Data cleaning method and system for smart campus platform

Abstract

The invention relates to the technical field of network course selection, in particular to a data cleaning method and system for an intelligent campus platform. The method comprises the following steps: constructing a course selection map based on courses of a specialty to which a to-be-tested student belongs, and determining suspected abnormal courses based on a pre-repair relationship between a current selection course and a repaired course; selecting actual abnormal courses in the suspected abnormal courses according to the selection and repair conditions of the graduates participating in the competition on the suspected abnormal courses and the condition that the suspected abnormal courses are the same as the subject categories to which the repaired courses and the current selection and repair courses belong; and determining a recommended course of the actual abnormal course based on the association condition of the current uncorrected course and the course corresponding to the node in the course selection map. According to the method, the abnormal degree of the current selected course is comprehensively analyzed according to the personal hobbies and interests of the students and the competition participation condition, the abnormal course screening accuracy is improved, and the data cleaning effect of the course selection data of the smart campus platform is improved.

Description

Technical Field

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

[0002] According to the general teaching management regulations of Chinese universities, the courses for freshmen in the first semester are usually arranged by the school uniformly. Students usually need to select courses in advance in the student management system of the smart campus platform before each subsequent semester. In institutions that emphasize professional depth and structured cultivation, such as engineering institutions, students are required to have corresponding knowledge bases for the selected courses. Due to the insufficient understanding of students about the course content, prerequisite requirements, and their own learning progress, some students may misselect courses, reducing the learning effect of students and wasting teaching resources, and thus affecting the school's teaching plan and resource allocation. Identifying misselected courses from the courses selected by students is of great significance for improving the execution efficiency of the teaching plan and optimizing resource allocation.

[0003] Certain courses must be selected after completing the prerequisite courses that are the basis for them to avoid learning difficulties due to lack of basic knowledge. By judging whether the prerequisite courses of the selected courses after the students complete course selection have been selected, the abnormally selected courses are determined. However, due to the personal interests and hobbies of students and their participation in competitions, etc., students can choose courses without following the prerequisite relationship between courses, making the misselected courses determined based on the prerequisite relationship between courses inaccurate, resulting in poor data cleaning effect of the course selection data on the smart campus platform. Summary of the Invention

[0004] In order to solve the technical problem that the misselected courses are inaccurately selected due to the course selection situation where personal interests and hobbies and participation in competitions do not need to follow 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, and the specific 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, and the method includes:

[0006] Obtain the courses of the major to which the student to be tested belongs and the subject categories to which they belong, as well as the courses already taken, the currently selected courses, and the courses not yet taken by the student to be tested;

[0007] Construct a course selection graph with courses as nodes and the prerequisite relationship between courses as the relationship based on the courses of the major to which the student to be tested belongs; select the suspected abnormal courses among the currently selected courses based on the prerequisite relationship between the currently selected courses and the courses already taken;

[0008] Select the actual abnormal courses among the suspected abnormal courses according to the elective situations of each suspected abnormal course by the graduates who participated in the competitions that the students to be tested participated in, and according to the same subject categories of each suspected abnormal course with the completed courses and the currently elective courses respectively.

[0009] Based on the association between the currently uncompleted courses and the courses corresponding to the nodes in the course elective graph, determine the recommended courses for the actual abnormal courses.

[0010] Further, the selection of the suspected abnormal courses among the currently elective courses includes:

[0011] Delete other nodes in the course elective graph except the nodes corresponding to the completed courses and the currently elective courses of the students to be tested, and all edges associated with the other nodes, and denote the remaining graph as the course selection path graph of the students to be tested.

[0012] Obtain the prerequisite courses for each course; if there is no prerequisite course corresponding to the currently elective course in the courses corresponding to the predecessor nodes of the nodes corresponding to the currently elective courses of the students to be tested, then mark each currently elective course as a suspected abnormal course.

[0013] Further, the selection of the actual abnormal courses among the suspected abnormal courses includes:

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

[0015] Denote the proportion of the completed courses in the same subject category as each suspected abnormal course among the completed courses of the students to be tested as the subject interest degree of each suspected abnormal course.

[0016] Denote the proportion of the currently elective courses in the same subject category as each suspected abnormal course among the currently elective courses of the students to be tested as the course association degree of each suspected abnormal course.

[0017] According to the competition relevance, the subject interest degree and the course association degree, obtain the abnormality degree of each suspected abnormal course; select the actual abnormal courses among the suspected abnormal courses based on the abnormality degree.

[0018] Further, the determination of the recommended courses for the actual abnormal courses based on the association between the currently uncompleted courses and the courses corresponding to the nodes in the course elective graph includes:

[0019] For each of the course selection path diagrams, determine whether there are nodes in the course selection path diagram that have a prerequisite relationship with each currently uncompleted course. If so, mark the nodes as associated nodes. When the course corresponding to the associated node is a prerequisite course of the currently uncompleted course, add an edge from the associated node to the currently uncompleted course; when the currently uncompleted course is a prerequisite course of the course corresponding to the associated node, add an edge from the currently uncompleted course to the associated node; otherwise, each currently uncompleted course cannot be added to the course selection path diagram;

[0020] The diagram when all currently uncompleted courses are added to the course selection path diagram is denoted as the extended path diagram;

[0021] If the nodes of the currently uncompleted courses existing in the extended path diagram are not connected to the nodes corresponding to the actual abnormal courses, then denote the extended path diagram as the analysis diagram of the currently uncompleted courses; count the number of analysis diagrams of the currently uncompleted courses in all extended path diagrams, and denote it as the recommended value of the currently uncompleted courses;

[0022] Select the currently uncompleted courses corresponding to the largest n recommended values from all currently uncompleted courses as the recommended courses for the actual abnormal courses of the to-be-tested students.

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

[0024] Perform a negative correlation mapping on the product of the competition relevance and the subject interest degree, and perform a normalization process on the product of the mapping result and the course correlation degree to obtain the abnormality degree of each suspected abnormal course.

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

[0026] Further, the current elective courses are the remaining courses among the courses elected by all graduates of the major to which the to-be-tested student belongs in the current semester except the current elective courses.

[0027] Further, there is no prerequisite relationship among the currently uncompleted courses.

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

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

[0030] A data collection module, configured to obtain the courses of the major to which the to-be-tested student belongs and their subject categories, as well as the completed courses, current elective courses and currently uncompleted courses of the to-be-tested student;

[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 students, with courses as nodes and prerequisite relationships between courses as relationships; based on the prerequisite relationship between the current elective courses and the courses already taken, select the suspected abnormal courses in the current elective courses;

[0032] The actual abnormal course screening module is used to select the actual abnormal courses among the suspected abnormal courses according to the elective situation of each suspected abnormal course by the graduates who participated in the competition in which the students to be tested participated, and the situation that each suspected abnormal course is in 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 association 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 initially selected based on the prerequisite relationship between the current elective courses and the courses that have been taken; since 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, the specific analysis is 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 the same as the subjects of the taken courses and the current elective courses, and the selection of suspected abnormal courses by the students to be tested is presented in turn. The interest in abnormal courses and the possibility that the suspected abnormal courses are professional courses are analyzed by combining the above factors to analyze the abnormal degree of the suspected abnormal courses, and select the wrong course selection data, that is, the actual abnormal courses, so that the course selection path is more in line with personal expertise and the subject interest is used to limit students from blindly selecting courses, providing flexible space for personalized course selection under the premise of ensuring academic foundation; the association between the current untaken courses and the corresponding courses in the course selection map reflects the consistency of the current untaken courses and the learning path of the students to be tested, and the actual abnormal courses are replaced based on the recommended courses that meet the learning needs of the students to be tested, so as to modify the abnormal course selection data and improve the data cleaning effect of the course selection data of the smart campus platform. This solution is reasonable in an education system that focuses on the cultivation of professional core capabilities and takes into account competition and deep interest development. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

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

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

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

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

[0041] Figure 5 The schematic diagram of a computer device of a data cleaning device for a smart campus platform provided by an embodiment of the present invention. Detailed implementation manners

[0042] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of a data cleaning method and system for a smart campus platform proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0044] The specific scenario targeted by the present invention: cleaning the course selection data of students in the school educational administration system of the smart campus platform to determine the abnormal course selection data existing when students select courses.

[0045] The following specifically describes the specific solutions of a data cleaning method and system for a smart campus platform provided by the present invention in combination with the drawings.

[0046] Embodiment 1:

[0047] The present invention proposes a data cleaning method for a smart campus platform. Please refer to Figure 1 , which shows a flowchart of the steps of a data cleaning method for a smart campus platform provided by an embodiment of the present invention. The method includes:

[0048] Step S1: Obtain the courses of the major to which the student to be tested belongs and their respective subject categories, as well as the courses that the student to be tested has completed, the currently selected courses, and the courses not yet taken.

[0049] College students usually need to select courses in advance before each semester starts. After the course selection is completed, obtain from the database of the educational administration system of the smart campus platform the courses selected by the student to be tested in the current semester and the courses that have been selected during the previous semester from the start of the semester to the current semester, and record them as the currently selected courses and the completed courses in sequence; obtain from the database of the educational administration system the courses selected by the graduates of the major to which the student to be tested belongs in each semester, and record the remaining courses in the courses selected by all graduates in the current semester except the currently selected courses as the courses not yet taken. Obtain from the educational administration system the courses of the major to which the student to be tested belongs, their prerequisite courses, and their respective subject categories.

[0050] It should be noted that according to the general teaching management regulations of Chinese universities, the courses for freshmen in the first semester of their freshman year are usually arranged by the school uniformly, so the student to be tested starts to select courses from the second semester of their freshman year.

[0051] Step S2: Construct a course selection graph with courses as nodes and the prerequisite relationships between courses as edges based on the courses of the major to which the student to be tested belongs; select the suspected abnormal courses among the currently selected courses based on the prerequisite relationships between the currently selected courses and the completed courses.

[0052] Certain courses can only be selected after completing their prerequisite courses as a foundation to ensure that students study in a reasonable order and avoid learning difficulties due to lack of basic knowledge. Therefore, a course selection graph is determined based on the prerequisite relationships between courses.

[0053] In the embodiment of the present invention, the direction of the edge between any 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 is a partial schematic diagram of a course selection graph provided by an embodiment of the present invention. As Figure 2 shown, Figure 2 all the nodes in it represent the courses of the major to which the student to be tested belongs. The gray nodes A, B, and D represent the completed courses, the gray nodes G, H, I, and U represent the currently selected courses, and the white nodes C, E, K, T, R, and Y represent the courses of the major to which the student to be tested belongs that have not been selected in the current semester.

[0054] It should be noted that the course selection graph is a directed graph and there is no directed cycle; since there is no prerequisite relationship among the currently selected courses, there is no edge among the currently selected courses in the course selection graph.

[0055] In an embodiment of the present invention, the method for obtaining suspected abnormal courses includes: deleting other nodes in the course selection graph except the nodes corresponding to the completed courses and the currently selected courses of the student to be tested, and all edges associated with other nodes, and denoting the remaining graph as the course selection path graph of the student to be tested; obtaining the prerequisite courses of each course; if there is no prerequisite course corresponding to the currently selected course among the courses corresponding to the precursor nodes of the nodes corresponding to each currently selected course of the student to be tested in the course selection path graph, then each currently selected course is denoted as a suspected abnormal course.

[0056] Figure 3 It is a partial schematic diagram of a course selection path graph provided by an embodiment of the present invention. Figure 3 Each graph structure in it represents a course selection path graph, and the course selection path graph reflects the learning path and interests of the student to be tested. Some courses can only be selected after completing their prerequisite courses as the foundation. If the prerequisite course of the currently selected course does not exist in the completed courses, it means that the currently selected course does not meet the learning requirements, so the currently selected course is a course that may be misselected during course selection, and is denoted as a suspected abnormal course.

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

[0058] Step S3: According to the selection situations of each suspected abnormal course by the graduates who have participated in the competitions participated by the student to be tested, and the same subject category situations of each suspected abnormal course with the completed courses and the currently selected courses respectively, select the actual abnormal courses among the suspected abnormal courses.

[0059] Some universities will provide green passes for students with outstanding performance in competitions, that is, students can not follow the prerequisite relationship when selecting courses related to the competition to a high degree, making their course selection path more in line with personal specialties, rather than a one-size-fits-all restriction; restricting students from blindly selecting courses through subject interests can effectively balance academic rigor and interest development, and prevent waste of teaching resources caused by blind course selection.

[0060] Elective courses due to competitions or personal interests, etc. do not require prerequisite relationships between courses. The elective situations of graduates who have participated in the competitions that the students to be tested have participated in reflect the degree of correlation between the suspected abnormal courses and the competitions. The situation where the suspected abnormal courses and the completed courses belong to the same subject category reflects the interest of the students to be tested in the suspected abnormal courses. The situation where the suspected abnormal courses and the currently elective courses belong to the same subject category reflects the possibility that the suspected abnormal courses are professional courses. Analyze the degree of abnormality of the suspected abnormal courses based on the above factors, so as to select the abnormal course selection data, that is, the actual abnormal courses.

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

[0062] Some universities or colleges may provide competition training courses or guidance for students participating in competitions, and these courses may be closely related to the knowledge of the majors that the students are studying. Some students may choose courses involving competition-related knowledge. The more students choose a suspected abnormal course involving competition-related knowledge, the greater the relevance between the suspected abnormal course and the competition. Since the students participating in the competition have the relevant knowledge of the suspected abnormal course, the impact of not taking the prerequisite course of the suspected abnormal course on learning this course is smaller, making the abnormal degree of the suspected abnormal course smaller. It is known that if a certain course is a course that the to-be-tested student is interested in, the to-be-tested student may not study based on the order of prerequisite courses; the more courses in the historical elective records of the to-be-tested student, that is, the courses in the completed courses that belong to the subject category of the suspected abnormal course, the greater the interest of the to-be-tested student in this subject category, that is, the greater the subject interest degree, and the smaller the possibility of studying based on the order of prerequisite courses, then the abnormal degree of the suspected abnormal course is smaller. It is known that most of the current elective courses are professional courses, and professional courses require a knowledge foundation of prerequisite courses; if the number of current elective courses belonging to the same subject category as the suspected abnormal course in the current elective courses is larger, it indicates that the correlation degree between the suspected abnormal course and the current elective courses is greater, and the possibility that the suspected abnormal course is a professional course is greater, then the abnormal degree of the suspected abnormal course is greater. Therefore, both the competition relevance and the subject interest degree have a negative correlation with the abnormal degree, and the course correlation degree has a positive correlation with the abnormal degree.

[0063] In an embodiment of the present invention, the product of the competition relevance and the subject interest degree is subjected to a negative correlation mapping, and the product of the mapping result and the course correlation degree is normalized to obtain the abnormal degree of each suspected abnormal course. In an embodiment of the present invention, the correlation relationship between the competition relevance, the subject interest degree, the course correlation degree and the abnormal degree can also be constructed through other basic mathematical operations, which will not be limited and elaborated here.

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

[0065] Since the greater the abnormal degree of a suspected abnormal course, the greater the possibility that it is a wrongly selected course when the to-be-tested student selects courses, the suspected abnormal course with an abnormal degree greater than the preset abnormal threshold is used as the actual abnormal course.

[0066] In an implementation manner of an embodiment of the present invention, the preset abnormal threshold is set to 0.7.

[0067] It should be noted that professional compulsory courses are courses that students must take to cultivate their professional knowledge and skills, and they cannot be selected according to personal interests; in the embodiments of the present invention, if a suspected abnormal course is a professional compulsory course of the major to which the student to be tested belongs, the interest degree of the suspected abnormal course is set to a constant 0.

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

[0069] There is partial overlap in the courses selected by the student to be tested and the graduates of the same major in each semester due to professional requirements. The currently unselected courses are the interest courses of the graduates in each semester. Courses with a knowledge foundation and learning needs for the student to be tested can be selected from these interest courses, that is, the currently unselected courses. The association between the currently unselected courses and the courses corresponding to the nodes in the course selection graph reflects the unity of the currently unselected courses and the learning path of the student to be tested. According to this, courses that meet the learning needs of the student to be tested are recommended to replace the actual abnormal courses, so as to modify the abnormal course selection data.

[0070] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the recommended courses includes: for each course selection path graph, determine whether there is a node in the course selection path graph that has a prerequisite relationship with each currently unselected course. If so, mark the node as an associated node. When the course corresponding to the associated node is a prerequisite course of the currently unselected course, add an edge from the associated node to the currently unselected course; when the currently unselected course is a prerequisite course of the course corresponding to the associated node, add an edge from the currently unselected course to the associated node; if not, each currently unselected course cannot be added to the course selection path graph; the graph when all currently unselected courses are added to the course selection path graph is denoted as the extended path graph; if the nodes of the currently unselected courses existing in the extended path graph are not connected to the nodes corresponding to the actual abnormal courses, denote the extended path graph as the analysis graph of the currently unselected courses; count the number of analysis graphs of the currently unselected courses in all extended path graphs, denoted as the recommended value of the currently unselected courses; select the currently unselected courses corresponding to the largest n recommended values from all currently unselected courses as the recommended courses for the actual abnormal courses of the student to be tested.

[0071] The extended path diagram further considers the courses that have a prerequisite relationship with the courses corresponding to the nodes in the diagram, and more comprehensively depicts the learning needs and potential interests of the students to be tested. The connection between the current untaken courses and the nodes in the course selection path diagram reflects the correlation between these courses. If the current untaken courses frequently appear in multiple extended path diagrams and are connected to multiple associated nodes, it indicates that the current untaken courses have a strong correlation with the learning path of the students to be tested. Therefore, when the number of analysis diagrams of the current untaken courses is more, the correlation between the current untaken courses and the learning path of the students to be tested is stronger and the paths are highly unified, the current untaken courses are more likely to meet the students' learning needs, and the current untaken courses are more recommended to the students to be tested.

[0072] In the 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 duration, the number of courses selected by different people in each semester is relatively close, and the actual abnormal course is a low-probability event. The current untaken courses include all the courses that graduates have not selected in the current semester. Therefore, the current number of untaken courses should be greater than the actual number of abnormal courses.

[0073] Some universities will provide green passes to students who are outstanding in competitions, that is, students do not need to follow the prerequisite relationship when choosing courses that are highly relevant to competitions, so that their course selection path is more in line with their personal strengths, rather than a one-size-fits-all restriction; restrict students from blindly choosing courses by subject interests, effectively balance academic rigor and interest development, and prevent waste of teaching resources caused by blind course selection. This solution provides flexible space for personalized course selection while ensuring academic foundation by quantifying indicators such as the relevance of courses to competitions and subject interests; once the academic affairs system finds actual abnormal courses, it will send a notification to the students to be tested through the student management system to remind the students to be tested of the actual abnormal courses they have chosen, and push relevant recommended courses, requiring the students to be tested to modify the course selection of the actual abnormal courses, and complete the data cleaning of the student course selection data on the smart campus platform. This solution is reasonable in an education system that focuses on the cultivation of professional core capabilities and takes into account competitions and in-depth interest development.

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

[0075] Embodiment 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 an embodiment of the present invention, the system comprising:

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

[0078] The suspected abnormal course screening module 520 is used to construct a course elective graph with courses as nodes and prerequisite relationships between courses based on the courses of the major to which the student to be tested belongs; and select the suspected abnormal courses in the current elective courses based on the prerequisite relationships between the current elective courses and the completed courses.

[0079] The actual abnormal course screening module 530 is used to select the actual abnormal courses among the suspected abnormal courses according to the elective situations of each suspected abnormal course by the graduates who participated in the competitions that the student to be tested participated in, and the same subject category situations of each suspected abnormal course with the completed courses and the current elective courses respectively.

[0080] The course recommendation module 540 is used to determine the recommended courses for the actual abnormal courses based on the association between the currently uncompleted courses and the courses corresponding to the nodes in the course elective graph.

[0081] It should be noted that: for the device provided in the above embodiments, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, a data cleaning system of a smart campus platform and an embodiment of a data cleaning method of a smart campus platform provided in the above embodiments belong to the same concept. For the specific implementation process, please refer to the method embodiments and will not be elaborated here.

[0082] Embodiment 5:

[0083] Figure 5 It is a schematic diagram of a computer device of a data cleaning device of a smart campus platform provided by an embodiment of the present invention. Exemplarily, as Figure 5 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. When the processor 602 executes the computer program 603, the computer device can execute any one of the data cleaning methods of 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. Among them, 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 of a smart campus platform provided by an embodiment of the present application.

[0085] In this embodiment, the device can be divided into functional modules according to the above method examples. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0086] It should be understood that the device provided in this embodiment is used to execute the above data cleaning method of an intelligent campus platform, so the same effect as the above implementation method can be achieved.

[0087] In the case of adopting an integrated unit, the device can include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc.

[0088] Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logical blocks, modules, and circuits included in the disclosure of this application. The processor can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0089] It should be noted that the above sequence of embodiments of the present invention is only for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

[0091] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data cleaning method for a smart campus platform, characterized in that, The method includes: Obtaining the courses of the major to which the student to be tested belongs and their corresponding subject categories, as well as the courses that the student to be tested has already taken, the currently selected courses, and the courses not yet taken; Constructing a course selection graph with courses as nodes and prerequisite relationships between courses as relationships based on the courses of the major to which the student to be tested belongs; selecting suspected abnormal courses among the currently selected courses based on the prerequisite relationships between the currently selected courses and the courses already taken; Selecting the actual abnormal courses among the suspected abnormal courses according to the selection situations of each suspected abnormal course by the graduates who participated in the competitions that the student to be tested participated in, and the same subject category situations of each suspected abnormal course with the courses already taken and the currently selected courses; Determining the recommended courses for the actual abnormal courses based on the association between the courses not yet taken and the courses corresponding to the nodes in the course selection graph; 2. The data cleaning method of a smart campus platform according to claim 1, wherein, The selection of the suspected abnormal courses among the currently selected courses includes: Deleting other nodes in the course selection graph except the nodes corresponding to the courses already taken and the currently selected courses of the student to be tested, and all edges associated with the other nodes, and denoting the remaining graph as the course selection path graph of the student to be tested; Obtaining the prerequisite courses for each course; if there is no prerequisite course corresponding to the currently selected course for the node corresponding to each currently selected course of the student to be tested in the courses corresponding to the precursor nodes of the node in the course selection path graph, then each currently selected course is denoted as a suspected abnormal course; 3. The data cleaning method of an intelligent campus platform according to claim 1, wherein The selection of the actual abnormal courses among the suspected abnormal courses includes: Obtaining the competitions that the student to be tested and each graduate participated in; selecting the graduates who participated in all the competitions that the student to be tested participated in before the current semester as the 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 selected each suspected abnormal course to the total number of students to be analyzed; Denoting the proportion of the courses already taken with the same subject category as each suspected abnormal course among the courses already taken by the student to be tested as the subject interest degree of each suspected abnormal course; Denoting the proportion of the currently selected courses with the same subject category as each suspected abnormal course among the currently selected courses of the student to be tested as the course association degree of each suspected abnormal course; Obtaining the abnormality degree of each suspected abnormal course according to the competition relevance, the subject interest degree, and the course association degree; selecting the actual abnormal courses among the suspected abnormal courses based on the abnormality degree; 4. A data cleaning method for a smart campus platform according to claim 2, characterized in that, The determination of the recommended courses for the actual abnormal courses based on the association between the courses not yet taken and the courses corresponding to the nodes in the course selection graph includes: For each of the course selection path graphs, determining whether there are nodes in the course selection path graph that have a prerequisite relationship with each course not yet taken. If so, denoting the nodes as associated nodes. When the course corresponding to the associated node is the prerequisite course of the course not yet taken, adding an edge from the associated node to the course not yet taken; when the course not yet taken is the prerequisite course of the course corresponding to the associated node, adding an edge from the course not yet taken to the associated node; if not, each course not yet taken cannot be added to the course selection path graph; Denoting the graph when all the courses not yet taken are added to the course selection path graph as the extended path graph; If the nodes of the currently uncompleted courses existing in the extended path diagram are not connected to the corresponding nodes of the actual abnormal courses, then mark the extended path diagram as the analysis diagram of the currently uncompleted courses; count the number of analysis diagrams of the currently uncompleted courses in all extended path diagrams, and denote it as the recommended value of the currently uncompleted courses. Select the currently uncompleted courses corresponding to the largest n recommended values from all currently uncompleted courses as the recommended courses for the actual abnormal courses of the student to be tested.

5. A data cleaning method for a smart campus platform according to claim 3, characterized in that, The obtaining the abnormality degree of each suspected abnormal course includes: Perform a negative correlation mapping on the product of the competition relevance and the subject interest degree, and perform a normalization process on the product of the mapping result and the course relevance degree to obtain the abnormality degree of each suspected abnormal course.

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

7. A data cleaning method for an intelligent campus platform according to claim 1, characterized in that The current elective course is the remaining courses among the courses elected by all graduates of the major to which the student to be tested belongs in the current semester except the current elective course.

8. A data cleaning method for an intelligent campus platform according to claim 1, characterized in that There is no prerequisite relationship among the currently uncompleted courses.

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

10. A data cleaning system for a smart campus platform, characterized in that, The system includes: A data acquisition module, configured to obtain the courses of the major to which the student to be tested belongs and their corresponding subject categories, as well as the completed courses, current elective courses and currently uncompleted courses of the student to be tested. A suspected abnormal course screening module, configured to construct a course elective graph with courses as nodes and the prerequisite relationships between courses as relationships based on the courses of the major to which the student to be tested belongs; select the suspected abnormal courses in the current elective courses based on the prerequisite relationships between the current elective courses and the completed courses. An actual abnormal course screening module, configured to select the actual abnormal courses from the suspected abnormal courses according to the elective situations of each suspected abnormal course by the graduates who have participated in the competitions that the student to be tested has participated in, and the same subject category situations of each suspected abnormal course and the completed courses and the current elective courses respectively. A course recommendation module, configured to determine the recommended courses for the actual abnormal courses based on the association between the currently uncompleted courses and the courses corresponding to the nodes in the course elective graph.

Images