A course resource management method and system for an online learning platform

Abstract

The present invention is applicable to the technical field of online course management, and provides a course resource management method and system for an online learning platform. In the course resource management method, a search and sorting algorithm based on user portrait is used to sort multiple courses corresponding to the search instruction, so that the online learning platform can deeply explore the user's potential interests and provide the search results required by the user according to the user's interests; based on the selection result of the sorted courses by the current logged-in user, the courses and the course clusters corresponding to the courses are assigned and updated at the same time; and when the number of assignment updates reaches a preset value, the course clusters and courses deleted in the course resource library are supplemented according to the assignment update result, and the course resource library is updated, so that the administrator can timely update and manage the course resources of the learning platform, and optimize the management level of the course resource library in the online learning platform.

Description

Technical Field

[0001] The present invention belongs to the technical field of online course management, and in particular relates to a course resource management method and system for an online learning platform. Background Art

[0002] At present, information technology with the Internet as the core has been widely used in the global education field. Internet-based information-based teaching has shown its unique advantages and realized the networked online teaching model, so that the classroom is no longer restricted by time and space. At the same time, it also provides a large number of the latest and richest online learning resources and new interactive communication channels for communication between teachers and students.

[0003] Therefore, with the popularization and in-depth application of the Internet, online learning platforms have become an important way of education and knowledge sharing. However, traditional learning platforms cannot conduct effective data analysis on student behavior data, and administrators cannot timely understand the learning situation of students, and thus cannot timely update and manage the course resources of the learning platform, which will affect the learning effect of students on the learning platform to a certain extent.

[0004] In the related technology, the data of the course resource library is selectively deleted and updated by counting the evaluation feedback of the staff on the course resources of the learning platform:

[0005] On the one hand, it is difficult to collect evaluation feedback results, and different students have different evaluation standards, which are highly subjective. In addition, it is troublesome to compile statistics on the collected results, which makes it inconvenient for administrators to update and manage the course resources of the learning platform in a timely manner, and management is difficult.

[0006] On the other hand, the retrieval system of current learning platforms cannot deeply explore users' potential interests, resulting in search results that cannot truly meet the needs of students. Summary of the invention

[0007] The purpose of the embodiments of the present invention is to provide a course resource management method and system for an online learning platform, aiming to solve the technical problems that the existing online learning platform is not convenient for administrators to timely update and manage the course resources of the learning platform, the management is relatively difficult, and the current learning platform retrieval system is unable to deeply explore the user's potential interests, resulting in the search results cannot truly meet the needs of students.

[0008] To achieve the above object, the present invention provides the following technical solutions.

[0009] In one embodiment of the present invention, a course resource management method for an online learning platform is provided, and the course resource management method comprises the following steps:

[0010] Constructing an online learning platform including a course resource library, wherein the course resource library includes a plurality of course clusters, and the course cluster is used to represent a collection of a plurality of courses of the same type;

[0011] In response to a search instruction of a currently logged-in user on the platform, in a plurality of course clusters matching the currently logged-in user, a plurality of courses corresponding to the search instruction are sorted using a search sorting algorithm based on a user profile, and a plurality of matching courses are displayed on the platform according to the sorting results;

[0012] Based on the selection results of the currently logged-in user for the sorted courses, the selected courses are output on the platform; and according to the user's course selection results, the courses and the course clusters corresponding to the courses are assigned and updated at the same time;

[0013] When the number of assignment updates reaches the preset value, the current assignment results of each course cluster are counted. Based on the current assignment results of the course clusters, the course clusters whose assignment results do not meet the first condition are deleted from the course resource library. The assignment results of each course in the remaining course clusters are counted, and the courses in each course cluster whose assignment results do not meet the second condition are deleted. The course clusters and courses deleted from the course resource library are supplemented, and the course resource library is updated.

[0014] Furthermore, multiple course clusters matching the currently logged-in user are obtained in the following manner:

[0015] Obtain user information of the currently logged-in user, the user information including the user ID;

[0016] Extract the historical behavior information of the current user from the platform log database based on the user ID, and use the historical behavior information to extract the user behavior features;

[0017] Based on user behavior characteristics, multiple required course clusters are matched in the course resource library.

[0018] Furthermore, the step of extracting user behavior features using historical behavior information includes:

[0019] Based on the K-center clustering algorithm, the data of historical behavior information after normalization preprocessing is clustered and analyzed. The similarity of user behavior data is expressed as:

[0020]

[0021] In the formula, and represents two random user behavior data of the same user; i and j represent data labels; Indicates the similarity between two data; N indicates the total amount of user behavior data after extraction; Represents the core elements of data, Indicates the weight of the core elements;

[0022] The data that meets the clustering threshold is clustered, and the data clustering processing is expressed as:

[0023]

[0024] In the formula, L represents the clustered user behavior data cluster; μ represents the clustering threshold;

[0025] Based on the clustering behavior data, the user behavior characteristics of each cluster are extracted, which can be expressed as:

[0026]

[0027] In the formula, X represents the user behavior characteristics; c represents the feature label; T represents the time series characteristics of the data cluster.

[0028] Furthermore, in the step of using a search and ranking algorithm based on user portrait to sort multiple courses corresponding to the search instruction, a user portrait model is established, the association probability between the course vector and the user portrait vector is calculated using the KNN method, and the final PageRank value p is obtained by combining the PageRank algorithm, and the searched multiple courses are sorted according to the p value to obtain a sorting result;

[0029] Among them, the association probability between the course vector and the user portrait vector is expressed as:

[0030]

[0031]

[0032] In the formula, represents the association probability, which is used to characterize the correlation between user interests and courses; p represents the user interest vector; U represents the set of course vectors; A vector representing course i; express The course vector space to which it belongs; represents the nearest neighbor course vector; K represents the total number of courses;

[0033] The final PageRank value p is calculated as follows:

[0034]

[0035]

[0036] In the formula, Represents each course pointing to course p PageRank value; Indicates the course The number of courses pointed to; d represents the damping coefficient, which is used to represent the probability of a user selecting a course; n represents the number of course vectors.

[0037] Furthermore, the step of simultaneously updating the assignment of the course and the course cluster corresponding to the course includes: in response to the user's selection confirmation signal for the current course, performing a depreciation update processing on the attribute assignment of the currently selected and confirmed course; based on the selected and confirmed course, determining the course cluster corresponding to the course, and performing a depreciation update processing on the attribute assignment of the course cluster.

[0038] Furthermore, the step of deleting course clusters whose assignment results do not meet the first condition in the course resource library based on the current assignment results of the course clusters includes: obtaining the current assignment results of each course cluster attribute; comparing each current assignment result with the first threshold value, and determining the course clusters to be deleted based on the comparison results, wherein the course clusters whose current assignment results are greater than the first threshold value are deleted from the course resource library.

[0039] Furthermore, the step of deleting courses in each course cluster whose assignment results do not meet the second condition includes: obtaining the current assignment results of all courses in the remaining course clusters; comparing each current assignment result with the second threshold, and determining the courses to be deleted based on the comparison results, wherein the courses whose current assignment results are greater than the second threshold are deleted from the corresponding course cluster.

[0040] Furthermore, the step of supplementing the deleted course clusters and courses in the course resource library and updating the course resource library includes:

[0041] The information of existing and deleted course clusters in the course resource library is obtained, and the course clusters are re-matched based on the course library outside the online learning platform, wherein the re-matched course clusters are different from the existing and deleted course clusters in the course resource library, and the course clusters of the course resource library are updated with the re-matched course clusters.

[0042] Acquire incomplete course cluster information with course vacancies, re-match courses that match the incomplete course cluster information based on a course library outside the online learning platform, wherein the re-matched courses are different from the deleted courses, and update the incomplete course cluster with the re-matched courses;

[0043] Reassign the attributes of all course clusters and courses in the course resource library to complete the update of the course resource library.

[0044] Another embodiment of the present invention provides a course resource management system for an online learning platform, the course resource management system includes the following modules:

[0045] A platform construction module is used to construct an online learning platform including a course resource library, wherein the course resource library includes a plurality of course clusters, and a course cluster is used to represent a collection of a plurality of courses of the same type;

[0046] The search and sorting module is used for responding to the search instruction of the currently logged-in user on the platform, and sorting the multiple courses corresponding to the search instruction in the multiple course clusters matching the currently logged-in user by using the search and sorting algorithm based on the user portrait, and displaying the multiple matching courses on the platform according to the sorting results;

[0047] The assignment update module is used to output the selected courses in the platform based on the selection results of the currently logged-in user for the sorted courses; and according to the user's course selection results, the course and the course cluster corresponding to the course are assigned and updated at the same time;

[0048] The resource update module is used to count the current assignment results of each course cluster when the number of assignment updates reaches a preset value, delete the course clusters whose assignment results do not meet the first condition in the course resource library based on the current assignment results of the course clusters, and count the assignment results of each course in the remaining course clusters, and delete the courses in each course cluster whose assignment results do not meet the second condition; supplement the course clusters and courses deleted in the course resource library, and update the course resource library.

[0049] Compared with the prior art, the course resource management method and system for the online learning platform provided by the present invention have the following beneficial effects:

[0050] First, in the course resource management method of the present invention, by responding to the search instruction of the currently logged-in user on the platform, in multiple course clusters matching the currently logged-in user, a search and sorting algorithm based on user portrait is used to sort multiple courses corresponding to the search instruction, and multiple matching courses are displayed on the platform according to the sorting results; wherein, in the process of sorting multiple courses corresponding to the search instruction using the search and sorting algorithm based on user portrait, the online learning platform can deeply explore the user's potential interests and provide the user with the search results required according to the user's interests;

[0051] Secondly, the present invention performs a value update on the courses and the course clusters corresponding to the courses at the same time based on the selection results of the currently logged-in user on the sorted courses; and when the number of value updates reaches a preset value, the course clusters and courses deleted from the course resource library are supplemented and the course resource library is updated according to the value update results. Therefore, the present invention performs value updates based on the user's course selection results, so that the online learning platform can identify which courses are more popular, and the administrator can timely update and manage the course resources of the learning platform, thereby optimizing the management level of the course resource library in the online learning platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0053] Figure 1 This is a flow chart of a method for managing course resources on an online learning platform according to the present invention;

[0054] Figure 2 A sub-flow chart of a course resource management method for an online learning platform of the present invention;

[0055] Figure 3 This is a structural block diagram of a course resource management system for an online learning platform of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] In the related technology, the data of the course resource library is selectively deleted and updated through the evaluation feedback of the statisticians on the course resources of the learning platform: on the one hand, the evaluation feedback results are difficult to collect, and the evaluation standards of different students are different, which are highly subjective, and it is also troublesome to compile statistics on the collected results, which makes it inconvenient for administrators to timely update and manage the course resources of the learning platform, and the management is difficult; on the other hand, the current learning platform's retrieval system cannot deeply explore the user's potential interests, resulting in the search results cannot truly meet the needs of students.

[0058] To solve the above problems, the present invention utilizes a search and sorting algorithm based on user portraits to sort multiple courses corresponding to the search instructions. The online learning platform can deeply explore the user's potential interests and provide the search results required by the user based on the user's interests. The online learning platform can further assign values ​​and update the user's course selection results, so that the online learning platform can identify which courses are more popular, and the administrator can timely update and manage the course resources of the learning platform, thereby optimizing the management level of the course resource library in the online learning platform.

[0059] The specific implementation of the course resource management method and system of the online learning platform of the present invention is described in detail below in conjunction with specific embodiments.

[0060] Please refer to Figure 1In one embodiment of the present invention, a course resource management method for an online learning platform is provided, and the course resource management method comprises the following steps:

[0061] S11, constructing an online learning platform including a course resource library, wherein the course resource library includes a plurality of course clusters, and the course cluster is used to represent a collection of a plurality of courses of the same type;

[0062] S12, in response to a search instruction of the currently logged-in user on the platform, in a plurality of course clusters matching the currently logged-in user, a plurality of courses corresponding to the search instruction are sorted using a search sorting algorithm based on a user portrait, and a plurality of matching courses are displayed on the platform according to the sorting results;

[0063] As a preferred embodiment of the present disclosure, multiple course clusters matching the currently logged-in user are obtained in the following manner: obtaining user information of the currently logged-in user, the user information including the user ID; extracting historical behavior information of the current user from the platform log database based on the user ID, and extracting user behavior features using the historical behavior information; matching the required multiple course clusters in the course resource library based on the user behavior features; wherein the step of extracting user behavior features using the historical behavior information includes:

[0064] Based on the K-center clustering algorithm, the data of historical behavior information after normalization preprocessing is clustered and analyzed. The K-center clustering algorithm can effectively process large-scale data and identify the patterns and trends of user behavior. Specifically, the similarity of user behavior data is expressed as:

[0065]

[0066] In the formula, and represents two random user behavior data of the same user; i and j represent data labels; Indicates the similarity between two data; N indicates the total amount of user behavior data after extraction; Represents the core elements of data, Indicates the weight of the core elements;

[0067] The data that meets the clustering threshold is clustered, and the data clustering processing is expressed as:

[0068]

[0069] In the formula, L represents the clustered user behavior data cluster; μ represents the clustering threshold;

[0070] Based on the clustering behavior data, the user behavior characteristics of each cluster are extracted, which can be expressed as:

[0071]

[0072] In the formula, X represents the user behavior characteristics; c represents the feature label; T represents the time series characteristics of the data cluster.

[0073] In addition, in the embodiment of the present invention, in the step of using the search and sorting algorithm based on user portrait to sort the multiple courses corresponding to the search instruction, a user portrait model is established, the KNN method is used to calculate the association probability between the course vector and the user portrait vector, and the PageRank algorithm is combined to obtain the final PageRank value p, and the searched multiple courses are sorted according to the p value to obtain the sorting result;

[0074] The present invention combines the PageRank algorithm, and the online learning platform can dynamically sort the search results according to the importance of the course and the association probability of the user's interest, ensuring that the user sees the most relevant and important courses first; wherein the association probability between the course vector and the user portrait vector is expressed as:

[0075]

[0076]

[0077] In the formula, represents the association probability, which is used to characterize the correlation between user interests and courses; p represents the user interest vector; U represents the set of course vectors; A vector representing course i; express The course vector space to which it belongs; represents the nearest neighbor course vector; K represents the total number of courses;

[0078] The final PageRank value p is calculated as follows:

[0079]

[0080]

[0081] In the formula, Represents each course pointing to course p PageRank value; Indicates the course The number of courses pointed to; d represents the damping coefficient, which is used to represent the probability of a user selecting a course; n represents the number of course vectors;

[0082] Among them, in the course search of the online learning platform, if a course is recommended by many other courses, then its PageRank value will be relatively high; the more courses a course points to, the lower its recommendation weight for each course; the meaning of the recommendation is: if a user is interested in a certain course, other similar courses will be recommended when the user searches for courses on the learning platform.

[0083] The recommendation process may be implemented in the following forms: similarity recommendation between courses, course label classification recommendation, and course popularity recommendation, etc., so that the present invention can not only provide more personalized recommendations, but also enhance the accuracy and relevance of the recommendations.

[0084] Therefore, in the process of sorting multiple courses corresponding to the search instructions based on the search sorting algorithm of the present invention based on user portraits, the online learning platform can deeply explore the user's potential interests and provide the search results required by the user according to the user's interests.

[0085] Please continue to refer to Figure 1 The course resource management method in the embodiment of the present invention further includes the following steps:

[0086] S13, based on the selection result of the currently logged-in user for the sorted courses, the selected courses are output in the platform; and according to the course selection result of the user, the courses and the course clusters corresponding to the courses are assigned and updated at the same time;

[0087] Furthermore, the step of updating the values ​​of the course and the course cluster corresponding to the course at the same time includes: in response to the user's confirmation signal of selecting the current course, performing a decrement update process on the attribute value of the currently selected and confirmed course; determining the course cluster corresponding to the course according to the selected and confirmed course, and performing a decrement update process on the attribute value of the course cluster;

[0088] In the embodiment of the present invention, when the user searches in the learning platform, based on the process of step S12, a course list required by the user is obtained, and the course list can be formed by multiple courses selected from one or more course clusters; wherein, for the course selected by the user, the course is assigned and updated; preferably, the assignment and update in this embodiment adopts the following method:

[0089] For example, the update cycle of the course resource library is when multiple users in the learning platform search 100 times in total, and the initial assignment of each course / course cluster is 100. When the user selects course A1, the assignment of course A1 is updated; if course A1 is selected once, the assignment of course A1 becomes 99, and at the same time, the assignment of course cluster A corresponding to course A1 also becomes 99, and so on.

[0090] S14. When the number of assignment updates reaches a preset value, the current assignment results of each course cluster are counted, and based on the current assignment results of the course cluster, the course clusters whose assignment results do not meet the first condition are deleted from the course resource library, and the assignment results of each course in the remaining course clusters are counted, and the courses whose assignment results do not meet the second condition in each course cluster are deleted; the course clusters and courses deleted from the course resource library are supplemented, and the course resource library is updated;

[0091] In an embodiment of the present invention, the step of deleting the course clusters whose assignment results do not meet the first condition in the course resource library based on the current assignment results of the course clusters includes: obtaining the current assignment results of each course cluster attribute; comparing each current assignment result with the first threshold value, and determining the course clusters to be deleted based on the comparison results, wherein the course clusters whose current assignment results are greater than the first threshold value are deleted from the course resource library;

[0092] Exemplarily, in this embodiment, the step of determining the course cluster to be deleted based on the comparison result includes: for the course cluster whose current assignment result is greater than the first threshold, it means that the course cluster is selected less times, and the course cluster with less selection results is deleted.

[0093] Furthermore, the step of deleting courses in each course cluster whose assignment results do not meet the second condition includes: obtaining the current assignment results of all courses in the remaining course clusters; comparing each current assignment result with the second threshold, and determining the courses to be deleted based on the comparison results, wherein the courses whose current assignment results are greater than the second threshold are deleted from the corresponding course cluster.

[0094] Exemplarily, in this embodiment, the step of determining the courses to be deleted based on the comparison results includes: for courses whose current assignment results are greater than a first threshold, it means that the course has been selected less times, and the courses with fewer selection results are deleted.

[0095] For further information, please refer to Figure 2 In a preferred embodiment of the present disclosure, the step of supplementing the course clusters and courses deleted from the course resource library and updating the course resource library includes:

[0096] S21: obtaining information of existing and deleted course clusters in the course resource library, and re-matching course clusters based on course libraries outside the online learning platform, wherein the re-matched course clusters are different from the existing and deleted course clusters in the course resource library, and updating the course clusters in the course resource library with the re-matched course clusters;

[0097] S22: obtaining incomplete course cluster information with course vacancies, re-matching courses that match the incomplete course cluster information based on a course library outside the online learning platform, wherein the re-matched courses are different from the deleted courses, and updating the incomplete course cluster with the re-matched courses;

[0098] S23: Reassign the attributes of all course clusters and courses in the course resource library to complete the update of the course resource library.

[0099] The present invention performs a value update on the courses and the course clusters corresponding to the courses at the same time based on the selection results of the currently logged-in user on the sorted courses; and when the number of value updates reaches a preset value, the course clusters and courses deleted from the course resource library are supplemented according to the value update results, and the course resource library is updated. Therefore, the present invention performs value updates based on the user's course selection results, so that the online learning platform can identify which courses are more popular, and the administrator can timely update and manage the course resources of the learning platform, thereby optimizing the management level of the course resource library in the online learning platform.

[0100] Please refer to Figure 3 In another embodiment of the present invention, a course resource management system for an online learning platform is provided, and the course resource management system includes the following modules:

[0101] A platform construction module 31 is used to construct an online learning platform including a course resource library, wherein the course resource library includes a plurality of course clusters, and a course cluster is used to represent a collection of a plurality of courses of the same type;

[0102] The search sorting module 32 is used for responding to the search instruction of the currently logged-in user on the platform, sorting the multiple courses corresponding to the search instruction in the multiple course clusters matching the currently logged-in user using the search sorting algorithm based on the user portrait, and displaying the multiple matching courses on the platform according to the sorting results;

[0103] The assignment update module 33 is used to output the selected courses in the platform based on the selection result of the currently logged-in user on the sorted courses; and according to the user's course selection result, the course and the course cluster corresponding to the course are assigned and updated at the same time;

[0104] The resource update module 34 is used to count the current assignment results of each course cluster when the number of assignment updates reaches a preset value, delete the course clusters whose assignment results do not meet the first condition in the course resource library based on the current assignment results of the course clusters, and count the assignment results of each course in the remaining course clusters, and delete the courses in each course cluster whose assignment results do not meet the second condition; supplement the course clusters and courses deleted in the course resource library, and update the course resource library.

[0105] Furthermore, another embodiment of the present invention provides a computer device, which includes a memory and a processor, the memory stores a computer program executable by the processor, and the processor implements the course resource management method of the online learning platform provided in the above embodiment when executing the computer program.

[0106] Furthermore, another embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is read and executed, the course resource management method of the online learning platform provided in the above embodiment is implemented.

[0107] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0109] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0110] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a memory and includes several requests to enable a computer device (which can be a personal computer, server or network device, etc., specifically a processor in a computer device) to perform some or all steps of the method described in each embodiment of the present invention.

[0111] In the embodiments provided by the present invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0112] A person skilled in the art can understand that part or all of the steps in the various methods of the embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0113] The course resource management method and system of the online learning platform disclosed in the embodiment of the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A course resource management method for an online learning platform, characterized in that: The course resource management method includes the following steps: Constructing an online learning platform including a course resource library, wherein the course resource library includes a plurality of course clusters, and the course cluster is used to represent a collection of a plurality of courses of the same type; In response to a search instruction of a currently logged-in user on the platform, in a plurality of course clusters matching the currently logged-in user, a plurality of courses corresponding to the search instruction are sorted using a search sorting algorithm based on a user profile, and a plurality of matching courses are displayed on the platform according to the sorting results; Based on the selection result of the currently logged-in user on the sorted courses, the selected courses are output on the platform; and according to the user's course selection result, the courses and the course clusters corresponding to the courses are assigned and updated at the same time; When the number of assignment updates reaches a preset value, the current assignment results of each course cluster are counted, and based on the current assignment results of the course cluster, the course clusters whose assignment results do not meet the first condition are deleted from the course resource library, and the assignment results of each course in the remaining course clusters are counted, and the courses whose assignment results do not meet the second condition in each course cluster are deleted; the course clusters and courses deleted from the course resource library are supplemented, and the course resource library is updated; Multiple course clusters matching the currently logged in user are obtained in the following way: Obtain user information of the currently logged-in user, the user information including the user ID; Extract the historical behavior information of the current user from the platform log database based on the user ID, and use the historical behavior information to extract the user behavior features; Based on user behavior characteristics, multiple required course clusters are matched in the course resource library; The step of extracting user behavior features using historical behavior information includes: Based on the K-center clustering algorithm, the data of historical behavior information after normalization preprocessing is clustered and analyzed. The similarity of user behavior data is expressed as: ； In the formula, and represents two random user behavior data of the same user; i and j represent data labels; Indicates the similarity between two data; N indicates the total amount of user behavior data after extraction; Represents the core elements of data, Indicates the weight of the core elements; The data that meets the clustering threshold is clustered, and the data clustering processing is expressed as: ； In the formula, L represents the clustered user behavior data cluster; μ represents the clustering threshold; Based on the clustering behavior data, the user behavior characteristics of each cluster are extracted, which can be expressed as: ； In the formula, X represents the user behavior characteristics; c represents the feature label; T represents the time series characteristics of the data cluster; In the step of using a search and sorting algorithm based on user portrait to sort multiple courses corresponding to the search instruction, a user portrait model is established, the association probability between the course vector and the user portrait vector is calculated using the KNN method, the final PageRank value is obtained by combining the PageRank algorithm, and the searched multiple courses are sorted according to the PageRank value to obtain a sorting result; The association probability between the course vector and the user portrait vector is expressed as: ； ； In the formula, represents the association probability, which is used to characterize the correlation between user interests and courses; p represents the user interest vector; U represents the set of course vectors; A vector representing course i; express The course vector space to which it belongs; represents the nearest neighbor course vector; K represents the total number of courses; The final PageRank value is calculated as follows: ； ； In the formula, Indicates each course PageRank value; Indicates the course The number of courses pointed to; d represents the damping coefficient, which is used to represent the probability of a user selecting a course; n represents the number of course vectors.

2. The course resource management method of the online learning platform according to claim 1, characterized in that: The step of simultaneously updating the assignment of the course and the course cluster corresponding to the course includes: in response to the user's confirmation signal for the current course selection, updating the attribute assignment of the currently selected and confirmed course by depreciating the value; determining the course cluster corresponding to the course based on the selected and confirmed course, and updating the attribute assignment of the course cluster by depreciating the value.

3. The course resource management method of the online learning platform according to claim 2, characterized in that: The step of deleting the course clusters whose assignment results do not meet the first condition in the course resource library based on the current assignment results of the course clusters includes: obtaining the current assignment result of each course cluster attribute; comparing each current assignment result with the first threshold value, and determining the course clusters to be deleted based on the comparison results, wherein the course clusters whose current assignment results are greater than the first threshold value are deleted from the course resource library.

4. The course resource management method of the online learning platform according to claim 3 is characterized in that: The step of deleting courses in each course cluster whose assignment results do not meet the second condition includes: obtaining the current assignment results of all courses in the remaining course clusters; comparing each current assignment result with the second threshold value, and determining the courses to be deleted based on the comparison result, wherein the courses whose current assignment results are greater than the second threshold value are deleted from the corresponding course cluster.

5. The course resource management method of the online learning platform according to claim 4 is characterized in that: The step of supplementing the course clusters and courses deleted from the course resource library and updating the course resource library includes: Obtaining information on existing and deleted course clusters in the course resource library, re-matching course clusters based on course libraries outside the online learning platform, wherein the re-matched course clusters are different from both existing and deleted course clusters in the course resource library, and updating the course clusters in the course resource library with the re-matched course clusters; obtaining information on incomplete course clusters with course vacancies, and re-matching courses that are compatible with the incomplete course cluster information based on course libraries outside the online learning platform, wherein the re-matched courses are different from the deleted courses, and updating the incomplete course clusters with the re-matched courses; Reassign the attributes of all course clusters and courses in the course resource library to complete the update of the course resource library.

6. A system for implementing the course resource management method of an online learning platform as claimed in any one of claims 1 to 5, characterized in that: The system includes the following modules: A platform construction module is used to construct an online learning platform including a course resource library, wherein the course resource library includes a plurality of course clusters, and a course cluster is used to represent a collection of a plurality of courses of the same type; The search and sorting module is used for responding to the search instruction of the currently logged-in user on the platform, and sorting the multiple courses corresponding to the search instruction in the multiple course clusters matching the currently logged-in user by using the search and sorting algorithm based on the user portrait, and displaying the multiple matching courses on the platform according to the sorting results; The assignment update module is used to output the selected courses in the platform based on the selection results of the currently logged-in user for the sorted courses; and to perform an assignment update on the courses and the course clusters corresponding to the courses at the same time according to the course selection results of the user; The resource update module is used to count the current assignment results of each course cluster when the number of assignment updates reaches a preset value, delete the course clusters whose assignment results do not meet the first condition in the course resource library based on the current assignment results of the course clusters, and count the assignment results of each course in the remaining course clusters, and delete the courses in each course cluster whose assignment results do not meet the second condition; supplement the course clusters and courses deleted in the course resource library, and update the course resource library.

Images