A data cleaning method and system for a smart campus platform

Abstract

The present invention relates to the field of online course selection technology, and in particular to a data cleaning method and system for a smart campus platform. The present invention constructs a course selection map based on the courses of the major to be tested, and determines suspected abnormal courses based on the prerequisite relationship between the current elective courses and the courses already taken; selects actual abnormal courses from the suspected abnormal courses based on the elective situation of graduates who have participated in competitions, and the situation that the suspected abnormal courses are in the same subject category as the courses already taken and the current elective courses; determines the recommended courses of the actual abnormal courses based on the correlation between the current untaken courses and the courses corresponding to the nodes in the course selection map. The present invention comprehensively analyzes the abnormality of the current elective courses based on the analysis of the students' personal interests and hobbies and their participation in competitions, increases the accuracy of abnormal course screening, and improves the data cleaning effect of the course selection data of the smart campus platform.

Description

Technical Field

[0001] The present invention relates to the technical field of online course selection, and in particular to a data cleaning method and system for a smart campus platform. Background Art

[0002] According to general teaching management regulations at Chinese universities, first-semester courses for freshmen are typically arranged centrally by the university. Students are typically required to pre-select courses in the student management system on the smart campus platform before each subsequent semester. Institutions that emphasize professional depth and structured development, such as engineering schools, require students to have a sufficient knowledge base for their elective courses. Due to insufficient understanding of course content, prerequisites, and their own learning progress, some students may choose the wrong courses, which reduces learning outcomes and wastes teaching resources, further impacting the university's teaching plans and resource allocation. Identifying misselected courses from students' chosen courses is crucial for improving the efficiency of teaching plan execution and optimizing resource allocation.

[0003] Certain courses must be taken after students have completed their prerequisite courses to avoid learning difficulties due to a lack of foundational knowledge. Abnormal elective courses can be identified by determining whether students have already taken the prerequisite courses for the elective courses they choose. However, due to personal interests, participation in competitions, and other circumstances, students may choose courses without following the prerequisite relationships between courses. This can lead to inaccurate determination of incorrectly selected courses based on the prerequisite relationships between courses, resulting in poor data cleaning effectiveness for the smart campus platform's course selection data. Summary of the Invention

[0004] In order to solve the technical problem of inaccurate course selection caused by personal interests and hobbies, participation in competitions, etc., which do not require the prerequisite relationship between courses, the purpose of the present invention is to provide a data cleaning method and system for a smart campus platform. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a data cleaning method for a smart campus platform, the method comprising:

[0006] Obtain the courses and subject categories of the major of the student to be tested, as well as the courses already taken, current elective courses and current untaken courses of the student to be tested;

[0007] Based on the courses of the major of the student to be tested, a course elective map is constructed with courses as nodes and prerequisite relationships between courses as relationships; based on the prerequisite relationship between the current elective course and the courses already taken, suspected abnormal courses are selected from the current elective courses;

[0008] Based on the elective status of each suspected abnormal course by graduates who participated in the competition in which the students to be tested participated, and the fact that each suspected abnormal course is in the same subject category as the courses already taken and the current elective courses, the actual abnormal courses among the suspected abnormal courses are selected;

[0009] Based on the correlation between the current untaken courses and the courses corresponding to the nodes in the course selection map, the recommended courses for the actual abnormal courses are determined.

[0010] Furthermore, the selection of suspected abnormal courses from the current elective courses includes:

[0011] Delete all nodes in the course selection graph except for the nodes corresponding to the courses already taken by the student to be tested and the current elective courses, as well as all edges associated with the other nodes, and record the remaining graph as the course selection path graph of the student to be tested;

[0012] Obtain the prerequisite courses for each course; if each current elective course of the student to be tested does not have a prerequisite course corresponding to the current elective course in the course corresponding to the predecessor node of the corresponding node in the course selection path graph, then each current elective course is recorded as a suspected abnormal course.

[0013] Furthermore, selecting actual abnormal courses from suspected abnormal courses includes:

[0014] Obtain the competitions participated by the students to be tested and each graduate; select graduates who have participated in all competitions participated by the students to be tested before the current semester as students to be analyzed, and calculate the ratio of the number of students to be analyzed who have taken each suspected abnormal course to the total number of students to be analyzed to obtain the competition relevance of each suspected abnormal course;

[0015] The proportion of the subjects of the students being tested that are in the same subject category as each suspected abnormal course is recorded as the subject interest level of each suspected abnormal course;

[0016] The proportion of the current elective courses of the tested students that belong to the same subject category as each suspected abnormal course is recorded as the course correlation degree of each suspected abnormal course;

[0017] According to the competition relevance, the subject interest and the course association, the abnormality of each suspected abnormal course is obtained; and based on the abnormality, an actual abnormal course among the suspected abnormal courses is selected.

[0018] Furthermore, the process of determining the recommended courses for the actual abnormal courses based on the correlation between the currently untaken courses and the courses corresponding to the nodes in the course selection graph includes:

[0019] For each of the course selection path graphs, determine whether there is a node in the course selection path graph that has a prerequisite relationship with each currently untaken course. If so, record the node as an associated node. When the course corresponding to the associated node is a prerequisite course for the currently untaken course, add an edge from the associated node to the currently untaken course. When the currently untaken course is a prerequisite course for the course corresponding to the associated node, add an edge from the currently untaken course to the associated node. Otherwise, each currently untaken course cannot be added to the course selection path graph.

[0020] The graph when all currently untaken courses are added to the course selection path graph is called the extended path graph;

[0021] If the node of the currently untaken course in the extended path graph is not connected to the node corresponding to the actual abnormal course, the extended path graph is recorded as the analysis graph of the currently untaken course; the number of analysis graphs of the currently untaken course in all extended path graphs is counted and recorded as the recommended value of the currently untaken course;

[0022] The n currently untaken courses corresponding to the largest recommendation values ​​are selected from all currently untaken courses as the recommended courses for the actual abnormal courses of the students to be tested.

[0023] Furthermore, obtaining the abnormality degree of each suspected abnormal course includes:

[0024] A negative correlation mapping is performed on the product of the competition relevance and the subject interest, and the mapping result and the product of the course association are normalized to obtain the abnormality degree of each suspected abnormal course.

[0025] Furthermore, the actual abnormal course is a suspected abnormal course whose abnormality degree is greater than a preset abnormality threshold.

[0026] Furthermore, the current elective courses are the remaining courses taken by all graduates of the major of the student to be tested in the current semester except the current elective courses.

[0027] Furthermore, there is no prerequisite relationship between the currently untaken courses.

[0028] Furthermore, the n is equal to the actual number of abnormal courses.

[0029] In a second aspect, another embodiment of the present invention provides a data cleaning system for a smart campus platform, the system comprising:

[0030] The data collection module is used to obtain the courses of the major of the tested student and the subject category to which they belong, as well as the courses the tested student has taken, the current elective courses and the current courses not taken;

[0031] The suspected abnormal course screening module is used to construct a course selection map based on the courses of the major of the tested student, with courses as nodes and prerequisite relationships between courses as relationships; based on the prerequisite relationship between the current elective course and the courses already taken, the suspected abnormal courses in the current elective course are selected;

[0032] The actual abnormal course screening module is used to select the actual abnormal courses among the suspected abnormal courses based on the elective status of each suspected abnormal course by graduates who have participated in the competition in which the tested students participated, and whether each suspected abnormal course belongs to the same subject category as the courses already taken and the current elective courses;

[0033] The course recommendation module is used to determine the recommended courses for actual abnormal courses based on the association between the current untaken courses and the courses corresponding to the nodes in the course selection graph.

[0034] The present invention has the following beneficial effects:

[0035] In the embodiment of the present invention, in order to analyze the relationship between courses and determine the course selection map, since some courses can only be selected after completing the prerequisite courses that serve as their basis, the suspected abnormal courses are preliminarily selected based on the prerequisite relationship between the current elective courses and the courses that have been taken; because the courses selected for competitions or personal interests do not need to consider the prerequisite relationship between courses, in order to ensure the accuracy of the selection of abnormal course selection data, a specific analysis is made as follows: the selection of suspected abnormal courses by graduates who have participated in the competitions participated by the students to be tested reflects the degree of correlation between the suspected abnormal courses and the competitions. The suspected abnormal courses are respectively in the same subject category as the courses that have been taken and the current elective courses, and the selection of suspected abnormal courses by the students to be tested is presented in turn. The team analyzes the degree of abnormality of suspected abnormal courses by combining these factors, including interest in unusual courses and the likelihood that the suspected abnormal courses are professional courses. The team then selects the incorrectly selected courses, which are actually abnormal courses, to make the course selection path more aligned with individual strengths and utilize subject interests to limit students' blind course selection. This provides flexibility for personalized course selection while ensuring academic foundations. The association between the currently untaken courses and the corresponding courses in the course selection map reflects the consistency between the currently untaken courses and the learning path of the students being tested. Based on this, the team recommends courses that meet the students' learning needs to replace the actual abnormal courses, thus modifying the abnormal course selection data and improving the data cleaning effectiveness of the smart campus platform's course selection data. This solution is reasonable within an education system that prioritizes the cultivation of core professional competencies while also taking into account competitions and the development of in-depth interests. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A flowchart of a data cleaning method for a smart campus platform provided by one embodiment of the present invention;

[0038] Figure 2 A partial schematic diagram of a course selection map provided by one embodiment of the present invention;

[0039] Figure 3 A partial schematic diagram of a course selection path diagram provided by one embodiment of the present invention;

[0040] Figure 4 A system structure diagram of a data cleaning system for a smart campus platform provided by one embodiment of the present invention;

[0041] Figure 5 A schematic diagram of a computer device for a data cleaning device for a smart campus platform provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the data cleaning method and system of a smart campus platform proposed by the present invention, its specific implementation method, structure, features and effects are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics of one or more embodiments may be combined in any suitable form.

[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0044] The specific scenario targeted by the present invention is to clean the students' course selection data in the school's academic affairs system of the smart campus platform and determine the abnormal course selection data that exists when students select courses.

[0045] The following describes in detail a data cleaning method and system for a smart campus platform provided by the present invention in conjunction with the accompanying drawings.

[0046] Example 1:

[0047] This invention proposes a data cleaning method for a smart campus platform. Figure 1 , which shows a flowchart of the steps of a data cleaning method for a smart campus platform provided by one embodiment of the present invention, the method comprising:

[0048] Step S1: Obtain the courses of the major of the student to be tested and the subject categories to which they belong, as well as the courses already taken, the current elective courses and the current untaken courses of the student to be tested.

[0049] College students typically select courses before each semester. After course selection, the Smart Campus Platform's academic affairs system database retrieves the student's elective courses for the current semester and the courses taken in the previous semester from the start of the semester. These are recorded as current elective courses and taken courses, respectively. The academic affairs system database also retrieves the elective courses taken by graduates of the student's major each semester. All courses taken by all graduates in the current semester, excluding the current elective courses, are recorded as untaken courses. The academic affairs system also retrieves the courses, prerequisite courses, and subject categories of the student's major.

[0050] It should be noted that according to the general teaching management regulations of Chinese universities, the courses for freshmen in the first semester are usually arranged by the school. Therefore, the students to be tested will start to choose courses from the second semester of their freshman year.

[0051] Step S2: Based on the courses of the major of the student to be tested, a course elective map is constructed with courses as nodes and prerequisite relationships between courses as relationships; based on the prerequisite relationship between the current elective course and the courses already taken, suspected abnormal courses are selected from the current elective courses.

[0052] Certain courses must be taken after completing the prerequisite courses that serve as their foundation. This ensures that students learn in a reasonable order and avoid learning difficulties due to lack of basic knowledge. Therefore, the course selection map is determined based on the prerequisite relationship between courses.

[0053] In the embodiment of the present invention, the direction of the edge between two nodes in the course selection graph is from the node corresponding to the prerequisite course of each course to the node corresponding to each course. Figure 2 A partial schematic diagram of a course selection map provided by an embodiment of the present invention is shown as follows: Figure 2 As shown, Figure 2 All nodes in the figure represent the courses of the student's major. Gray nodes A, B, and D represent courses that have been taken. Gray nodes G, H, I, and U represent current elective courses. White nodes C, E, K, T, R, and Y represent courses in the student's major that have not been taken in the current semester.

[0054] It should be noted that the course selection graph is a directed graph and does not have directed cycles; since there is no prerequisite relationship between the current elective courses, there are no edges between the current elective courses in the course selection graph.

[0055] In an embodiment of the present invention, a method for obtaining suspected abnormal courses includes: deleting other nodes in the course elective graph except for the nodes corresponding to the courses taken by the student to be tested and the current elective courses, as well as all edges associated with other nodes, and recording the remaining graph as the course selection path graph of the student to be tested; obtaining the prerequisite courses for each course; if each current elective course of the student to be tested does not have a prerequisite course corresponding to the current elective course in the course corresponding to the predecessor node of the corresponding node in the course selection path graph, then each current elective course is recorded as a suspected abnormal course.

[0056] Figure 3 A partial schematic diagram of a course selection path diagram provided by one embodiment of the present invention is provided. Figure 3 Each graph structure in the graph represents a course selection path, which reflects the learning path and interests of the students being tested. Some courses can only be taken after completing the prerequisite courses that serve as their foundation. If the prerequisite courses of the current elective course do not exist in the courses already taken, it means that the current elective course does not meet the learning requirements. The current elective course is a possible mistake during course selection and is recorded as a suspected abnormal course.

[0057] It should be noted that there may be multiple course selection path graphs and a course selection path graph may consist of only one node; the current elective course has a corresponding node in only one course selection path graph.

[0058] Step S3: Select the actual abnormal courses from the suspected abnormal courses based on the elective status of each suspected abnormal course by graduates who participated in the competition in which the tested students participated, and whether each suspected abnormal course belongs to the same subject category as the courses already taken and the current elective courses.

[0059] Some universities will provide green passes for students who excel in competitions, meaning that students do not have to follow the prerequisites when choosing courses that are more relevant to competitions, making their course selection path more in line with their personal strengths rather than a one-size-fits-all restriction; limiting students' blind course selection through subject interests effectively balances academic rigor and interest development, and prevents waste of teaching resources caused by blind course selection.

[0060] Courses chosen for competitions or personal interests do not require a prerequisite relationship. The selection of suspected anomalous courses by graduates who participated in the same competition as the student under test reflects the relevance of the suspected anomalous course to the competition. The fact that the suspected anomalous course belongs to the same subject category as a course already taken reflects the student's interest in the suspected anomalous course. The fact that the suspected anomalous course belongs to the same subject category as a currently selected course reflects the likelihood that the suspected anomalous course is a major course. By combining these factors to analyze the degree of anomalousness of the suspected anomalous course, the anomalous course selection data, namely the actual anomalous courses, are selected.

[0061] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining actual abnormal courses includes: obtaining competitions participated in by the student to be tested and each graduate; selecting graduates who have participated in all competitions participated in by the student to be tested before the current semester as students to be analyzed, and obtaining the competition relevance of each suspected abnormal course by taking the ratio of the number of students to be analyzed who have taken each suspected abnormal course to the total number of students to be analyzed; recording the proportion of the courses taken by the student to be tested that have the same subject category as the subject category of each suspected abnormal course as the subject interest of each suspected abnormal course; recording the proportion of the current elective courses of the student to be tested that have the same subject category as the subject category of each suspected abnormal course as the course relevance of each suspected abnormal course; obtaining the abnormality of each suspected abnormal course based on the competition relevance, subject interest and course relevance; and selecting the actual abnormal courses among the suspected abnormal courses based on the abnormality.

[0062] Some universities or colleges may offer competition training courses or guidance to students participating in competitions. These courses may be closely related to the students' majors. Some students may choose courses related to competitions. The more students choose these courses, the greater the relevance of the suspected anomalous course to the competition. Because students participating in competitions already possess the relevant knowledge of the suspected anomalous course, the less likely they are to take the course if they haven't taken the prerequisite courses, making the suspected anomalous course less anomalous. It's known that if a course is of interest to the student being tested, they may not take it based on the required sequence of prerequisite courses. The more courses in the student's historical elective history (i.e., the number of courses in the subject category of the suspected anomalous course) that appear in the student's course list, the greater their interest in the subject category, indicating a higher degree of subject interest. The less likely they are to take the course based on the required sequence of prerequisite courses, and the less anomalous the suspected anomalous course is. It's known that most current elective courses are professional courses, which require a foundation in prerequisite courses. The greater the number of current elective courses that fall into the same subject category as the suspected anomalous course, the greater the correlation between the suspected anomalous course and the current elective, the greater the likelihood that the suspected anomalous course is a professional course, and the greater the degree of anomalousness of the suspected anomalous course. Therefore, competition relevance and subject interest are both negatively correlated with anomalousness, while course relevance is positively correlated with anomalousness.

[0063] In this embodiment of the present invention, the product of competition relevance and subject interest is negatively correlated, and the mapping result is normalized by the product of course relevance to obtain the abnormality degree of each suspected abnormal course. In this embodiment of the present invention, other basic mathematical operations can also be used to construct the correlation between competition relevance, subject interest, course relevance, and abnormality, which are not limited or detailed here.

[0064] It should be noted that in the embodiment of the present invention, the Norm function is used for normalization processing, and the reciprocal is taken for negative correlation mapping. In the embodiment of the present invention, normalization methods such as function transformation and decimal calibration normalization can also be selected, and negative correlation mapping methods such as taking negative numbers and using the opposite of the numerical value as an exponent with a natural constant as the base can also be selected, which are not limited here.

[0065] Since the suspected abnormal course with a larger abnormality degree is more likely to be a wrong course selected by the tested student, the suspected abnormal course with an abnormality degree greater than the preset abnormality threshold is regarded as the actual abnormal course.

[0066] In one implementation of the embodiment of the present invention, the preset abnormality threshold is set to 0.7.

[0067] It should be noted that compulsory professional courses are courses that students must take to develop their professional knowledge and skills, and are not elective courses based on personal interests. In this embodiment of the present invention, if the suspected abnormal course is a compulsory professional course for the major of the student to be tested, the interest level of the suspected abnormal course is set to a constant 0.

[0068] Step S4: Based on the association between the currently untaken courses and the courses corresponding to the nodes in the course selection graph, the recommended courses for the actual abnormal courses are determined.

[0069] Due to professional requirements, the courses taken by the student under test and graduates of the same major each semester partially overlap. The currently untaken courses represent the graduates' preferred courses for each semester. From these preferred courses, the student under test can select courses that meet their knowledge base and learning needs. The association between the currently untaken courses and the corresponding courses in the course selection graph reflects the consistency of the student under test's learning path. Based on this, the system recommends courses that meet the student's learning needs to replace the actual abnormal courses, thus correcting the abnormal course selection data.

[0070] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining recommended courses includes: for each course selection path graph, determining whether there is a node in the course selection path graph that has a prerequisite relationship with each currently untaken course; if so, recording the node as an associated node; when the course corresponding to the associated node is a prerequisite course of the currently untaken course, adding an edge from the associated node to the currently untaken course; when the currently untaken course is a prerequisite course of the course corresponding to the associated node, adding an edge from the currently untaken course to the associated node; otherwise, each currently untaken course cannot be added to the course selection path graph; recording the graph when all currently untaken courses are added to the course selection path graph as an extended path graph; if the node of the currently untaken course in the extended path graph is not connected to the node corresponding to the actual abnormal course, recording the extended path graph as an analysis graph of the currently untaken course; counting the number of analysis graphs of the currently untaken courses in all extended path graphs, and recording it as the recommended value of the currently untaken course; selecting the currently untaken courses corresponding to the largest n recommendation values ​​from all currently untaken courses as the recommended courses for the actual abnormal courses of the student to be tested.

[0071] The expanded path diagram further considers courses that have prerequisite relationships with the courses corresponding to the nodes in the diagram, providing a more comprehensive picture of the student's learning needs and potential interests. The connections between currently untaken courses and nodes in the course selection path diagram reflect the correlation between these courses. If a currently untaken course frequently appears in multiple expanded path diagrams and is connected to multiple associated nodes, it indicates a strong correlation between the currently untaken course and the student's learning path. Therefore, the more analysis diagrams for currently untaken courses, the stronger the correlation between the currently untaken course and the student's learning path, the more consistent the paths, the greater the likelihood that the currently untaken course meets the student's learning needs, and the more strongly the currently untaken course is recommended to the student.

[0072] In this embodiment of the present invention, n is equal to the actual number of abnormal courses. It should be noted that due to the similar course durations, the number of courses enrolled by different students in each semester is relatively similar. The actual number of abnormal courses is a low-probability event. Furthermore, the number of currently untaken courses includes all courses that graduates did not enroll in the current semester. Therefore, the number of currently untaken courses should be greater than the actual number of abnormal courses.

[0073] Some universities will provide green passes to students who excel in competitions. This means that students do not need to follow prerequisites when choosing courses that are highly relevant to competitions, allowing their course selection path to better suit their personal strengths rather than being subject to a one-size-fits-all restriction. Limiting students' blind course selection based on subject interests effectively balances academic rigor with interest development, preventing the waste of teaching resources caused by blind course selection. This solution provides flexibility for personalized course selection while ensuring academic foundations by quantifying indicators such as the relevance of courses to competitions and subject interests. Once the academic affairs system detects an actual abnormal course, it will send a notification to the student being tested through the student management system, reminding the student of the actual abnormal course selected, and push relevant recommended courses. The student is required to modify the course selection of the actual abnormal course, completing the data cleansing of student course selection data on the smart campus platform. This solution is reasonable in an education system that focuses on cultivating core professional skills while taking into account competitions and the development of in-depth interests.

[0074] So far, the present invention is completed.

[0075] Example 2:

[0076] This invention proposes a data cleaning system for a smart campus platform. Figure 4 , which shows a system structure diagram of a data cleaning system for a smart campus platform provided by one embodiment of the present invention, the system includes:

[0077] The data collection module 510 is used to obtain the courses of the major of the student to be tested and the subject categories to which they belong, as well as the courses already taken, the current elective courses and the current untaken courses of the student to be tested;

[0078] The suspected abnormal course screening module 520 is used to construct a course selection map based on the courses of the major of the tested student, with courses as nodes and prerequisite relationships between courses as relationships; based on the prerequisite relationships between the current elective courses and the courses already taken, select suspected abnormal courses among the current elective courses;

[0079] The actual abnormal course screening module 530 is used to select the actual abnormal courses among the suspected abnormal courses based on the elective status of each suspected abnormal course by graduates who participated in the competition in which the tested student participated, and whether each suspected abnormal course belongs to the same subject category as the courses already taken and the current elective courses;

[0080] The course recommendation module 540 is used to determine the recommended courses for the actual abnormal courses based on the association between the current untaken courses and the courses corresponding to the nodes in the course selection map.

[0081] It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the data cleaning system for a smart campus platform provided in the above embodiment and the data cleaning method embodiment for a smart campus platform are of the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0082] Example 5:

[0083] Figure 5 A computer device diagram of a data cleaning device for a smart campus platform provided by an embodiment of the present invention. For example, Figure 5 As shown, the computer device includes: a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602, wherein when the processor 602 executes the computer program 603, the computer device can execute any one of the data cleaning methods for the smart campus platform introduced above.

[0084] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a data cleaning method for a smart campus platform provided in an embodiment of the present application.

[0085] In this embodiment, the device can be divided into functional modules based on the above-described method examples. For example, each functional module can be mapped to a specific functional module, or two or more functions can be integrated into a single processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used.

[0086] It should be understood that the device provided in this embodiment is used to execute the above-mentioned data cleaning method of the smart campus platform, and therefore can achieve the same effect as the above-mentioned implementation method.

[0087] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the operation of the device. The storage module may be used to support the device in executing mutual program codes, etc.

[0088] The processing module may be a processor or controller that implements or executes various exemplary logic blocks, modules, and circuits disclosed herein. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processing (DSP) and a microprocessor, and the storage module may be a memory.

[0089] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0091] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A data cleaning method for a smart campus platform, characterized in that: The method includes: Obtain the courses and subject categories of the major of the student to be tested, as well as the courses already taken, current elective courses and current untaken courses of the student to be tested; Based on the courses of the major of the student to be tested, a course elective map is constructed with courses as nodes and prerequisite relationships between courses as relationships; based on the prerequisite relationship between the current elective course and the courses already taken, suspected abnormal courses are selected from the current elective courses; Based on the elective status of each suspected abnormal course by graduates who participated in the competition in which the students to be tested participated, and the fact that each suspected abnormal course is in the same subject category as the courses already taken and the current elective courses, the actual abnormal courses among the suspected abnormal courses are selected; Based on the correlation between the current untaken courses and the courses corresponding to the nodes in the course selection map, the recommended courses for the actual abnormal courses are determined.

2. The data cleaning method of a smart campus platform according to claim 1, characterized in that: The selected courses suspected of being abnormal in the current elective courses include: Delete all nodes in the course selection graph except for the nodes corresponding to the courses already taken by the student to be tested and the current elective courses, as well as all edges associated with the other nodes, and record the remaining graph as the course selection path graph of the student to be tested; Obtain the prerequisite courses for each course; if each current elective course of the student to be tested does not have a prerequisite course corresponding to the current elective course in the course corresponding to the predecessor node of the corresponding node in the course selection path graph, then each current elective course is recorded as a suspected abnormal course.

3. The data cleaning method of a smart campus platform according to claim 1, characterized in that: The selection of actual abnormal courses from the suspected abnormal courses includes: Obtain the competitions participated by the students to be tested and each graduate; select graduates who have participated in all competitions participated by the students to be tested before the current semester as students to be analyzed, and calculate the ratio of the number of students to be analyzed who have taken each suspected abnormal course to the total number of students to be analyzed to obtain the competition relevance of each suspected abnormal course; The proportion of the subjects of the students being tested that are in the same subject category as each suspected abnormal course is recorded as the subject interest level of each suspected abnormal course; The proportion of the current elective courses of the tested students that belong to the same subject category as each suspected abnormal course is recorded as the course correlation degree of each suspected abnormal course; According to the competition relevance, the subject interest and the course association, the abnormality of each suspected abnormal course is obtained; and based on the abnormality, an actual abnormal course among the suspected abnormal courses is selected.

4. The data cleaning method of a smart campus platform according to claim 2, characterized in that: The process of determining the recommended courses for the actual abnormal courses based on the correlation between the currently untaken courses and the courses corresponding to the nodes in the course selection map includes: For each of the course selection path graphs, determine whether there is a node in the course selection path graph that has a prerequisite relationship with each currently untaken course. If so, record the node as an associated node. When the course corresponding to the associated node is a prerequisite course for the currently untaken course, add an edge from the associated node to the currently untaken course. When the currently untaken course is a prerequisite course for the course corresponding to the associated node, add an edge from the currently untaken course to the associated node. Otherwise, each currently untaken course cannot be added to the course selection path graph. The graph when all currently untaken courses are added to the course selection path graph is called the extended path graph; If the node of the currently untaken course in the extended path graph is not connected to the node corresponding to the actual abnormal course, the extended path graph is recorded as the analysis graph of the currently untaken course; the number of analysis graphs of the currently untaken course in all extended path graphs is counted and recorded as the recommended value of the currently untaken course; The n currently untaken courses corresponding to the largest recommendation values ​​are selected from all currently untaken courses as the recommended courses for the actual abnormal courses of the students to be tested.

5. The data cleaning method of a smart campus platform according to claim 3 is characterized in that: Obtaining the abnormality degree of each suspected abnormal course includes: A negative correlation mapping is performed on the product of the competition relevance and the subject interest, and the mapping result and the product of the course association are normalized to obtain the abnormality degree of each suspected abnormal course.

6. The data cleaning method of a smart campus platform according to claim 3 is characterized in that: The actual abnormal course is a suspected abnormal course whose abnormality degree is greater than a preset abnormality threshold.

7. The data cleaning method of a smart campus platform according to claim 1, characterized in that: The currently untaken courses are the remaining courses taken by all graduates of the major of the student to be tested in the current semester except the currently selected courses.

8. The data cleaning method of a smart campus platform according to claim 1, characterized in that: There is no prerequisite relationship between the currently untaken courses.

9. The data cleaning method of a smart campus platform according to claim 4, characterized in that: The n is equal to the actual number of abnormal courses.

10. A data cleaning system for a smart campus platform, characterized in that: The system includes: The data collection module is used to obtain the courses of the major of the tested student and the subject category to which they belong, as well as the courses the tested student has taken, the current elective courses and the current courses not taken; The suspected abnormal course screening module is used to construct a course selection map based on the courses of the major of the tested student, with courses as nodes and prerequisite relationships between courses as relationships; based on the prerequisite relationship between the current elective course and the courses already taken, the suspected abnormal courses in the current elective course are selected; The actual abnormal course screening module is used to select the actual abnormal courses among the suspected abnormal courses based on the elective status of each suspected abnormal course by graduates who have participated in the competition in which the tested students participated, and whether each suspected abnormal course belongs to the same subject category as the courses already taken and the current elective courses; The course recommendation module is used to determine the recommended courses for actual abnormal courses based on the association between the current untaken courses and the courses corresponding to the nodes in the course selection graph.

Images