Course recommendation method and system for teaching integrated platform

Abstract

The invention discloses a course recommendation method and system for a teaching integrated platform, and belongs to the technical field of teaching recommendation. The method comprises the following steps: establishing a link between a user port and a course interface, generating an initialized course learning packet set, collecting user learning behaviors to form a behavior chain, verifying a user learning behavior state, evaluating the acceptability of a course learning packet in a user group, and quantifying and displaying a collaborative recommendation degree based on a knowledge point nesting relationship. The corresponding system comprises a port link and course package initialization module, a learning behavior chain processing module and a course recommendation evaluation module. According to the method, accurate curriculum recommendation can be realized, the learning efficiency of the user is improved, the problem that the existing recommendation technology neglects knowledge point association and lacks group acceptance evaluation is solved, and the method is suitable for curriculum recommendation scenes of various teaching integrated platforms.

Description

Technical Field

[0001] This invention relates to the field of teaching recommendation technology, specifically to a course recommendation method and system for an integrated teaching platform. Background Technology

[0002] In the process of digital development in education, integrated teaching platforms have become the core carrier for integrating course resources and supporting blended learning, and their course recommendation functions directly affect users' learning experience and learning outcomes. Currently, the course recommendation technology of mainstream integrated teaching platforms has the following main shortcomings:

[0003] The recommendation logic is simplistic and ignores the connections between knowledge points: Current recommendations are mostly based on users' browsing history or simple interest tags, without considering the nested relationships between theoretical knowledge points within the course (such as the logical connection between "derivative" and "differential" in "advanced mathematics"). This results in recommended courses not matching the user's current learning progress and knowledge reserves, requiring users to additionally filter resources related to the current learning content, wasting learning time.

[0004] The distinction between learning behaviors is blurred, and the identification of needs is inaccurate: Existing technologies do not finely distinguish users' learning behaviors and cannot determine whether users are "directly learning the complete course" (primary need) or "supplementing learning related knowledge points in sub-courses" (secondary need). This can easily lead to "over-recommendation" or "recommendation bias," such as recommending the complete course to users who only need to supplement sub-courses, which increases the user's learning burden.

[0005] Lack of group acceptance assessment leads to unstable recommendation quality: The recommendation process does not consider the overall acceptance of course learning packages among the user group. Some low-quality courses or courses that do not conform to the learning habits of most users may be recommended frequently, which leads to a decrease in users' trust in the platform's recommendations and also reduces the exposure efficiency of high-quality courses.

[0006] The lack of a collaborative recommendation mechanism results in low resource utilization: The platform has not established a collaborative recommendation logic between course learning packages, making it impossible to recommend other courses with complementary or progressive knowledge points based on a user's learning behavior for a particular course. This makes it difficult for high-quality course resources on the platform to form a "closed-loop learning path," leading to insufficient resource utilization.

[0007] Therefore, there is an urgent need for a course recommendation method and system that can combine the nested relationships of knowledge points, accurately identify user learning needs, and evaluate group acceptance to improve the recommendation accuracy and user learning experience of the integrated teaching platform. Summary of the Invention

[0008] The purpose of this invention is to provide a course recommendation method and system for an integrated teaching platform to solve the problems mentioned in the background art.

[0009] To solve the above-mentioned technical problems, the present invention provides the following specific technical solutions:

[0010] A course recommendation system for an integrated teaching platform, comprising: a port linking and course package initialization module, a learning behavior chain processing module, and a course recommendation evaluation module;

[0011] The port link and course package initialization module is used to establish a corresponding link between the user port and the course interface in the integrated teaching platform, so that users can enter the corresponding course for learning through the course interface, and add program comments to the theoretical knowledge points in the course, and generate an initialized course learning package and course learning package set.

[0012] The learning behavior chain processing module is used to record the user's browsing behavior when calling the course learning package through the course interface after obtaining user authorization, form and output the user's learning behavior chain, and use it to uniformly process the course learning package and learning sub-packages. Combined with the user's learning behavior chain, it verifies whether the user's learning behavior status is the main learning behavior status or the auxiliary learning behavior status.

[0013] The course recommendation and evaluation module is used to evaluate the acceptance of a course learning package among users within a fixed learning period based on the behavioral status feedback of different users towards the same course learning package. Based on the acceptance, it determines whether to initiate collaborative recommendation of the course learning package. When collaborative recommendation is initiated, it generates a feature set of user-called learning sub-packages based on the theoretical nesting relationship between course knowledge points, quantifies the collaborative recommendation degree between different course learning packages, and recommends and displays them in the integrated teaching platform according to the collaborative recommendation degree.

[0014] As a preferred embodiment of the present invention, the port linking and course package initialization module includes a port configuration unit and a course package generation unit;

[0015] The port configuration unit is used to configure a unique course interface for each course and a unique user port for each user in the integrated teaching platform, so that users can establish a link with the corresponding course interface through the exclusive port, and mark the correspondence between the sub-courses contained in the course and the theoretical knowledge points, as well as the theoretical nesting relationship between the knowledge points.

[0016] The course package generation unit is used to annotate each theoretical knowledge point in the course, integrate the content of several sub-courses into an initialized course learning package, and the course learning packages together constitute a course learning package set. Each sub-course corresponds to a learning sub-package, and the learning sub-packages are combined to form a course learning package.

[0017] As a preferred embodiment of the present invention, the learning behavior chain processing module includes a learning log recording unit and a behavior chain classification unit;

[0018] The learning log recording unit is used to record the browsing behavior details of the user calling the course learning package through the course interface in real time after the user authorizes it, forming a user learning log. The log content covers the course learning package and learning sub-package called by the user.

[0019] The behavior chain classification unit is used to divide the learning behavior chain into a main learning behavior chain and a secondary learning behavior chain based on the behavior details in the user's learning log: the main learning behavior chain refers to the behavior chain corresponding to the user's browsing behavior of not calling the learning sub-packages with nested knowledge point theories, and the secondary learning behavior chain refers to the behavior chain corresponding to the user's browsing behavior of calling the learning sub-packages with nested knowledge point theories, and forms a main learning behavior chain set and a secondary learning behavior chain set respectively.

[0020] As a preferred embodiment of the present invention, the course recommendation and evaluation module includes an acceptance calculation unit, a recommendation decision unit, a feature set generation unit, and a recommendation display unit;

[0021] The acceptance calculation unit is used to count the number of auxiliary learning behavior states of different users for the same course learning package within a fixed learning period, and calculate the acceptance of the course learning package by combining the total number of users and the overall behavior statistics.

[0022] The recommendation decision unit is used to preset an acceptance threshold and compare the calculated acceptance of the course learning package with the acceptance threshold: if the acceptance of the course learning package is greater than the acceptance threshold, collaborative recommendation is not initiated; if the acceptance of the course learning package is less than or equal to the acceptance threshold, collaborative recommendation is initiated.

[0023] The feature set generation unit is used to collect user behavior data of calling nested learning sub-packages based on the nesting relationship of knowledge point theory after collaborative recommendation is started, and generate a call feature set.

[0024] The recommendation display unit quantifies the collaborative recommendation degree between different course learning packages based on the feature set, and displays the recommended course learning packages and the learning sub-packages corresponding to the feature set in the teaching integration platform in descending order of collaborative recommendation degree.

[0025] A course recommendation method for an integrated teaching platform, comprising the following steps:

[0026] Step S1: Establish a link between the user and the course through the course interface and user port in the integrated teaching platform, so that the user can access the corresponding course for learning through the course interface; generate an initial course learning package by adding program comments to the theoretical knowledge points, and form a course learning package set.

[0027] Step S2: Based on the user's learning behavior of browsing the course learning package through the course interface, generate the user's learning behavior chain;

[0028] Step S3: Based on the learning behavior chain set, verify the user's learning behavior status to obtain the main learning behavior status or the secondary learning behavior status.

[0029] Step S4: Based on the primary or secondary learning status feedback from different users regarding the same course learning package, assess the acceptance of the course learning package among the user group to determine whether to conduct collaborative recommendation of the course learning package;

[0030] Step S5: When performing collaborative recommendation of course learning packages, based on the nesting relationship of knowledge points and theories, generate a call feature set of learning sub-packages that have nesting relationships of knowledge points and theories through the course interface, so as to quantify the collaborative recommendation degree between course learning packages and make recommendations.

[0031] As a preferred embodiment of the present invention, the specific implementation process of step S1 includes:

[0032] The integrated teaching platform sets up course interfaces and user ports, which are used by users to access the corresponding courses for learning through the course interfaces. One course corresponds to one course interface, and one user corresponds to one user port. The courses contain sub-courses of theoretical knowledge points, and one sub-course in the course corresponds to one theoretical knowledge point. There is a nested relationship between the theoretical knowledge points.

[0033] The theoretical knowledge points are annotated with program comments, and an initialized course learning package is generated. Each course learning package contains several sub-courses of theoretical knowledge points, and each sub-course is programmed to form a learning sub-package. The course learning packages are composed of the learning sub-packages to generate a course learning package set.

[0034] As a preferred embodiment of the present invention, the specific implementation process of step S2 includes:

[0035] After user authorization, the learning logs of each user are recorded through the integrated teaching platform. The learning logs record the user's learning behavior of browsing the course learning package by calling the course interface. The user port provides feedback on the corresponding user's learning behavior to generate a user's learning behavior chain.

[0036] The learning behaviors include primary learning behaviors and secondary learning behaviors. The primary learning behaviors refer to the learning behavior chain in which the user browses through the course interface without calling the learning sub-packages with nested knowledge point theories, and generate a primary learning behavior chain set, which is equal to the course learning package set. The secondary learning behavior chain refers to the learning behavior chain in which the user browses through the course interface by calling the learning sub-packages with nested knowledge point theories, and generate a secondary learning behavior chain set, which belongs to the primary learning behavior chain set.

[0037] As a preferred embodiment of the present invention, the specific implementation process of step S3 includes:

[0038] The course learning packages and learning sub-packages are uniformly encoded. Based on the encoding information, the set of course learning packages generated corresponding to the i-th course learning package is denoted as U. i ={V j |j∈[1,J]}, where V j Let J represent the j-th learning sub-package, and J represent the total number of learning sub-packages;

[0039] Based on user learning behavior feedback from user ports, the set of learning behavior chains corresponding to the x-th user port under the ith course learning package is denoted as L. w (x, i) = {V j |j∈[1,J]}, where w=1 or 2, if w=1, it represents the main learning behavior state, and L w (x, i) represents the primary learning behavior chain set, and if w = 2, it represents the secondary learning behavior state, and L w (x, i) represents the set of auxiliary learning behavior chains;

[0040] Based on the learning behavior chain set, the user's learning behavior status is verified. If L w (x, i) = U i Then the verification is the primary learning behavior state, if L w (x, i) ≠ U i If so, it is verified as a secondary learning behavior state.

[0041] As a preferred embodiment of the present invention, the specific implementation process of step S4 includes:

[0042] Under a fixed learning period, based on the primary or secondary learning status feedback from different users regarding the same course learning package, the acceptance of the course learning package among the user group is evaluated, and the acceptance of the i-th course learning package is... In the formula, N represents the total number of users, F[·] represents the counting function, and if there exists a set of learning behavior chains L w The learning state corresponding to (x, i) is the secondary learning state, i.e., w = 2, then let If a learning behavior chain set L exists w The learning state corresponding to (x, i) is the primary learning state, i.e., w = 1. Then let...

[0043] A preset acceptance threshold is set. If the acceptance of the i-th course learning package is greater than the acceptance threshold, collaborative recommendation between course learning packages will not be performed. If the acceptance of the i-th course learning package is less than or equal to the acceptance threshold, collaborative recommendation between course learning packages will be performed.

[0044] As a preferred embodiment of the present invention, the specific implementation process of step S5 includes:

[0045] Based on the course learning package set and the auxiliary learning behavior chain set, a call feature set is generated for users calling learning sub-packages with nested knowledge point theories through the course interface.

[0046] Based on the feature set of invocation, the collaborative recommendation degree of course learning packages is quantified. In the formula, e is the code number of the course learning package, and e≠i;

[0047] Based on the order of collaborative recommendation degree from largest to smallest, a sequence of collaboratively recommended course learning packages for the i-th course learning package is generated, and the course learning package sequence and the learning sub-packages corresponding to the called feature set are recommended and displayed on the integrated teaching platform.

[0048] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0049] By introducing the nested relationships of knowledge points, recommendations no longer rely on a single historical record, but are based on the user's current learning needs related to knowledge points. For example, recommending the sub-course "Java Interfaces and Inheritance" to a user learning "Java Object-Oriented Programming" significantly improves the matching accuracy.

[0050] By distinguishing between primary and secondary learning behaviors, it is possible to accurately determine whether a user is engaged in "complete learning" or "supplementary learning." For example, the "SQL Query Optimization" sub-course can be recommended to users who only call the "Database SQL Syntax" sub-package, rather than the complete "Database Principles" course, thus reducing invalid recommendations.

[0051] Based on the group acceptance assessment, high-quality courses with high acceptance (such as courses with an acceptance rate of >80%) can be selected, avoiding the frequent recommendation of low-quality courses, which helps to improve user satisfaction with the platform's recommended resources.

[0052] Through collaborative recommendation mechanisms, courses with complementary knowledge points are formed into "learning paths," such as collaborative recommendations of "Python basics → Python web scraping → data visualization," which drives up the click-through rate of related courses within the platform and significantly improves resource utilization.

[0053] Users do not need to additionally filter courses related to their current learning; the recommended content directly matches their knowledge needs and learning progress, saving users time in searching for resources and helping to improve learning efficiency. Attached Figure Description

[0054] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0055] Figure 1 This is a schematic diagram illustrating the steps of a course recommendation method for an integrated teaching platform according to the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] This invention constructs a course recommendation technology solution for an integrated teaching platform based on a closed-loop logic of "basic linking - behavior collection - status verification - acceptance filtering - collaborative recommendation". The technical idea can be summarized as follows:

[0058] The foundational layer, including port connections and course package initialization, establishes a one-to-one correspondence between "course-interface" and "user-port" to ensure that users can accurately access target courses. At the same time, courses are broken down into sub-courses according to theoretical knowledge points and learning sub-packages are generated, which are then combined into a course learning package set, laying the data foundation for subsequent recommendations based on knowledge point associations.

[0059] Data layer, learning behavior chain collection and classification: Under the premise of user authorization, record the user's browsing behavior of calling course learning packages. By distinguishing between "not calling nested sub-packages" (main behavior) and "calling nested sub-packages" (auxiliary behavior), two types of learning behavior chains are formed to achieve refined identification of user learning needs.

[0060] Processing layer: Learning behavior status verification and acceptance assessment: By uniformly encoding course learning packages and learning sub-packages, the current learning behavior status (primary / secondary) of users is verified to clarify the real needs of users; at the same time, based on the group behavior data within a fixed period, the acceptance of course learning packages is calculated to select high-quality courses that meet the needs of most users and exclude low-quality resources.

[0061] At the application layer, collaborative recommendation calculation and display: For courses that meet the acceptance criteria, user call feature sets are generated based on the nesting relationship of knowledge points to quantify the collaborative recommendation degree between different course learning packages (such as the collaborative demand degree of users learning "Python Basics" for "Python Data Analysis"). The courses are displayed in order of recommendation degree, forming a course recommendation path of "current learning - related supplements".

[0062] To realize the above-mentioned technical concept, the present invention is demonstrated through the following embodiments:

[0063] In this first embodiment, a course recommendation system for an integrated teaching platform is provided. The system includes: a port linking and course package initialization module, a learning behavior chain processing module, and a course recommendation evaluation module.

[0064] The port linking and course package initialization module is used to establish a corresponding link between the user port and the course interface in the integrated teaching platform, so that users can enter the corresponding course for learning through the course interface, and add program comments to the theoretical knowledge points in the course, and generate the initialized course learning package and course learning package set.

[0065] The port connection and course package initialization module includes a port configuration unit and a course package generation unit.

[0066] The port configuration unit is used to configure a unique course interface for each course and a unique user port for each user in the integrated teaching platform, so that users can establish a link with the corresponding course interface through the exclusive port, and mark the correspondence between the sub-courses contained in the course and the theoretical knowledge points, as well as the theoretical nesting relationship between the knowledge points.

[0067] The course package generation unit is used to add program comments to each theoretical knowledge point in the course, integrate the content of several sub-courses into an initialized course learning package, and the course learning packages together constitute a course learning package set. Each sub-course corresponds to a learning sub-package, and the learning sub-packages are combined to form a course learning package.

[0068] The learning behavior chain processing module is used to record the user's browsing behavior when calling the course learning package through the course interface after obtaining user authorization, form and output the user's learning behavior chain, and use it to uniformly process the course learning package and learning sub-packages. Combined with the user's learning behavior chain, it verifies whether the user's learning behavior status is the primary learning behavior status or the secondary learning behavior status.

[0069] The learning behavior chain processing module includes a learning log recording unit and a behavior chain classification unit.

[0070] The learning log recording unit is used to record the user's browsing behavior details when calling the course learning package through the course interface in real time after user authorization, forming a user learning log. The log content covers the course learning package and learning sub-packages called by the user.

[0071] The behavior chain classification unit is used to divide the learning behavior chain into main learning behavior chain and auxiliary learning behavior chain based on the behavior details in the user's learning log: the main learning behavior chain refers to the behavior chain corresponding to the user's browsing behavior of not calling the learning sub-packages with nested knowledge point theories, and the auxiliary learning behavior chain refers to the behavior chain corresponding to the user's browsing behavior of calling the learning sub-packages with nested knowledge point theories, and forms the main learning behavior chain set and the auxiliary learning behavior chain set respectively.

[0072] The course recommendation and evaluation module is used to evaluate the acceptance of a course learning package among users within a fixed learning period based on the behavioral status feedback of different users towards the same course learning package. Based on the acceptance, it determines whether to initiate collaborative recommendation of course learning packages. When collaborative recommendation is initiated, it generates a feature set of user calls to learning sub-packages based on the theoretical nesting relationship between course knowledge points, quantifies the collaborative recommendation degree between different course learning packages, and recommends and displays them in the integrated teaching platform according to the collaborative recommendation degree.

[0073] The course recommendation and evaluation module includes an acceptance calculation unit, a recommendation decision unit, a feature set generation unit, and a recommendation display unit.

[0074] The acceptance calculation unit is used to count the number of auxiliary learning behaviors of different users towards the same course learning package within a fixed learning period, and to calculate the acceptance of the course learning package by combining the total number of users and the overall behavior statistics.

[0075] The recommendation decision unit is used to preset an acceptance threshold. It compares the calculated acceptance of the course learning package with the acceptance threshold: if the acceptance of the course learning package is greater than the acceptance threshold, collaborative recommendation is not initiated; if the acceptance of the course learning package is less than or equal to the acceptance threshold, collaborative recommendation is initiated.

[0076] The feature set generation unit is used to collect user behavior data of calling nested learning sub-packages based on the nesting relationship of knowledge point theory after collaborative recommendation is started, and generate call feature sets.

[0077] The recommendation display unit quantifies the collaborative recommendation degree between different course learning packages based on the feature set. The recommended course learning packages and the corresponding learning sub-packages based on the feature set are displayed in the integrated teaching platform in descending order of collaborative recommendation degree.

[0078] Please see Figure 1In this second embodiment, a course recommendation method for an integrated teaching platform is provided, applicable to the first embodiment described above. This method includes the following steps:

[0079] Step S1: Establish a link between the user and the course through the course interface and user port in the integrated teaching platform, so that the user can access the corresponding course for learning through the course interface; generate an initial course learning package by adding program comments to the theoretical knowledge points, and form a course learning package set.

[0080] For example, a course interface and a user port are set up in the teaching integration platform so that users can enter the corresponding course for learning through the course interface. One course is set up for one course interface and one user is configured for one user port. The course contains sub-courses of theoretical knowledge points, and one sub-course in the course corresponds to one theoretical knowledge point. There is a nested relationship between theoretical knowledge points.

[0081] Add program comments to the theoretical knowledge points and generate an initial course learning package. Each course learning package contains several sub-courses of theoretical knowledge points. Each sub-course is programmed to form a learning sub-package, and the learning sub-packages are combined to form a course learning package set.

[0082] For example, taking a university's "Integrated Teaching Platform for Computer Science" as an application scenario, and targeting the recommendation requirements of the "Java Programming" course (course number: CS202401) on the platform, 100 second-year computer science students (user numbers: U001-U100) were selected as test users, with a fixed learning period of 1 month.

[0083] When configuring the ports, a unique course interface (interface number: IF-CS202401) was configured for the "Java Programming" course through the platform backend, and unique user ports (port numbers: P001-P100) were configured for 100 test users to ensure that users could access the course interface through their dedicated ports. At the same time, it was clarified that the course contains 5 sub-courses, corresponding to 5 theoretical knowledge points, and the knowledge points are nested: "Java Syntax Basics" → "Flow Control" → "Arrays" → "Object-Oriented Programming" → "Interfaces and Inheritance" (sub-course numbers: S01-S05, each sub-course corresponds to 1 learning sub-package).

[0084] When generating the course package, program comments are added to the 5 theoretical knowledge points (such as adding comments such as "class and object definition" and "constructor method" to the "object-oriented" knowledge point) to generate an initial course learning package (package number: LP-CS202401). This learning package contains 5 learning sub-packages (sub-package numbers: SP01-SP05, corresponding to S01-S05 respectively), forming a course learning package set (including LP-CS202401 and other computer science course learning packages, such as the "data structure" learning package LP-CS202402).

[0085] Step S2: Based on the user's learning behavior of browsing the course learning package through the course interface, generate the user's learning behavior chain;

[0086] For example, after user authorization, the learning logs of each user are recorded through the integrated teaching platform. The learning logs record the user's learning behavior of browsing the course learning package by calling the course interface. The user port provides feedback on the corresponding user's learning behavior to generate a user's learning behavior chain.

[0087] Learning behaviors include primary learning behaviors and secondary learning behaviors. Primary learning behaviors refer to the learning behavior chain in which users browse through the course interface without calling learning sub-packages with nested knowledge point theories, and generate a primary learning behavior chain set, which is equal to the course learning package set. Secondary learning behavior chains refer to the learning behavior chain in which users browse through the course interface by calling learning sub-packages with nested knowledge point theories, and generate a secondary learning behavior chain set, which belongs to the primary learning behavior chain set.

[0088] When recording learning logs, after user authorization, the platform records the learning logs of 100 users through the learning behavior chain collection module. The log content includes the course learning packages and sub-packages called by the user, the call duration (≥10 minutes is counted as a valid call), and the call frequency; for example, user U001 called LP-CS202401 on September 5 but did not call any sub-packages, and user U002 called LP-CS202401 on September 8 and simultaneously called SP04 (object-oriented) and SP05 (interface and inheritance);

[0089] When classifying behavior chains, user behavior chains were divided into primary learning behavior chains (without calling nested sub-packages) and secondary learning behavior chains (calling nested sub-packages) using behavior chain classification units. Within one month, a total of 180 valid learning behavior chains were collected, including 70 primary learning behavior chains (38.9%) and 110 secondary learning behavior chains (61.1%), forming a primary learning behavior chain set (containing complete course call records such as LP-CS202401) and a secondary learning behavior chain set (containing sub-package call records such as SP01-SP05).

[0090] Step S3: Based on the learning behavior chain set, verify the user's learning behavior status to obtain the main learning behavior status or the secondary learning behavior status.

[0091] For example, the course learning package and learning sub-packages are uniformly encoded, and based on the encoding information, the set of course learning packages corresponding to the i-th course learning package is denoted as U. i ={V j |j∈[1,J]}, where V j Let J represent the j-th learning sub-package, and J represent the total number of learning sub-packages;

[0092] Based on user learning behavior feedback from user ports, the set of learning behavior chains corresponding to the x-th user port under the ith course learning package is denoted as L. w (x, i) = {V j |j∈[1,J]}, where w=1 or 2, if w=1, it represents the main learning behavior state, and L w (x, i) represents the primary learning behavior chain set, and if w = 2, it represents the secondary learning behavior state, and L w (x, i) represents the set of auxiliary learning behavior chains;

[0093] Based on the learning behavior chain set, the user's learning behavior status is verified. If L w (x, i) = U i Then the verification is the primary learning behavior state, if L w (x, i) ≠ U i If so, it is verified as a secondary learning behavior state;

[0094] When encoding, the course learning package and its sub-packages are uniformly encoded: LP-CS202401 is encoded as U1, SP01-SP05 are encoded as V1-V5, and U1 = {V1,V2,V3,V4,V5}.

[0095] During state verification, if Lw(x,1) = U1 (i.e., the user calls LP-CS202401 and covers V1-V5), then it is the primary learning behavior state (w = 1); if Lw(x,1) ≠ U1 (i.e., the user only calls part of V1-V5), then it is the auxiliary learning behavior state (w = 2), where x is the user number and i = 1 corresponds to U1.

[0096] Step S4: Based on the primary or secondary learning status feedback from different users regarding the same course learning package, assess the acceptance of the course learning package among the user group to determine whether to conduct collaborative recommendation of the course learning package;

[0097] For example, under a fixed learning period, based on the primary or secondary learning status feedback from different users regarding the same course learning package, the acceptance of the course learning package among the user group is evaluated, and the acceptance of the i-th course learning package is... In the formula, N represents the total number of users, F[·] represents the counting function, and if there exists a set of learning behavior chains L w The learning state corresponding to (x, i) is the secondary learning state, i.e., w = 2, then let If a learning behavior chain set L exists w The learning state corresponding to (x, i) is the primary learning state, i.e., w = 1. Then let...

[0098] A preset acceptance threshold is set. If the acceptance of the i-th course learning package is greater than the acceptance threshold, collaborative recommendation between course learning packages will not be performed. If the acceptance of the i-th course learning package is less than or equal to the acceptance threshold, collaborative recommendation between course learning packages will be performed.

[0099] When calculating the acceptance rate, the total number of users N = 100, the number of users with auxiliary learning behavior status (F = 65), and the total number of overall behavior statistics (auxiliary behavior statistics for all courses) = 500; then P(1) = 1 - (65 / 500) = 0.87;

[0100] At the initial stage of the recommendation decision, the preset acceptance threshold is 0.8. Since P(1) = 0.87 > 0.8, it is determined that LP-CS202401 has a high acceptance among users and there is no need to start collaborative recommendation. At the same time, the acceptance of the "Advanced C Language" course learning package (LP-CS202403) is calculated as P(3) = 1 - (80 / 500) = 0.84 > 0.8, so collaborative recommendation is not started. However, the acceptance of the "Assembly Language" course learning package (LP-CS202404) is P(4) = 1 - (120 / 500) = 0.76 < 0.8, so collaborative recommendation needs to be started.

[0101] Step S5: When performing collaborative recommendation of course learning packages, based on the nesting relationship of knowledge points and theories, generate a call feature set of learning sub-packages that have nesting relationships of knowledge points and theories through the course interface, so as to quantify the collaborative recommendation degree between course learning packages and display the recommendations.

[0102] For example, based on the course learning package set and the auxiliary learning behavior chain set, a call feature set is generated for users calling learning sub-packages with nested knowledge point theories through the course interface.

[0103] Based on the feature set of invocation, the collaborative recommendation degree of course learning packages is quantified. In the formula, e is the code number of the course learning package, and e≠i;

[0104] Based on the order of collaborative recommendation degree from large to small, generate a sequence of collaboratively recommended course learning packages for the i-th course learning package, and display the course learning package sequence and the learning sub-packages corresponding to the called feature set in the integrated teaching platform.

[0105] When generating the feature set, based on the nesting relationship of knowledge points ("Assembly Language" is related to "Computer Organization" and "C Language Basics"), the behavior data of users calling the associated sub-packages of LP-CS202404 are collected to generate the call feature set H(4) (which includes the user calling the "Computer Organization" sub-package and the "C Language Basics" sub-package).

[0106] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0107] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A course recommendation method for an integrated teaching platform, characterized in that, The method includes the following steps: Step S1: Establish a link between the user and the course through the course interface and user port in the integrated teaching platform, so that the user can access the corresponding course for learning through the course interface; generate an initial course learning package by adding program comments to the theoretical knowledge points, and form a course learning package set. Step S2: Based on the user's learning behavior of browsing the course learning package through the course interface, generate the user's learning behavior chain; Step S3: Based on the learning behavior chain set, verify the user's learning behavior status to obtain the main learning behavior status or the secondary learning behavior status. Step S4: Based on the primary or secondary learning status feedback from different users regarding the same course learning package, assess the acceptance of the course learning package among the user group to determine whether to conduct collaborative recommendation of the course learning package; Step S5: When performing collaborative recommendation of course learning packages, based on the nesting relationship of knowledge points and theories, generate a call feature set of learning sub-packages that have nesting relationships of knowledge points and theories through the course interface, so as to quantify the collaborative recommendation degree between course learning packages and make recommendations.

2. The course recommendation method for an integrated teaching platform according to claim 1, characterized in that, The specific implementation process of step S1 includes: The integrated teaching platform sets up course interfaces and user ports, which are used by users to access the corresponding courses for learning through the course interfaces. One course corresponds to one course interface, and one user corresponds to one user port. The courses contain sub-courses of theoretical knowledge points, and one sub-course in the course corresponds to one theoretical knowledge point. There is a nested relationship between the theoretical knowledge points. The theoretical knowledge points are annotated with program comments, and an initialized course learning package is generated. Each course learning package contains several sub-courses of theoretical knowledge points, and each sub-course is programmed to form a learning sub-package. The course learning packages are composed of the learning sub-packages to generate a course learning package set.

3. The course recommendation method for an integrated teaching platform according to claim 1, characterized in that, The specific implementation process of step S2 includes: After user authorization, the learning logs of each user are recorded through the integrated teaching platform. The learning logs record the user's learning behavior of browsing the course learning package by calling the course interface. The user port provides feedback on the corresponding user's learning behavior to generate a user's learning behavior chain. The learning behaviors include primary learning behaviors and secondary learning behaviors. The primary learning behaviors refer to the learning behavior chain in which the user browses through the course interface without calling the learning sub-packages with nested knowledge point theories, and generate a primary learning behavior chain set, which is equal to the course learning package set. The secondary learning behavior chain refers to the learning behavior chain in which the user browses through the course interface by calling the learning sub-packages with nested knowledge point theories, and generate a secondary learning behavior chain set, which belongs to the primary learning behavior chain set.

4. The course recommendation method for an integrated teaching platform according to claim 1, characterized in that, The specific implementation process of step S3 includes: The course learning packages and learning sub-packages are uniformly encoded. Based on the encoding information, the set of course learning packages generated corresponding to the i-th course learning package is denoted as U. i ={V j |j∈[1,J]}, where V j Let J represent the j-th learning sub-package, and J represent the total number of learning sub-packages; Based on user learning behavior feedback from user ports, the set of learning behavior chains corresponding to the x-th user port under the ith course learning package is denoted as L. w (x, i) = {V j |j∈[1,J]}, where w=1 or 2, if w=1, it represents the main learning behavior state, and L w (x, i) represents the primary learning behavior chain set, and if w = 2, it represents the secondary learning behavior state, and L w (x, i) represents the set of auxiliary learning behavior chains; Based on the learning behavior chain set, the user's learning behavior status is verified. If L w (x, i) = U i Then the verification is the primary learning behavior state, if L w (x, i) ≠ U i If so, it is verified as a secondary learning behavior state.

5. The course recommendation method for an integrated teaching platform according to claim 4, characterized in that, The specific implementation process of step S4 includes: Under a fixed learning period, based on the primary or secondary learning status feedback from different users regarding the same course learning package, the acceptance of the course learning package among the user group is evaluated, and the acceptance of the i-th course learning package is... In the formula, N represents the total number of users, F[·] represents the counting function, and if there exists a set of learning behavior chains L w The learning state corresponding to (x, i) is the secondary learning state, i.e., w = 2, then let If a learning behavior chain set L exists w The learning state corresponding to (x, i) is the primary learning state, i.e., w = 1. Then let... A preset acceptance threshold is set. If the acceptance of the i-th course learning package is greater than the acceptance threshold, collaborative recommendation between course learning packages will not be performed. If the acceptance of the i-th course learning package is less than or equal to the acceptance threshold, collaborative recommendation between course learning packages will be performed.

6. The course recommendation method for an integrated teaching platform according to claim 5, characterized in that, The specific implementation process of step S5 includes: Based on the course learning package set and the auxiliary learning behavior chain set, a call feature set is generated for users calling learning sub-packages with nested knowledge point theories through the course interface. Based on the feature set of invocation, the collaborative recommendation degree of course learning packages is quantified. In the formula, e is the code number of the course learning package, and e≠i; Based on the order of collaborative recommendation degree from largest to smallest, a sequence of collaboratively recommended course learning packages for the i-th course learning package is generated, and the course learning package sequence and the learning sub-packages corresponding to the called feature set are recommended and displayed on the integrated teaching platform.

7. A course recommendation system for an integrated teaching platform, executing the course recommendation method for an integrated teaching platform as described in claim 1, characterized in that, The system includes: a port connection and course package initialization module, a learning behavior chain processing module, and a course recommendation and evaluation module; The port link and course package initialization module is used to establish a corresponding link between the user port and the course interface in the integrated teaching platform, so that users can enter the corresponding course for learning through the course interface, and add program comments to the theoretical knowledge points in the course, and generate an initialized course learning package and course learning package set. The learning behavior chain processing module is used to record the user's browsing behavior when calling the course learning package through the course interface after obtaining user authorization, form and output the user's learning behavior chain, and use it to uniformly process the course learning package and learning sub-packages. Combined with the user's learning behavior chain, it verifies whether the user's learning behavior status is the main learning behavior status or the auxiliary learning behavior status. The course recommendation and evaluation module is used to evaluate the acceptance of a course learning package among users within a fixed learning period based on the behavioral status feedback of different users towards the same course learning package. Based on the acceptance, it determines whether to initiate collaborative recommendation of the course learning package. When collaborative recommendation is initiated, it generates a feature set of user-called learning sub-packages based on the theoretical nesting relationship between course knowledge points, quantifies the collaborative recommendation degree between different course learning packages, and recommends and displays them in the integrated teaching platform according to the collaborative recommendation degree.

8. A course recommendation system for an integrated teaching platform according to claim 7, characterized in that, The port connection and course package initialization module includes a port configuration unit and a course package generation unit; The port configuration unit is used to configure a unique course interface for each course and a unique user port for each user in the integrated teaching platform, so that users can establish a link with the corresponding course interface through the exclusive port, and mark the correspondence between the sub-courses contained in the course and the theoretical knowledge points, as well as the theoretical nesting relationship between the knowledge points. The course package generation unit is used to annotate each theoretical knowledge point in the course, integrate the content of several sub-courses into an initialized course learning package, and the course learning packages together constitute a course learning package set. Each sub-course corresponds to a learning sub-package, and the learning sub-packages are combined to form a course learning package.

9. A course recommendation system for an integrated teaching platform according to claim 7, characterized in that, The learning behavior chain processing module includes a learning log recording unit and a behavior chain classification unit; The learning log recording unit is used to record the browsing behavior details of the user calling the course learning package through the course interface in real time after the user authorizes it, forming a user learning log. The log content covers the course learning package and learning sub-package called by the user. The behavior chain classification unit is used to divide the learning behavior chain into a main learning behavior chain and a secondary learning behavior chain based on the behavior details in the user's learning log: the main learning behavior chain refers to the behavior chain corresponding to the user's browsing behavior of not calling the learning sub-packages with nested knowledge point theories, and the secondary learning behavior chain refers to the behavior chain corresponding to the user's browsing behavior of calling the learning sub-packages with nested knowledge point theories, and forms a main learning behavior chain set and a secondary learning behavior chain set respectively.

10. A course recommendation system for an integrated teaching platform according to claim 7, characterized in that, The course recommendation and evaluation module includes an acceptance calculation unit, a recommendation decision unit, a feature set generation unit, and a recommendation display unit. The acceptance calculation unit is used to count the number of auxiliary learning behavior states of different users for the same course learning package within a fixed learning period, and calculate the acceptance of the course learning package by combining the total number of users and the overall behavior statistics. The recommendation decision unit is used to preset an acceptance threshold and compare the calculated acceptance of the course learning package with the acceptance threshold: if the acceptance of the course learning package is greater than the acceptance threshold, collaborative recommendation will not be initiated. If the acceptance rate of the course learning package is less than or equal to the acceptance rate threshold, then collaborative recommendation is initiated; The feature set generation unit is used to collect user behavior data of calling nested learning sub-packages based on the nesting relationship of knowledge point theory after collaborative recommendation is started, and generate a call feature set. The recommendation display unit quantifies the collaborative recommendation degree between different course learning packages based on the feature set, and displays the recommended course learning packages and the learning sub-packages corresponding to the feature set in the teaching integration platform in descending order of collaborative recommendation degree.

Images