the first database; after determining that the first maximum similarity is less than or equal to the first matching threshold, calculate the second maximum similarity between the original electronic homework and all the original electronic homework previously stored in the second database; after determining that the second maximum similarity is greater than the second matching threshold, associate and bundle the second plagiarism label with the original electronic homework and store it in the first database; after determining that the second maximum similarity is less than or equal to the second matching threshold, generate a copy of the original electronic homework, store it in the intermediate database after performing preprocessing, and then store the original electronic homework in the second database;

[0089] The teacher management subsystem 230 is used to perform the following functions: conduct a statistical analysis of the plagiarism behavior habits of all the original electronic homework assigned with the second plagiarism label or the first plagiarism label in the first database, and generate and output a student plagiarism report; and receive all the target electronic homework submitted by teachers and store them in the third database, where all the target electronic homework are actually obtained by teachers after correcting all the original electronic homework stored in the second database;

[0090] The data storage subsystem 220 is used to perform the following function: store the above-mentioned first database, second database, third database, and intermediate database.

[0091] The content in the above method embodiments is applicable to the present device embodiment. The functions implemented by the present device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are the same as those of the above method embodiments, and will not be elaborated here.

[0092] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the anti-plagiarism management method for electronic assignments in the above embodiment is implemented. Among them, the computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. That is to say, the storage device includes any medium that stores or transmits information in a readable form by a device (such as a computer, mobile phone, etc.), and can be a read-only memory, a disk, or an optical disk, etc.

[0093] In addition, Figure 3 FIG. is a schematic diagram of the hardware structure of the computer device provided by the embodiment of the present invention. The computer device includes devices such as a processor 320, a memory 330, an input unit 340, and a display unit 350. Those skilled in the art can understand that Figure 3 the device structure devices shown do not constitute a limitation to all devices, and may include more or fewer components than those shown, or combine some components. The memory 330 can be used to store the computer program 310 and each functional module. The processor 320 runs the computer program 310 stored in the memory 330, thereby performing various functional applications and data processing of the device. The memory can be an internal memory or an external memory, or include an internal memory and an external memory. The internal memory can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, or a random access memory. The external memory can include a hard disk, a floppy disk, a ZIP disk, a USB flash drive, a magnetic tape, etc. The memory 330 disclosed in the embodiment of the present invention includes, but is not limited to, these types of memories. The memory 330 disclosed in the embodiment of the present invention is only an example and not a limitation.

[0094] The input unit 340 is used to receive the input of signals and the keywords input by the user. The input unit 340 may include a touch panel and other input devices. The touch panel can collect the touch operations of the user on or near it (such as the operations of the user using any suitable object or accessory such as a finger, a stylus, etc. on or near the touch panel), and drive the corresponding connection device according to a preset program; the other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as play control keys, switch keys, etc.), a trackball, a mouse, a joystick, etc. The display unit 350 can be used to display the information input by the user or the information provided to the user and various menus of the terminal device. The display unit 350 may be in the form of a liquid crystal display, an organic light emitting diode, etc. The processor 320 is the control center of the terminal device, connecting various parts of the entire device through various interfaces and lines, and by running or executing the software programs and / or modules stored in the memory 320, and calling the data stored in the memory, performing various functions and processing data.

[0095] As an embodiment, the computer device includes at least one processor 320, at least one memory 330, and at least one computer program 310, wherein the at least one computer program 310 is stored in the at least one memory 330 and is configured to be executed by the at least one processor 320, and the at least one computer program 310 is configured to execute the anti-plagiarism management method for electronic operations in the above embodiment.

[0096] Although the description of the present application has been quite detailed and has particularly described several of the embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but rather should be regarded as effectively covering the intended scope of the present application by considering the prior art to provide a broad interpretation of these claims. In addition, the present application has been described above in terms of embodiments foreseeable by the inventor for the purpose of providing a useful description, and non-substantive changes to the present application that are not currently foreseeable may still represent equivalent changes to the present application.

Claims

1. An anti-plagiarism management method for electronic assignments, characterized in that, The method comprises: Receiving, through the student operation subsystem, an original electronic homework submitted by a student within a first preset time period, and generating a corresponding original homework image; Calculating a first maximum similarity between the original homework image and all the intermediate homework images previously stored in the intermediate database, and determining whether it exceeds a first matching threshold; wherein all the intermediate homework images previously stored in the intermediate database are displayed on the operation interface of the student operation subsystem within the first preset time period; If yes, the original electronic homework is assigned a first plagiarism label and then stored in a first database; If not, calculating a second maximum similarity between the original electronic assignment and all original electronic assignments previously stored in the second database, and determining whether it exceeds a second matching threshold; If yes, the original electronic homework is assigned a second plagiarism label and then stored in the first database; The teacher management subsystem collects statistics of plagiarism behavior habits for all original electronic assignments assigned with the first plagiarism label or the second plagiarism label in the first database, and generates a student plagiarism report output; Wherein, the method further comprises: When the student operation subsystem determines that the second maximum similarity does not exceed the second matching threshold, a copy of the original electronic homework is generated and stored in the intermediate database after preprocessing, and then the original electronic homework is stored in the second database; All target electronic assignments submitted by teachers are received through the teacher management subsystem and stored in the third database. All target electronic assignments are obtained by the teacher correcting all original electronic assignments stored in the second database.

2. The anti-plagiarism management method for electronic assignments according to claim 1, wherein Calculating the first maximum similarity between the original job image and all the intermediate job images originally stored in the intermediate database includes: Calculate the original feature vector corresponding to the original working image and all the feature vectors to be tested corresponding to all the intermediate working images originally stored in the intermediate database by using the HOG feature operator; The Euclidean distance between the original feature vector and each feature vector to be tested is calculated, and then the maximum Euclidean distance is obtained and defined as the first maximum similarity.

3. The anti-plagiarism management method for electronic operations according to claim 1, characterized in that, Calculating the second maximum similarity between the original electronic assignment and all original electronic assignments previously stored in the second database includes: Extracting a first valid sentence set from the original electronic assignment, and extracting all corresponding second valid sentence sets from all original electronic assignments originally stored in the second database; The similarity measure between the first valid sentence set and each second valid sentence set is calculated in combination with the maximum common subsequence algorithm, and the maximum similarity measure is obtained and defined as the second maximum similarity.

4. The anti-plagiarism management method for electronic assignments according to claim 1, wherein The process of generating the student plagiarism report includes: The first plagiarism tag records information about students who have plagiarized and warning information about online plagiarism, and the second plagiarism tag records information about students who have plagiarized, information about students who have been plagiarized, and warning information about offline plagiarism; Extract all the original electronic assignments given the first plagiarism label from the first database, record the information of all students with plagiarism behavior, and statistically generate an online plagiarism statistics table for the current school year; Extract all the original electronic assignments given the second plagiarism label from the first database, record the information of all students with plagiarism behavior and the information of all students who have been plagiarized, and statistically generate an offline plagiarism statistics table for the current school year; Merge the online plagiarism statistics table and the offline plagiarism statistics table to obtain a student plagiarism report.

5. The anti-plagiarism management method for electronic operations according to claim 1, characterized in that, Preprocess the original electronic assignment copy, including: after partially obscuring the content of the original electronic assignment copy, convert it into an intermediate assignment image.

6. An anti-plagiarism management system for electronic assignments, characterized in that, The system includes: A student operation subsystem, which is used to receive the original electronic assignments submitted by students within the first preset time period and generate corresponding original assignment images; calculate the first maximum similarity between the original assignment images and all the intermediate assignment images previously stored in the intermediate database; when it is determined that the first maximum similarity exceeds the first matching threshold, assign the first plagiarism label to the original electronic assignment and then store it in the first database; when it is determined that the first maximum similarity does not exceed the first matching threshold, calculate the second maximum similarity between the original electronic assignment and all the original electronic assignments previously stored in the second database; when it is determined that the second maximum similarity exceeds the second matching threshold, assign the second plagiarism label to the original electronic assignment and then store it in the first database; when it is determined that the second maximum similarity does not exceed the second matching threshold, generate a copy of the original electronic assignment, preprocess it and then store it in the intermediate database, and then store the original electronic assignment in the second database; A teacher management subsystem, which is used to statistically analyze the plagiarism behavior habits of all the original electronic assignments given the first plagiarism label or the second plagiarism label in the first database, generate and output a student plagiarism report; and receive all the target electronic assignments submitted by the teacher and store them in the third database, where all the target electronic assignments are obtained by the teacher correcting all the original electronic assignments stored in the second database; A data storage subsystem, which is used to store the intermediate database, the first database, the second database, and the third database.

7. A computer device, characterized in that, Includes: At least one memory; At least one processor; The memory stores a computer program, and the processor executes the computer program to implement the anti-plagiarism management method for electronic assignments as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the anti-plagiarism management method for electronic assignments as described in any one of claims 1 to 5.

Images