Course recommendation method and system for intelligently building education platform

Abstract

The invention discloses a course recommendation method and system for intelligently building an education platform, and relates to the technical field of intelligent education informatization, and the method comprises the steps: building a knowledge graph, and completing the multi-level association of tasks and knowledge points; analyzing the assessment data, identifying weak knowledge points of the trainees, and setting score threshold fusion post weights; generating a course recommendation result on the basis of recognizing weak knowledge points of students, and optimizing recommendation logic in real time by adopting feedback; according to the method, a knowledge graph model associated with three layers of tasks, knowledge points and posts is constructed, student examination performance and post skill requirements are fused, and a course recommendation path construction mechanism driven by a multi-dimensional weight is realized; a dynamic feedback and real-time scoring algorithm is adopted, closed-loop logic of recommendation, assessment and re-recommendation is established, recommendation individuation and post matching degree are effectively improved, and the problems that knowledge points in an existing platform are not traceable, post adaptability is weak, and a recommendation strategy is single are solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent education information technology, and specifically to a course recommendation method and system for an intelligent construction education platform. Background Art

[0002] With the continuous advancement of information technology, artificial intelligence, and educational big data processing capabilities, intelligent education platforms have been widely used in scenarios such as vocational training, skills education, and engineering construction. In architectural vocational colleges, industry training institutions, and in-house training systems at engineering companies, online platforms undertake the important functions of course resource management, learning path planning, and skills assessment. To enhance course matching, most platforms integrate recommendation algorithms, building personalized recommendation mechanisms based on learning behavior data. Existing platforms primarily rely on static behavioral characteristics such as click history, course completion rates, and page dwell time to build matching models, forming relatively preliminary course recommendation frameworks.

[0003] The intelligent recommendation strategy has exposed many technical deficiencies during its promotion process. Most current platforms do not develop recommendation modeling based on learners' mastery of knowledge points, nor do they build multi-level bidirectional associations between knowledge points and chapter tasks. There is a lack of task recommendation paths driven by knowledge structure. Course recommendation results are mainly driven by course labels and are not modeled based on the knowledge distribution logic within the course. Especially in architecture courses, the course structure often contains multiple overlapping tasks, and the knowledge point coverage is complex. The existing platforms lack the ability to support task-level knowledge tracking, and the recommendation logic cannot effectively reflect the learning structure.

[0004] The recommendation system makes insufficient use of assessment data. Most platforms do not feed back the completion status of chapter tasks or scoring results into the recommendation logic. The recommendation path lacks responsiveness and adjustment to real-time learning effects. At the system structure level, teaching content and job skill requirements are often stored in a scattered manner, and structural integration is not achieved. As a result, the platform cannot dynamically adjust course priorities based on job requirements, and the recommendation results are difficult to support job competency-oriented learning goals. In professional modules such as structural design and BIM modeling, the disconnect between course content and job skills is particularly obvious. The recommendation mechanism of the intelligent education platform still has room for improvement in terms of knowledge organization granularity, feedback timeliness, and job adaptability. It is necessary to introduce a course recommendation method based on knowledge graph construction, dynamic score analysis, and job capability integration to improve recommendation accuracy and path intelligence. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: the existing intelligent construction education platform course recommendation method has the problems of rough knowledge structure modeling, low recommendation accuracy, poor job adaptability, and delayed feedback response, as well as how to dynamically identify the mastery of knowledge points based on branch task assessment data, adjust the recommendation weight based on job skill requirements, and realize real-time optimization and iteration of recommendation results.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a course recommendation method for an intelligent construction education platform, comprising constructing a knowledge graph, completing multi-level associations between tasks and knowledge points; analyzing assessment data, identifying students' weak knowledge points, and setting score thresholds to integrate job weights; generating course recommendation results based on identifying students' weak knowledge points, and using feedback to optimize recommendation logic in real time; multi-level associations include many-to-many mapping of knowledge points and branch tasks to form a bidirectional searchable index relationship, and the association relationship supports multiple coverage and cross-mapping between tasks and knowledge points in the graph, allowing one task to correspond to multiple knowledge points, and one knowledge point to be referenced by multiple tasks; setting score thresholds to integrate job weights includes performing score ratio calculations and comparing the score rate with a preset score threshold; if the score is below the score threshold, extracting the knowledge points corresponding to the task, combining the job weights set for the knowledge points in the job capability model, and merging the two types of weight data in a linear weighted manner to generate a comprehensive knowledge point weight for recommendation sorting.

[0008] As a preferred solution of the course recommendation method of the intelligent construction education platform described in the present invention, the construction of the knowledge graph includes presetting a knowledge point library, constructing multiple knowledge point nodes using a tree-like classification structure, and configuring the unique identifier, name, category, prerequisite knowledge point set and job adaptation weight of each knowledge point.

[0009] As a preferred solution of the course recommendation method of the intelligent construction education platform described in the present invention, the multi-level association includes, based on the chapter task content set by the intelligent construction education platform, performing a many-to-many mapping of the set multiple branch tasks and the relevant knowledge points in the knowledge point library, and maintaining a bidirectional searchable index relationship between chapters, tasks, and knowledge points in the graph.

[0010] As a preferred solution of the course recommendation method of the intelligent construction education platform described in the present invention, the identification of students' weak knowledge points includes calculating the score rate of the branch task based on the actual score of the students after completing the branch task and the total score of the preset task, and comparing it with the set score threshold. If it is lower than the score threshold, all knowledge points associated with the branch task are marked as knowledge points to be strengthened; if it is higher than the score threshold, the knowledge point weakness weight of the knowledge point to be strengthened is calculated based on the branch task score and the proportion of the task in the total score to form a portrait of the students' weak knowledge points.

[0011] As a preferred solution of the intelligent construction education platform course recommendation method described in the present invention, the integrated job weight includes obtaining the target knowledge point weight of the current student's job from the enterprise job database, linearly weighting the job weight and the knowledge point weakness weight to obtain the comprehensive weight of the knowledge point to be recommended.

[0012] As a preferred solution of the intelligent construction education platform course recommendation method described in the present invention, the linear weighted processing includes setting platform preset values ​​and dynamic adjustment values ​​based on weight parameters, making corrections according to job changes, and constructing a job-oriented weighted knowledge point recommendation priority list.

[0013] As a preferred solution of the course recommendation method for the intelligent construction education platform described in the present invention, the generating of course recommendation results includes retrieving all candidate courses that match the knowledge points corresponding to the weight of each comprehensive knowledge point from the course database, performing multi-dimensional priority sorting, calculating the comprehensive recommendation score, and establishing a candidate course set.

[0014] As a preferred solution of the intelligent construction education platform course recommendation method described in the present invention, the calculation of the comprehensive recommendation score includes the three factors of the aforementioned knowledge point comprehensive weight value, the global completion rate of the course in the platform's historical data, and the current student's learning preference value for the course, which are weighted and synthesized into a recommendation score according to a set ratio.

[0015] As a preferred solution of the course recommendation method of the intelligent construction education platform described in the present invention, the real-time optimization recommendation logic using feedback includes: after the students complete the recommended courses, re-initiating online assessments for the side tasks associated with the courses, and calculating the students' score rates on the side tasks; if the score rate is higher than the score threshold set by the platform, the knowledge points associated with the side tasks are removed from the list to be strengthened and no longer participate in the next round of recommendations; if the score rate is lower than the score threshold, the knowledge points are maintained in a high priority state, triggering the recommendation iteration logic, changing the course type, difficulty level and presentation method according to the original recommendation record, and re-outputting the recommendation results.

[0016] Another object of the present invention is to provide a course recommendation system for an intelligent construction education platform, which can solve the problems existing in the current course recommendation system, such as weak knowledge point structure expression ability, unclear task association, and inability to accurately track students' knowledge mastery, by constructing a knowledge graph and realizing multi-level association between tasks and knowledge points.

[0017] As a preferred solution of the course recommendation system of the intelligent construction education platform described in the present invention, it includes: a knowledge graph construction module, a weak knowledge point identification module, a job adaptation fusion module, a multi-dimensional course recommendation module, and a feedback and iterative optimization module; the knowledge graph construction module is used to read the knowledge point library and chapter task information when initializing the course update, build a multi-level many-to-many mapping graph structure, and generate a two-way searchable index between tasks, chapters and knowledge points for subsequent recommendation tracing; the weak knowledge point identification module is used to determine whether it is a knowledge point to be strengthened based on the comparison of the score with the score threshold after the student completes the branch task, calculate the weakness weight in combination with the task score ratio, and update it to the student's knowledge point. point weakness portrait; the job adaptation fusion module is used to call the enterprise job library to obtain the knowledge point weights of the target job, linearly weighted with the identified knowledge point weaknesses, output the comprehensive weight, and dynamically modify the weight parameters according to job changes; the multi-dimensional course recommendation module is used to screen candidate courses from the course library according to the comprehensive weight, sort them by weighted scores of knowledge point matching, course completion rate and student type preference, and output a recommendation list after screening out courses below the set score threshold; the feedback and iterative optimization module is used to trigger re-assessment after the student completes the recommended course. If the score rate is higher than the score threshold, the mastery status is updated; if it does not meet the standard, the course type is switched to enter the next round of recommendation until the standard is met and the round limit is reached.

[0018] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a course recommendation method for an intelligent construction education platform.

[0019] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for recommending courses on an intelligent construction education platform.

[0020] Beneficial effects of the present invention: The course recommendation method for the intelligent construction education platform provided by the present invention completes the multi-level association of tasks and knowledge points by constructing a knowledge graph, realizes a many-to-many mapping from chapters, branch tasks to knowledge points, enables the recommendation logic to accurately locate the knowledge point mastery structure, and improves the recommended knowledge tracking ability and path interpretability; by analyzing the assessment data, identifying the students' weak knowledge points, setting the score threshold and integrating the job weight, a weight fusion mechanism from the dynamic portrait of the students' performance to the job skill requirements is realized, so that the recommendation ranking is more in line with the job ability requirements and the career orientation of the recommended content is enhanced; by generating course recommendation results based on identifying the students' weak knowledge points, and using feedback to optimize the recommendation logic in real time, a real-time iterative recommendation process driven by the assessment results is realized, ensuring that the recommendation path is constantly adjusted and optimized, and improving the timeliness of the recommendation response and the accuracy of the course reinforcement; the present invention has achieved better results in terms of knowledge structure modeling accuracy, job orientation matching capability and dynamic recommendation feedback mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 This is an overall flow chart of a course recommendation method for an intelligent construction education platform provided in Example 1 of the present invention.

[0023] Figure 2 This is a role interaction and processing flow chart of a course recommendation system for an intelligent construction education platform provided in Example 2 of the present invention.

[0024] Figure 3 This is an overall schematic diagram of a course recommendation system for an intelligent construction education platform provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0025] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0026] Example 1, with reference to Figure 1 , as one embodiment of the present invention, provides a method for recommending courses on an intelligent construction education platform, comprising: S1: Build a knowledge graph to complete the multi-level association between tasks and knowledge points.

[0027] Furthermore, constructing a knowledge graph includes presetting a knowledge point library, constructing multiple knowledge point nodes using a tree-like classification structure, and configuring each knowledge point's unique identifier, name, category, set of previous knowledge points, and job adaptation weight.

[0028] It should be noted that the multi-level association includes, based on the chapter task content set in the intelligent construction education platform, many-to-many mapping of multiple branch tasks and related knowledge points in the knowledge point library, and maintaining a bidirectional searchable index relationship between chapters, tasks, and knowledge points in the graph.

[0029] It should be noted that the use of a tree-like classification structure includes, based on the knowledge system of the construction engineering field, dividing the knowledge points layer by layer according to the field direction to form a classification path with hierarchical logic, including using BIM technology as the root node of the knowledge graph to identify the professional direction to which the course belongs; setting the modeling specification as a standard process sub-node at the root node to aggregate the key technical rules of the construction; further refining the assessable skill nodes under the standard process sub-node to associate course tasks, assessment standards and students' knowledge mastery status.

[0030] It should also be noted that setting modeling specifications includes unifying the naming format in tasks, evaluating the accuracy and traceability of students' task completion based on the parameters and constraints in the tasks, standardizing the modeling operation methods and parameter configuration structures in course tasks, supporting the precise association between tasks and knowledge points, and establishing the assessment and recommendation logic for students' parametric modeling capabilities.

[0031] S2: Analyze assessment data, identify students’ weak knowledge points, set score thresholds and integrate job weights.

[0032] Furthermore, identifying students' weak knowledge points includes calculating the score rate of the side task based on the students' actual score after completing the side task and the total score of the preset task, and comparing it with the set score threshold. If it is lower than the score threshold, all knowledge points associated with the side task are marked as knowledge points to be strengthened; if it is higher than the score threshold, the knowledge point weakness weights of the knowledge points to be strengthened are calculated based on the side task score and the proportion of the task in the total score, thereby forming a portrait of the students' weak knowledge points.

[0033] Furthermore, the score rate of the side quest is calculated as follows: ; in, Indicates the student's side mission score rate, Indicates the actual score of the student in this branch task. Indicates the total score of the branch task. Based on the branch task score rate, the score threshold is determined. If the branch task score rate of the student in the task is less than 60%, the knowledge point associated with the task is marked as to be strengthened. Based on the task score rate and the correlation between the knowledge point, the knowledge point weakness weight is calculated, which is expressed as: ; in, Indicates the student's weakness weight in a certain knowledge point. Indicates the number of branch tasks associated with this knowledge point. Indicates the index of the branch task, Indicates that the students The score rate of each branch mission, Indicates that the students The total score of each branch mission is set. Indicates the total score of the chapter where the knowledge point is located. The "degree of non-mastery" (i.e. ) multiplied by the proportion of tasks in the chapter to obtain the overall weakness of the knowledge point. The higher the weight, the more the knowledge point needs to be strengthened, and it becomes the priority reinforcement target in the course recommendation system. The response is achieved in seconds through the analysis of branch task scores. If the student fails to master a certain knowledge point in the assessment, the system will immediately push the related courses after submitting the assessment, saving the corresponding update cycle.

[0034] It should be noted that the integration of job weights includes obtaining the target knowledge point weights of the current trainee's job from the enterprise job database, linearly weighting the job weights and the knowledge point weakness weights to obtain the comprehensive weights of the knowledge points to be recommended.

[0035] It should be noted that linear weighted processing includes setting platform preset values ​​and dynamic adjustment values ​​based on weight parameters, making corrections according to job changes, and building a job-oriented weighted knowledge point recommendation priority list.

[0036] It should also be noted that the construction of a position-oriented weighted knowledge point recommendation priority list includes receiving the current trainee position identification information returned by the position identification, extracting the knowledge point weight set corresponding to the position from the position capability model, forming a one-to-one mapping between each knowledge point and the position weight, and obtaining the comprehensive weight of the knowledge point to be recommended, which is expressed as: ; in, Indicates the comprehensive recommendation weight of the knowledge point to be recommended, Indicates the student's weakness weight in a certain knowledge point. Indicates the importance weight of the target position to this knowledge point, and Represents an adjustable parameter used to control the fusion ratio of the two, usually satisfying , before the comprehensive recommendation weight of the knowledge point to be recommended, 、 The values ​​of 、 Statistically calculate the maximum value within the sample range and perform normalization processing to uniformly map data of different dimensions to dimensionless values ​​in the interval [0,1]. If a certain knowledge point has high requirements for the position ( large) and students have weak grasp of ( large), the comprehensive weight This integrated mechanism ensures that course recommendations reflect not only the student's current ability gap but also the company's actual job skill requirements. Furthermore, through the dual calibration of knowledge point networks and job weights, recommendation accuracy is significantly improved, boosting student satisfaction with recommended courses.

[0037] S3: Generate course recommendation results based on identifying students’ weak knowledge points, and use feedback to optimize recommendation logic in real time.

[0038] Furthermore, generating course recommendation results includes retrieving all candidate courses that match the knowledge points corresponding to each comprehensive knowledge point weight from the course database, performing multi-dimensional priority sorting, calculating the comprehensive recommendation score, and establishing a candidate course set.

[0039] It should be noted that the calculation of the comprehensive recommendation score includes the three factors of the aforementioned comprehensive weight value of the knowledge points, the global completion rate of the course in the platform's historical data, and the current student's learning preference value for the course, which are weighted according to the set ratio to synthesize the recommendation score.

[0040] It should be noted that the recommendation scoring model is expressed as: ; in, Indicates the comprehensive score of course recommendations, used for sorting. Indicates the comprehensive recommendation weight of the knowledge point to be recommended, Indicates the average completion rate of the course in the platform history, reflecting the quality and acceptance of the course. Indicates the current student’s preference coefficient for this type of course. represents the knowledge point relevance weight parameter, represents the course completion rate weight parameter, Represents the course type preference weight parameter, satisfying , the information of the three dimensions is integrated into a score value, before calculating the comprehensive score of the course recommendation, 、 、 The values ​​of 、 、 Normalization is performed within the statistical calculation sample range, and data of different dimensions are uniformly mapped to dimensionless values ​​in the interval [0,1]. The system calculates the number of candidate courses. , and then sort by score, select the top several items as the recommendation results output, to ensure that course recommendations are not only based on accurate matching of knowledge needs, but also take into account course acceptability and user preferences, and build a dynamic sorting logic driven by multiple factors.

[0041] It should also be noted that the use of feedback to optimize the recommendation logic in real time includes: after the students complete the recommended courses, re-initiating online assessments for the side tasks associated with the courses, and calculating the students' score rate on the side tasks; if the score rate is higher than the score threshold set by the platform, the knowledge points associated with the side tasks will be removed from the list to be reinforced and will no longer participate in the next round of recommendations; if the score rate is lower than the score threshold, the knowledge points will be maintained in a high priority state, triggering the recommendation iteration logic, changing the course type, difficulty level and presentation method according to the original recommendation record, and re-outputting the recommendation results.

[0042] Example 2, reference Figure 2-Figure 3 , which is an embodiment of the present invention, provides a course recommendation system for an intelligent construction education platform, including a knowledge graph construction module 100, a weak knowledge point identification module 200, a job adaptation and fusion module 300, a multi-dimensional course recommendation module 400, and a feedback and iterative optimization module 500.

[0043] Among them, X1: the knowledge graph construction module 100 includes a knowledge point library management sub-module 101 and a chapter and task mapping sub-module 102.

[0044] It should be noted that the knowledge point library management submodule 101 is used to preset a multi-level knowledge point structure in the field of construction engineering, and adopts a tree-like classification structure to configure the knowledge point unique identification, name, category, pre-dependency and job adaptation weight to achieve standardized representation of knowledge content; the chapter and task mapping submodule 102 is used to make a many-to-many association between knowledge points and tasks according to the chapters and branch task contents set by the platform, and to construct a two-way searchable index relationship between tasks and knowledge points.

[0045] It should also be noted that the knowledge graph construction module 100 is initialized to establish a structural graph between tasks and knowledge points, which is the basis for subsequent analysis of student capabilities and generation of recommended courses.

[0046] X2: The weak knowledge point identification module 200 includes a score rate calculation submodule 201 and a knowledge point weakness analysis submodule 202 .

[0047] It should be noted that the score rate calculation submodule 201 is used to collect the score results of the students in the branch tasks, and calculate the branch task score rate by calculating the ratio of the actual branch score to the set total score of the branch task; the knowledge point weakness analysis submodule 202 is used to compare the score rate with the preset score threshold. If it is lower than the score threshold, the corresponding knowledge point will be marked as an item to be strengthened, and a weighted sum will be performed to generate the knowledge point weakness weight.

[0048] It should also be noted that the weak knowledge point identification module 200 analyzes the student's performance in real time based on the constructed graph structure, outputs a personalized knowledge mastery graph, and provides the original weight basis for subsequent job matching and course sorting.

[0049] X3: The job adaptation and fusion module 300 includes a job skill extraction submodule 301 and a comprehensive weight calculation submodule 302.

[0050] It should be noted that the job skill extraction submodule 301 is used to extract the knowledge points and job weights required for the trainee's job from the enterprise job competency database; the comprehensive weight calculation submodule 302 is used to linearly weight the job weight and the weakness weight, and generate the comprehensive knowledge point recommendation weight based on the proportion parameters set by the platform.

[0051] It should also be noted that the job adaptation integration module 300 realizes the integration of educational content and job requirements, so that the recommendation logic is not only based on the current abilities of the students, but also takes into account the actual employment standards of the enterprise, thereby improving the career matching degree of the recommended courses.

[0052] X4: The multi-dimensional course recommendation module 400 includes a candidate course screening submodule 401 and a recommendation score calculation submodule 402.

[0053] It should be noted that the candidate course screening submodule 401 is used to extract the entire course set that matches the knowledge points to be recommended from the course database; the recommendation score calculation submodule 402 is used to integrate three factors: the comprehensive weight of the knowledge points, the historical course completion rate, and the students' course type preferences, and calculate the recommendation score for each course based on the weighted scoring model.

[0054] It should also be noted that the multi-dimensional course recommendation module 400 generates the final recommendation list and is the key execution module for the transition from knowledge to courses, forming a closed loop with the feedback and iterative optimization module 500.

[0055] X5: The feedback and iterative optimization module 500 includes a reassessment submodule 501 and a recommended path update submodule 502 .

[0056] It should be noted that the reassessment submodule 501 is used to re-initiate assessment of related tasks after students complete the recommended courses and update the score data; the recommended path update submodule 502 is used to remove relevant knowledge points with a score rate higher than the set score threshold from the list to be strengthened; if the standards are not met, the course type, difficulty or content strategy will be changed and the next round of recommendations will be triggered.

[0057] It should also be noted that the feedback and iterative optimization module 500 realizes the adaptive evolution of the recommendation mechanism and is the implementation part of the dynamic recommendation closed loop, ensuring the continuous correction and optimization of the recommendation process.

Claims

1. A method for recommending courses on an intelligent construction education platform, characterized in that: include: Build a knowledge graph to complete the multi-level association between tasks and knowledge points; Analyze assessment data, identify students' weak knowledge points, set score thresholds and integrate job weights; Generate course recommendations based on identifying students' weak knowledge points, and use feedback to optimize recommendation logic in real time; Multi-level associations include many-to-many mappings between knowledge points and branch tasks, forming a bidirectional searchable index relationship. The association relationship supports multiple coverage and cross-mapping between tasks and knowledge points in the graph, allowing one task to correspond to multiple knowledge points, and one knowledge point to be referenced by multiple tasks. Setting the score threshold and integrating the job weights includes calculating the score ratio and comparing the score ratio with the preset score threshold; If the score is below the threshold, the knowledge points corresponding to the task are extracted, and combined with the job weights set for the knowledge points in the job competency model, the two types of weight data are merged through linear weighting to generate a comprehensive knowledge point weight for recommendation ranking; Identifying students’ weak knowledge points includes: Based on the student's actual score after completing the side task and the total score of the preset task, the side task score rate is calculated and compared with the set score threshold. If it is lower than the score threshold, all knowledge points associated with the side task are marked as knowledge points to be strengthened; If the score is higher than the threshold, the weight of the knowledge point to be strengthened will be calculated based on the score of the branch task and the proportion of the task in the total score, forming a profile of the student's knowledge point weaknesses; The weights of integrated positions include: Obtain the target knowledge point weights of the current trainee's position from the company's position database, perform linear weighting on the position weights and the knowledge point weakness weights to obtain the comprehensive weights of the knowledge points to be recommended; Linear weighting processing includes, Based on the weight parameters, set the platform preset values ​​and dynamic adjustment values, make corrections according to job changes, and build a job-oriented weighted knowledge point recommendation priority list.

2. The method for recommending courses on the intelligent construction education platform according to claim 1, wherein: The construction of the knowledge graph includes: A preset knowledge point library uses a tree-like classification structure to construct multiple knowledge point nodes, and configures each knowledge point's unique identifier, name, category, set of prerequisite knowledge points, and job adaptation weight.

3. The method for recommending courses on the intelligent construction education platform according to claim 2, wherein: The multi-level association includes: Based on the chapter task content set in the intelligent construction education platform, a many-to-many mapping is performed between the set multiple branch tasks and the relevant knowledge points in the knowledge point library, and a bidirectional searchable index relationship between chapters, tasks, and knowledge points is maintained in the graph.

4. The method for recommending courses on the intelligent construction education platform according to claim 3, wherein: The generating of the course recommendation result includes: All candidate courses that match the knowledge points corresponding to the weight of each comprehensive knowledge point are retrieved from the course database, multi-dimensional priority sorting is performed, the comprehensive recommendation score is calculated, and a candidate course set is established.

5. The method for recommending courses on an intelligent construction education platform according to any one of claim 4, wherein: The calculation of the comprehensive recommendation score includes: The three factors, namely, the comprehensive weight value of knowledge points, the global completion rate of the course in the platform's historical data, and the current students' learning preference value for the course, are weighted and synthesized into a recommended score according to a set ratio.

6. The method for recommending courses on the intelligent construction education platform according to claim 5, characterized in that: The real-time optimization recommendation logic using feedback includes: After the students complete the recommended course, they will be re-evaluated for the side tasks associated with the course and their score rate on the side tasks will be calculated; If the score rate is higher than the threshold set by the platform, the knowledge points associated with the side quest will be removed from the list to be strengthened and will no longer participate in the next round of recommendations; If the score rate is lower than the score threshold, the knowledge point will be maintained in a high priority state, triggering the recommendation iteration logic, changing the course type, difficulty level and presentation method according to the original recommendation record, and re-outputting the recommendation results.

7. A course recommendation system for an intelligent construction education platform, using the course recommendation method for an intelligent construction education platform as described in any one of claims 1 to 6, characterized in that: It includes a knowledge graph construction module (100), a weak knowledge point identification module (200), a job adaptation and integration module (300), a multi-dimensional course recommendation module (400), and a feedback and iterative optimization module (500); The knowledge graph construction module (100) is used to read the knowledge point library and chapter task information when initializing the course update, build a multi-level many-to-many mapping graph structure, and generate a bidirectional searchable index between tasks, chapters and knowledge points for subsequent recommendation and tracing; The weak knowledge point identification module (200) is used to determine whether a knowledge point is to be strengthened based on the comparison between the score and the score threshold after the student completes the branch task, calculate the weakness weight in combination with the task score ratio, and update it into the student's knowledge point weakness portrait; The job adaptation fusion module (300) is used to call the enterprise job database to obtain the knowledge point weight of the target job, perform linear weighting on the identified knowledge point weaknesses, output a comprehensive weight, and dynamically modify the weight parameter according to job changes; The multi-dimensional course recommendation module (400) is used to screen candidate courses from the course library according to comprehensive weights, sort them by weighted scores based on knowledge point matching, course completion rate and student type preference, and output a recommendation list after screening out courses that are below a set score threshold; The feedback and iterative optimization module (500) is used to trigger a reassessment after the trainee completes the recommended course, and if the score rate is higher than the score threshold, the mastery status is updated; If the requirements are not met, the course type will be switched to enter the next round of recommendations until the requirements are met and the round limit is reached.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent construction education platform course recommendation method described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent construction education platform course recommendation method described in any one of claims 1 to 6 are implemented.

Images