High vocational course content recommendation method and system based on big data analysis

Abstract

The invention relates to the technical field of education content recommendation, in particular to a higher vocational course content recommendation method and system based on big data analysis, and the method comprises the following steps: obtaining course task labels and matching knowledge points, extracting task-type knowledge points, analyzing post responsibility information, and delimiting post capability levels. Learning behavior records are recognized, silent learning behaviors are detected, capability attenuation is evaluated, content pushing priority is adjusted, operation intensity is extracted, a pushing period is adjusted, and a resource putting adjustment result is generated. According to the method, the matching relation between the task labels and the knowledge points is constructed, post responsibility grade division and the learning behavior response state are combined, the adaptation accuracy between the course content and the ability requirement is improved, the push rhythm and the content priority ranking of the recommended content are optimized by utilizing an ability attenuation evaluation and learning load adjustment mechanism, and the recommendation efficiency is improved. Course resource distribution better fits learning rhythm and post guidance, and the dynamic response capability of a recommended path to an individual state is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of educational content recommendation, and particularly to a method and system for recommending higher vocational course content based on big data analysis. Background Art

[0002] The technical field of educational content recommendation includes recommendation methods that target individual learner characteristics and behavioral data, and perform personalized course content push and organization based on the teaching resource structure and learning path model. The core content focuses on learner data collection, feature modeling, content tag extraction, course resource classification, learning path matching, and recommendation mechanisms. By analyzing learners' historical learning behaviors, current learning status, and resource usage, content distribution and resource scheduling are realized in an educational informatization platform, and are applied to various scenarios such as online education platforms, vocational education systems, and intelligent learning systems, supporting data-driven teaching decision-making and personalized content configuration, and involving the construction of data modeling, feature calculation, resource structure encoding, recommendation rule formulation, and intelligent push processes.

[0003] Among them, a method for recommending higher vocational course content based on big data analysis refers to a technical solution that addresses the problem of course content adaptability in the teaching system of vocational colleges. By using a resource annotation mechanism based on teaching tasks and student learning behavior trajectory data, combined with content structure tags and job ability standards, a multi-level course resource recommendation path is generated. The method covers technical matters such as task behavior data collection, small unit learning module annotation, establishment of a course resource classification system, extraction of job ability indicators, construction of the mapping relationship between course content and vocational ability, generation of course recommendation paths, and ranking of recommendation priorities. Specifically, it is designed and implemented through a job task analysis model, a course content structured decomposition model, a learning task completion degree analysis indicator, and a content recommendation logic rule.

[0004] In traditional higher vocational course content recommendation technologies, the content adaptation mechanism relies on the resource classification structure and label matching method, lacking a structural integration of the teaching task objectives and job responsibilities logic, resulting in the recommended content not covering the task completion ability requirements, causing a separation between the recommendation path and the vocational ability training goal. In terms of behavior response monitoring, click frequency or access path is used as the benchmark for determining the behavior state, ignoring the structural dependence of the task stage on the behavior response, resulting in an offset in behavior missing recognition. In resource delivery control, a fixed strategy or the content completion rate is used as the rhythm reference index, without considering the differences in behavior density and cognitive load, resulting in resource accumulation or push delay, reducing the acceptance efficiency of students in the dynamic learning process and limiting the adaptability and effectiveness in vocational education applications. Summary of the Invention

[0005] The object of the present invention is to solve the disadvantages existing in the prior art, and a method and system for recommending higher vocational course content based on big data analysis are proposed.

[0006] To achieve the above object, the present invention adopts the following technical solutions: A method for recommending higher vocational course content based on big data analysis, comprising the following steps: S1: Obtain the task target verbs, behavioral result keywords and cognitive level description phrases in the higher vocational course teaching task text, construct a course intention label structure tuple, compare and calculate the matching degree with each knowledge point in the course syllabus, and obtain a task-based knowledge point set; S2: Call the task-based knowledge point set, extract the number of tasks, the number of operation processes and the independent permission level in the job responsibility text, identify the operation complexity and the scope of responsibility control of each responsibility item, delimit the boundary of the job ability level, and generate a job grading threshold; S3: Call the job grading threshold, identify the task content of each job level, collect the click, interaction and submission records of each student in the learning task execution log, compare the preset behavior types with the behavior log trigger status in the task stage, mark the untriggered behavior, and obtain a silent behavior record; S4: According to the task-based knowledge point set and the silent behavior record, extract the last trigger time, the number of operations and the skill maintenance interval parameters of the corresponding course content of each knowledge point of the student, evaluate the attenuation degree of the corresponding ability, and adjust the recommendation priority of the corresponding course content to obtain a recommendation list adjustment record.

[0007] As a further solution of the present invention, the task-based knowledge point set includes a task target type label, a cognitive level label, and an achievement result type label. The job grading threshold is specifically a job ability level interval, a task level boundary parameter, and a course docking label. The silent behavior record includes the untriggered behavior stage number, the behavior type missing label, and the task stagnation duration parameter. The recommendation list adjustment record includes the knowledge point recommendation weight value, the compensation priority sorting value, and the ability attenuation marking item.

[0008] As a further solution of the present invention, the obtaining steps of the task-based knowledge point set are specifically as follows: S111: Obtain the task target verbs, behavioral result keywords and cognitive level description phrases in the higher vocational course teaching task text, construct a course intention label structure tuple, and obtain a task semantic label set; S112: According to the task semantic label set, extract the title field of each knowledge point in the course syllabus, compare the semantic similarity of the keywords in each label tuple with the words in the knowledge point title, calculate the label coverage intensity value, analyze the label matching degree of each knowledge point, and obtain a label coverage intensity coefficient set; S113: Invoke the label coverage intensity coefficient set, compare the coverage intensity values of each knowledge point title field in the curriculum syllabus with the task label recognition threshold, divide them into task-based knowledge points and non-task-based knowledge points, and obtain the task-based knowledge point set.

[0009] As a further solution of the present invention, the steps for obtaining the post grading threshold are specifically as follows: S211: Invoke the task-based knowledge point set, extract the number of tasks, the number of operation processes, and the independent permission level in the job responsibilities text, perform a structural combination of the process length, operation level, and permission level extracted from each job task, establish a set of task ability index compositions, and obtain the post task intensity parameter set; S212: According to the post task intensity parameter set, analyze the ability level requirement boundaries of each job task, extract the operation process length, permission level, collaboration role weight value, post task quantity, task operation granularity level, and course recommendation level, calculate the post task intensity level value, combine the task number distribution interval within the post, obtain the level boundary switching condition, and obtain the post ability level boundary coefficient group; S213: According to the post ability level boundary coefficient group, invoke the course content structure label in the task-based knowledge point set, and match the required course content for the recommended path corresponding to the post ability level according to the matching relationship between the course content label level and the boundary interval, so as to obtain the post grading threshold.

[0010] As a further solution of the present invention, the steps for obtaining the silent behavior record are specifically as follows: S311: Invoke the post grading threshold, identify the task content of each post level, extract the task identification field and the task stage number field, and establish an index mapping between the post level and the stage task number to obtain the post task stage index set; S312: According to the post task stage index set, collect the click, interaction, and submission records of each student in the learning task execution log, extract the task-bound behavior type and the actual behavior trigger status, calculate the behavior missing degree value of the student in each task stage, and record the missing item type, task number, and behavior deviation degree to obtain the task stage behavior missing parameter set; S313: According to the task stage behavior missing parameter set, calculate the behavior missing duration of each student to obtain the silent behavior record.

[0011] As a further solution of the present invention, the steps for obtaining the recommended list adjustment record are specifically as follows: S411: According to the task-based knowledge point set and the silent behavior record, extract the last trigger time, operation times, and skill maintenance interval parameters of the course content corresponding to each knowledge point of the student to obtain the knowledge point execution basic parameter set; S412: Execute the basic parameter set according to the knowledge point, compare the last trigger time and skill maintenance interval parameter of each knowledge point, calculate the ratio of the deviation of the knowledge point operation times from the maintenance reference value, evaluate the attenuation degree of the corresponding ability of each knowledge point of the target student, and obtain the ability attenuation degree value; S413: According to the ability attenuation degree value, adjust the priority of the target course content in the recommendation list according to the course content mapped by the knowledge point, and obtain the recommendation list adjustment record.

[0012] As a further solution of the present invention, the method further includes: S5: Call the recommendation list adjustment record, extract the operation intensity parameter, resource call frequency and stay cycle of the student within a unit time, identify the learning behavior load status, and adjust the planned cycle of the course content push task to generate a resource delivery adjustment result; The resource delivery adjustment result includes a push cycle delay value, a task queue adjustment position, and a resource rhythm control parameter.

[0013] As a further solution of the present invention, the obtaining step of the resource delivery adjustment result is specifically: S511: Call the recommendation list adjustment record, extract the number of click operations, course resource call frequency and page stay cycle of the student within a unit time, and obtain the original parameter set of behavior load; S512: According to the original parameter set of behavior load, analyze the learning behavior activity of multiple students according to the number of click operations, resource call frequency and page stay cycle, and calculate the learning behavior load status to obtain the learning behavior load status value; S513: According to the learning behavior load status value, combined with the current planned push time of each course content in the recommendation list, adjust the planned cycle of the course content push task to obtain the resource delivery adjustment result.

[0014] A higher vocational course content recommendation system based on big data analysis, the higher vocational course content recommendation system based on big data analysis is used to execute the above-mentioned higher vocational course content recommendation method based on big data analysis, and the system includes: The course intention analysis module obtains the task target verb, behavior result keyword and cognitive level description phrase in the higher vocational course teaching task text, constructs a course intention label structure tuple, compares and calculates the matching degree with each knowledge point in the course outline, screens the knowledge points, and establishes a task-based knowledge point set; The job ability analysis module extracts the number of tasks, the number of operation processes, and the independent permission level from the job responsibility text based on the task-based knowledge point set, identifies the operation complexity and the scope of responsibility control for each responsibility item, delimits the boundary of the job ability level, and generates the job grading threshold; The behavior silence diagnosis module identifies the task content of each job level based on the job grading threshold, collects the online learning task execution log data of students, including clicks, interactions, and submissions, compares the preset behavior types in the task stage with the triggered status of the behavior log, marks the untriggered behaviors, and obtains the silence behavior records; The knowledge decay evaluation module extracts the last trigger time, the number of operations, and the skill maintenance interval parameters of the course content corresponding to each knowledge point of the student based on the task-based knowledge point set and the silence behavior records, calculates the decay degree of the skill corresponding to the knowledge point, dynamically adjusts the recommended priority of the course content associated with the knowledge point, and obtains the recommended list adjustment record; The load status regulation module extracts the operation density parameter, the resource call frequency, and the stay period of the student within a unit time based on the recommended list adjustment record, identifies the learning behavior load status of the student, and adjusts the planned period of the course content push task to generate the resource delivery adjustment result.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by constructing the matching relationship between task tags and knowledge points, combining the job responsibility level division and the learning behavior response status, the adaptation accuracy between the course content and the ability requirements is improved. By using the ability decay evaluation and learning load regulation mechanisms, the push rhythm of the recommended content and the content priority sorting are optimized, so that the distribution of course resources is more in line with the learning rhythm and job orientation, and the dynamic response ability of the recommended path to the individual state is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the main steps of the present invention; Figure 2 It is a flowchart for obtaining the task-based knowledge point set of the present invention; Figure 3 It is a flowchart for obtaining the job grading threshold of the present invention; Figure 4 It is a flowchart for obtaining the silence behavior records of the present invention; Figure 5 It is a flowchart for obtaining the recommended list adjustment record of the present invention; Figure 6 It is a flowchart for obtaining the resource delivery adjustment result of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0019] Please refer to Figure 1 , the present invention provides a technical solution: a method for recommending higher vocational curriculum content based on big data analysis, including the following steps: S1: Obtain the task target verbs, behavioral result keywords, and cognitive level description phrases in the higher vocational curriculum teaching task text, construct a curriculum intention label structure tuple, compare it with each knowledge point in the curriculum syllabus, calculate the matching degree, and obtain a task-based knowledge point set; S2: Call the task-based knowledge point set, extract the number of tasks, the number of operation processes, and the independent permission level in the job responsibility text, identify the operation complexity and responsibility control scope of each responsibility item, delimit the job ability level boundary, and generate a job grading threshold; S3: Call the job grading threshold, identify the task content of each job level, collect the click, interaction, and submission records of each student in the learning task execution log, compare the preset behavior types with the behavior log trigger status in the task stage, mark the untriggered behaviors, and obtain silent behavior records; S4: According to the task-based knowledge point set and the silent behavior records, extract the last trigger time, the number of operations, and the skill maintenance interval parameters of the course content corresponding to each knowledge point of the student, evaluate the attenuation degree of the corresponding ability, and adjust the recommended priority of the corresponding course content to obtain a recommended list adjustment record; S5: Call the recommended list adjustment record, extract the operation intensity parameter, resource call frequency, and stay cycle of the student within a unit time, identify the learning behavior load status, and adjust the planned cycle of the course content push task to generate a resource delivery adjustment result.

[0020] The task-based knowledge point set includes task objective type tags, cognitive level tags, and achievement result type tags. The job grading thresholds are specifically the job ability level range, task level boundary parameters, and course docking tags. The silent behavior record includes the behavior non-triggering stage number, behavior type missing tags, and task stagnation duration parameters. The recommended list adjustment record includes the knowledge point recommendation weight value, compensation priority sorting value, and ability decay marking items. The resource investment adjustment result includes the push cycle delay value, task queue adjustment position, and resource rhythm control parameters.

[0021] Please refer to Figure 2 , and the acquisition steps of the task-based knowledge point set are specifically as follows: S111: Obtain the task objective verbs, behavior result keywords, and cognitive level description phrases in the higher vocational course teaching task text, construct a course intention label structure tuple, and obtain the task semantic label set; Through the breakdown of specific examples in the higher vocational course teaching task text, obtain the three contents of task objective verbs, behavior result keywords, and cognitive level description phrases. Among them, the task objective verbs call the standard verb library in Bloom's cognitive taxonomy for lexical mapping. For example, map the "master" in the higher vocational software testing course task text "Students can master the method of writing test cases" to "apply". The behavior result keywords are extracted through the course evaluation standard text. For example, "coverage rate" in "The software test coverage rate reaches 90%" is the result keyword. The cognitive level description phrases call the six cognitive level definitions of Bloom. For example, "analyze" in "Students can analyze program code errors" is the level description word. According to the invocation and matching of the above three categories of vocabulary, construct a structure tuple for the course task text, and establish a specific structure tuple example as shown in Table 1: Table 1 Task intention label structure tuple table:

[0022] Table 1 lists specific examples of the task intention label structure tuple. Taking the first row tuple as an example, the task objective verb is "apply", the behavior result keyword is "coverage rate", and the cognitive level description phrase is "analyze". Through the above method, construct the label structure tuple of all course contents to obtain the task semantic label set.

[0023] S112: According to the task semantic label set, extract the title field of each knowledge point in the course outline, compare the semantic similarity between the keywords in each label tuple and the words in the knowledge point title, and use the formula: ; Calculate the label coverage intensity value, analyze the label matching degree of each knowledge point, and obtain the label coverage intensity coefficient set; Among them, represents the The label coverage intensity value of a knowledge point, represents the semantic similarity score between the target verb in the th label tuple and the th knowledge point keyword, represents the matching score between the action result keyword and the knowledge point, represents the label importance evaluation value of the th label tuple, is the cognitive hierarchy level value, is the preset level of the task corresponding to this knowledge point, represents the total number of label tuples of the course task intention, represents the knowledge point number currently being processed, represents the th label tuple serial number that matches the th knowledge point; Call the structural tuple data in Table 1, and call the title fields of each knowledge point in the course syllabus, such as "Test Case Design", "Functional Defect Analysis", "Automated Test Script Execution", etc., respectively, and conduct semantic similarity comparison with the keywords in the task label tuple, such as "application", "coverage rate", "analysis", etc., one by one. For example, by calculating the cosine similarity of word vectors, specific values are obtained 、 , and at the same time, call the expert scoring data of the course evaluation to obtain the label importance evaluation value . The expert scoring uses the Likert 5-level scoring method (1 point means unimportant, 5 points means very important). For example, the expert evaluation value for the label tuple (application, coverage rate, analysis) is 4, is the cognitive hierarchy level value of the current task label tuple. Taking Bloom's cognitive hierarchy as the standard, memory is 1, understanding is 2, application is 3, analysis is 4, evaluation is 5, and creation is 6. For example, "analysis" of the above tuple is 4, is the preset level of the task corresponding to the knowledge point, which is set through the task design document. For example, the cognitive level corresponding to "Test Case Design" is 3. Now, taking the knowledge point "Test Case Design" as an example, substitute the above parameters into the formula: ; Set , obtained by calculating the cosine similarity, , , , , then: ; Calculate other knowledge points in the same way to obtain the label coverage intensity value. By calculating all knowledge points one by one as described above and summarizing them, a set of label coverage intensity coefficients is obtained. Among them, the label coverage intensity value refers to the degree to which a certain knowledge point is semantically covered by multiple curriculum intention label structure tuples in the curriculum task system. This value is obtained by evaluating the semantic fit between the label verb and the result keyword and the title of the knowledge point, and combining the consistency of the task cognitive level, resulting in a continuous quantitative value result, which represents how many teaching tasks the current knowledge point has semantic relevance to and whether the association has teaching task structure consistency. It is used to help the system identify those content that truly has task-oriented attributes from all curriculum knowledge points, construct a task-based content set oriented to job ability requirements, and provide a curriculum foundation with clear structure and complete labels for subsequent job level mapping and path generation. The higher the label coverage intensity value, the more types of teaching tasks the knowledge point can support, the clearer the task structure, and the higher the priority in the recommended path. The formula effectively quantifies the association strength between the knowledge point and the task label by comprehensively considering semantic similarity, label importance, and cognitive level gap.

[0024] S113: Invoke the set of label coverage intensity coefficients, compare the coverage intensity value of each knowledge point title field in the curriculum syllabus with the task label recognition threshold, divide them into task-based knowledge points and non-task-based knowledge points, and obtain the set of task-based knowledge points; Invoke the calculated values. For example, the coverage intensity value of the knowledge point "Test Case Design" is 1.55, the knowledge point "Functional Defect Analysis" is 2.30, and the knowledge point "Automation Test Script Execution" is 0.95. The task label recognition threshold is determined based on the results of previous experimental tests. For example, for the label coverage intensity values of 100 knowledge points, the coverage intensity values of the first 50% of the knowledge points are concentrated in the range of 1.20 - 2.50, then 1.20 is taken as the threshold. By comparing the coverage intensity value of each knowledge point with this threshold, if the coverage intensity value of the knowledge point "Test Case Design" (1.55) is higher than the threshold (1.20), it is determined as a task-based knowledge point, and the value of "Automation Test Script Execution" (0.95) is lower than the threshold, so it is determined as a non-task-based knowledge point. By comparing all knowledge points one by one as described above, the knowledge points higher than the threshold are classified into the set of task-based knowledge points, and finally the set of task-based knowledge points is obtained.

[0025] Please refer to Figure 3 , and the specific steps for obtaining the job grading threshold are as follows: S211: Invoke the set of task-based knowledge points, extract the number of tasks, the number of operation processes, and the independent permission level in the job responsibility text, perform a structural combination of the process length, operation level, and permission level extracted from each job task, establish a set of task ability index compositions, and obtain the set of job task intensity parameters; Invoke the knowledge point data in the obtained task semantic tag set, such as "test case design", "functional defect analysis", "performance test execution", etc., and disassemble them item by item for the text content of the job responsibilities. For example, for the text of the job responsibilities of a software test engineer, "Responsible for software defect analysis and functional use case design, with a permission level of 3 and 5 operation processes", then call the number of tasks in this responsibility as 2 (defect analysis, use case design), the number of operation processes as 5, and the permission level is set to 3. By calling multiple texts of job responsibilities, complete the item-by-item extraction of the above data. After the extraction, call the number of process lines, permission level, and number of tasks, and combine and calculate these three data according to the actual structure required by the responsibilities. Taking the software test engineer position as an example, by calculating (2 tasks, 5 process lines, 3 permission levels), obtain the task ability index structure. The calculation process of the task intensity of this position is to multiply the number of tasks by the number of process lines to get the value 10, and then add the permission level value 3 to get the value 13, that is, the task intensity value of the position is 13. In the same way, calculate the task intensity values of other job responsibilities one by one, and summarize all the calculated task intensity values of the positions to form a task intensity parameter set of the positions.

[0026] S212: According to the task intensity parameter set of the positions, analyze the ability level requirement boundaries of each job responsibility task, extract the operation process length, permission level, cooperation role weight value, number of position tasks, task operation granularity level, and course recommendation level, and use the formula: ; Calculate the task intensity level value of the position, combine the distribution interval of the number of tasks within the position, obtain the level boundary switching condition, and obtain the position ability level boundary coefficient group; Among them, is the level intensity value of the th position task, is the operation process length of the th position task, is the permission level value of the th position task, is the count value of the th cooperation role in the th position task, is the weight value of the th cooperation role in the th position task, is the total number of tasks corresponding to the th position, is the operation granularity level value of the th position task, is the recommended level value of the course matched by the th position task, It is the index of the job task number, It is the index of the collaboration role number, It is the total number of collaboration roles under a single job task; Call the example values of the task intensity parameters for the three positions of software test engineer, software development engineer, and project manager, which are 13, 16, and 21 respectively. By calling the specific task intensity parameters of the three positions, further call the operation process lengths of each position one by one (5, 6, and 7 respectively), permission levels (3, 4, and 5 respectively), the number of collaboration roles (2, 3, and 4 respectively), and the weight values of the corresponding roles (senior role weight 0.8, intermediate role weight 0.5, junior role weight 0.3, take the average), the number of job tasks (2, 3, and 4 respectively), the task operation granularity level (software test engineer level 3, development engineer level 4, project manager level 5), and the course recommendation level (level 3, level 4, and level 5 respectively), and present the above data in the form of Table 2: Table 2 Job Responsibility Parameter Table:

[0027] As shown in Table 2, calculate the job task intensity level value by calling the parameters item by item , taking the software test engineer position as an example, call the process length , permission level , collaboration role count value , role weight , total number of tasks , operation granularity level , recommendation level , substitute into the formula for calculation: ; ; Double counting for other positions. For example, the intensity value of the software development engineer position is 45.0, and the intensity value of the project manager position is 43.2. Further call the task intensity level values of all positions, sort them according to the task intensity values, and divide the grade boundaries based on the previous experimental results. For example, those with intensity values greater than 45 are designated as the high - level ability grade interval, those between 40 and 45 are designated as the medium - level ability grade interval, and those below 40 are designated as the low - level ability grade interval. Based on these conditions, a group of position ability grade boundary coefficients is defined. Among them, the grade intensity value of a position task refers to a comprehensive index under the cross - action of multiple dimensions such as the task execution structure, permission requirements, collaboration load, and course matching difficulty of a single job responsibility task in a position, used to express the strength of the ability required for this task. This index reflects the internal complexity of the task itself, and through the collaboration weight and course matching error, it reflects the interference degree or adaptation cost to the learning path design. By grading and sorting different tasks according to this intensity value, a position ability grade boundary is constructed. When the intensity values of multiple tasks are in a similar interval, they will be classified into the same grade; when there are obvious gradients in the intensity values, they are used to define the grade switching threshold and guide the grade adaptation matching logic of the course content, improving the matching accuracy of course stratification and ability fitting in the recommended path. Through multi - dimensional calculations such as the operation process, permission level, collaboration role, task operation granularity, and recommended grade, a refined boundary coefficient for the matching of job responsibilities and course content is obtained.

[0028] S213: According to the group of position ability grade boundary coefficients, call the course content structure labels in the task - type knowledge point set. According to the matching relationship between the course content label grade and the boundary interval, match the required course content for the recommended path of the corresponding position ability grade to obtain the position grading threshold. Call the grade boundaries corresponding to the three positions of software test engineer, software development engineer, and project manager calculated by paragraph. They are low - level, medium - level, and high - level respectively. Further call the course content structure labels of the knowledge points in the task - type knowledge point set. Specifically, "test case design" is medium - level, "functional defect analysis" is medium - level, "performance test execution" is high - level, etc. Call the position ability grade and the knowledge point label grade for one - by - one comparison operations. Taking the software test engineer as an example, if its ability grade is low - level, then match the knowledge points with the low - level label grade. After performing the matching operation for each position one by one, obtain the course knowledge point content corresponding to each position ability grade. Further bind the position ability grade and the matching knowledge point content. Specifically, the software test engineer corresponds to the "basic defect record" knowledge point, the software development engineer corresponds to the "test case design" knowledge point, and the project manager corresponds to the "performance test execution" knowledge point. In this way, a position grading threshold is established.

[0029] Please refer to Figure 4 , and the specific steps for obtaining the silent behavior record are as follows: S311: calling the position classification threshold, identifying the task content of each position level, extracting the task identification field and the task stage number field, and establishing an index mapping between the position level and the stage task number to obtain the position task stage index set; Taking the software testing positions of "junior, intermediate, and senior" as examples, the call is made by extracting the task identification fields and task stage number fields involved in the specific task content under each position level to achieve one-by-one disassembly. For example, the "task identification field" in the task content corresponding to the junior position is "defect record", and the task stage number field is "stage 1"; the task identification field corresponding to the intermediate position is "test case design", and the task stage number field is "stage 2"; the task identification field corresponding to the senior position is "performance testing", and the task stage number field is "stage 3". The index mapping operation of the position level and the stage task number is further performed. By calling the position level data and the task stage number field data one by one, taking the junior position "stage 1" as an example, the "junior" position level is called and mapped and marked as "junior-stage 1". The corresponding relationship between other position levels and stage numbers is obtained through the above mapping operation, as shown in Table 3: Table 3: Mapping table of job level and stage task number:

[0030] As shown in Table 3, the mapping indexes of all job levels and stage task numbers are established one by one, and all mapping index entries are summarized to form a job task stage index set.

[0031] S312: According to the job task stage index set, collect the click, interaction and submission records of each student in the learning task execution log, extract the task binding behavior type and the actual behavior triggering status, and use the formula: ; Calculate the students' behavior missing degree value at each task stage, record the missing item type, task number and behavior deviation degree, and obtain the behavior missing parameter set of the task stage; in, For the Students in The behavior deficiency degree value of each task stage, For the Students in In the task phase The item should execute the behavior state value, For the Students in In the task phase The actual completion behavior status value of the item. For the Students in The behavior impact weight value of the th behavior in a task stage, is the number of preset behavior items in each task stage, is the th student's behavior trigger delay time value in the th task stage, is the behavior trigger tolerance time constant set by the system, is the student number index, is the task stage number index, is the behavior item number index; Taking "Primary - Stage 1" in Table 3 as an example, for the student with student number in Stage 1, call the click, interaction, and submission records of this student in the learning task execution log. Among them, the click behavior includes page access actions; the interaction behavior includes leaving messages in the discussion area; the submission behavior includes task submission actions. Call each behavior record and extract the task - bound behavior types respectively. For example, the click behavior is bound to "page access", the interaction behavior is bound to "message interaction", and the submission behavior is bound to "task submission". And extract the actual behavior trigger status data of this student one by one. Among them, the click behavior is completed ( ), the interaction behavior is not completed ( ), the submission behavior is not completed ( ); the preset behavior status of the task stage is set to click 1, interaction 1, submission 1 ( ); the impact weight value of each behavior is set according to expert scoring. For example, the weight of page access is 0.3, the weight of message interaction is 0.4, and the weight of task submission is 0.3; further call the behavior trigger delay time. The actual delay of the student is , and the system behavior trigger tolerance time constant is set to ; Substitute the above parameters into the formula for calculation: ; The calculation process is: ; Calculate the behavior missing degree values of other students in each task stage in the same way, and record item by item that the type of behavior missing item is "interaction behavior", "submission behavior", the task number is "Stage 1", and the behavior deviation degree is 0.135 to obtain the behavior missing parameter set for the task stage. Among them, the behavior missing degree value refers to the quantitative value of the deviation degree of the response of a student to the preset behavior items in a certain task stage. The higher the value, the lower the expected behavior execution rate in that stage, the more obvious the behavior gap, indicating that the student's participation, responsiveness or task status at the current task node presents "silence" or "interruption". This indicator, as the core quantity for judging "silent behavior", will be directly used to identify the behavior vacuum in the stage, judge the discontinuous learning area, and serve as the input for the behavior activation trigger condition or the recommended task rebound control parameter. It is the core numerical result in the silent behavior recognition mechanism, ensuring that the behavior monitoring has dynamic comparability in terms of task granularity, time granularity and response structure, and providing a data basis for tracking students' learning progress and adjusting course content recommendations. The formula comprehensively calculates the differences in preset and actual completed behavior states, weights, and delays, reflecting the quantification degree of behavior missing.

[0032] S313: According to the behavior missing parameter set for the task stage, calculate the behavior missing duration of each student to obtain the silent behavior record; Taking the student number as an example, call the behavior missing degree value of 0.135 for Stage 1, further call the standard behavior trigger time preset for the task stage. For example, the standard trigger time for the interaction behavior in Stage 1 is 5 minutes, and the standard trigger time for the submission behavior is 10 minutes, and call the actual completion times of the interaction behavior and submission behavior in the student's actual behavior log. Assume that the student's interaction behavior is actually completed at 12 minutes and the submission behavior is completed at 15 minutes; call the preset standard time and the actual completion time respectively and perform subtraction operations item by item. The missing duration of the interaction behavior is the actual time of 12 minutes minus the standard time of 5 minutes, resulting in a missing duration of 7 minutes; the missing duration of the submission behavior is the actual time of 15 minutes minus the standard time of 10 minutes, resulting in a missing duration of 5 minutes; perform the above missing duration calculation process item by item, and obtain the behavior missing duration data of other students in other stages by repeating the above calculation, and summarize the missing duration record data of each item to form the silent behavior record.

[0033] Please refer to Figure 5 , and the specific steps for obtaining the recommended list adjustment record are as follows: S411: According to the task-based knowledge point set and the silent behavior record, extract the last trigger time, operation times and skill maintenance interval parameters of the course content corresponding to each knowledge point of the student to obtain the knowledge point execution basic parameter set; Call the task-based knowledge point data obtained in the previous article, such as "test case design", "functional defect analysis", etc., and the silent behavior record data such as the student number The missing time in "Test Case Design" is 7 minutes. The actual data of the student learning log is called to extract the specific timestamp of the last time the course content of each knowledge point was accessed and executed by the student. For example, the last trigger of the "Test Case Design" knowledge point was 14:00 on December 20, 2024, and the "Functional Defect Analysis" was 09:30 on December 21, 2024. The actual number of operations of each knowledge point is called, for example, the number of operations of the "Test Case Design" knowledge point is 3 times, and the number of operations of the "Functional Defect Analysis" is 2 times. The knowledge point skill maintenance interval parameters specified in the industry skill standards are called, for example, the maintenance interval of "Test Case Design" is 7 days, and the maintenance interval of "Functional Defect Analysis" is 10 days. The specific parameter data of the above calls and extractions are shown in Table 4: Table 4 Basic parameters for knowledge point execution:

[0034] As shown in Table 4, parameter calls and data are summarized for each knowledge point and organized into a basic parameter set for knowledge point execution.

[0035] S412: According to the knowledge point execution basic parameter set, the last trigger time of each knowledge point is compared with the skill maintenance interval parameter, the ratio of the number of knowledge point operations deviating from the maintenance benchmark value is calculated, the attenuation degree of the ability corresponding to each knowledge point of the target student is evaluated, and the ability attenuation degree value is obtained; Call the data in Table 4, for the knowledge point "Test Case Design", by calling the current evaluation date 12:00 on December 28, 2024 and the last trigger time 14:00 on December 20, 2024, the time difference is calculated one by one, and the trigger interval is about 8 days. Further call the skill maintenance interval parameter 7 days, perform the subtraction operation between the trigger interval and the skill maintenance interval, and calculate the excess maintenance interval value as 1 day. By calling the operation number 3 times and calling the maintenance benchmark value specified in the skill standard 4 times, calculate the proportion of the operation number deviation from the maintenance benchmark value for each knowledge point, and use (4 times -3 times) / 4 times is calculated as 0.25 (25%); in the same way, the "Functional Defect Analysis" knowledge point is called. The current date 12:00 on December 28, 2024 and 09:30 on December 21, 2024 are subtracted to 7 days and 3 hours, which is about 7.13 days. The maintenance interval is 10 days, and the subtraction is -2.87 days, which does not exceed the maintenance interval. The operation is called 2 times, and the baseline value is maintained 3 times. The deviation from the baseline value is calculated as (3-2) / 3, which is about 0.33 (33%); the deviation ratio values calculated from all knowledge points are summarized to obtain the capability attenuation value.

[0036] S413: According to the ability attenuation degree value, adjust the priority of the target course content in the recommendation list according to the course content mapped by knowledge points, and obtain the recommendation list adjustment record; The attenuation degree value of "test case design" is 25%, and the attenuation degree value of "functional defect analysis" is 33%. Call the knowledge point order in the course recommendation list one by one. For example, the current recommended order of knowledge points in the recommendation list is: "functional defect analysis" is at serial number 2, and "test case design" is at serial number 4. After calling the attenuation degree value data, perform comparison operations one by one. Taking the priority threshold corresponding to the attenuation degree value of 25% as 30% as an example, by judging that 25% is lower than the 30% threshold, the corresponding course recommendation priority remains unchanged; the attenuation degree value of 33% exceeds the 30% threshold. The original sorting position of the corresponding knowledge point "functional defect analysis" is serial number 2, and it is adjusted to a higher priority, that is, serial number 1 position. Execute the above comparison and judgment operations item by item, complete the adjustment of the knowledge point positions in the recommendation list according to the attenuation degree value, and form a recommendation list adjustment record.

[0037] Please refer to Figure 6 , and the specific steps for obtaining the resource investment adjustment result are as follows: S511: Call the recommendation list adjustment record, extract the number of click operations, the frequency of course resource calls, and the page stay period of the student within a unit time, and obtain the original parameter set of behavior load; By calling the student number The adjusted course recommendation order data, such as the knowledge point "functional defect analysis" is adjusted to serial number 1 position, and "test case design" is still at serial number 4 after adjustment. Further extract the operation log of this student on the course platform, and call the specific number of click operation data, the frequency of course resource call data, and the page stay period data within a unit time (taking 1 hour as a unit, such as from 10:00 to 11:00 on December 28, 2024) one by one. For example, the number of click operations within 1 hour is 15 times, the frequency of resource calls is 5 times, and the average page stay period is 180 seconds. Call and extract the data within other time periods in a similar way. The example is shown in Table 5: Table 5 Original parameter table of behavior load:

[0038] As shown in Table 5, by calling the data records of each student within each unit time one by one, the original parameter set of behavior load is obtained by summarization.

[0039] S512: According to the original parameter set of behavior load, analyze the learning behavior activity of multiple students according to the number of click operations, the frequency of resource calls, and the page stay period, and calculate the learning behavior load status to obtain the learning behavior load status value; Taking the data of student number 1 in Table 5 as an example, call the parameters of the number of click operations, the frequency of resource calls, and the page stay period, and perform the numerical analysis operation of the parameters one by one. The number of click operations, such as 15 times and 12 times, is compared with the set click frequency activity threshold of 10 times respectively. If it exceeds 10 times, it is determined as high activity, and if it is less than or equal to 10 times, it is determined as low activity. Therefore, the time period from 10:00 to 11:00 is high activity, and the time period from 11:00 to 12:00 is high activity; the resource call frequencies are called 5 times and 3 times respectively, and the resource call frequency activity threshold is 3 times. If it is greater than 3 times, it is high active, and if it is less than or equal to 3 times, it is low active. Then the former is determined as high active and the latter is low active; the page stay periods are called 180 seconds and 240 seconds respectively, and the standard threshold of the stay period is 200 seconds. Compare the cycle duration with the threshold. If the cycle is less than 200 seconds, it is determined as a lower stay period, and if it is higher than 200 seconds, it is determined as a higher stay period. Therefore, the former is a lower cycle and the latter is a higher cycle. Perform the above numerical comparison and analysis one by one, and record the parameters with high activity as 1 and the low activity as 0. Accumulate the above numerical values one by one. For example, the activity total from 10:00 to 11:00 is 2 (high click, high resource call) and a low stay period value, and the overall activity value is relatively high; the activity value from 11:00 to 12:00 is 1 (high click, low resource call) and a higher stay period, and the overall activity value is relatively low. Calculate the behavior load status values of each student in each time period item by item to obtain the learning behavior load status value.

[0040] S513: According to the learning behavior load status value, combined with the current planned push time of each course content in the recommendation list, adjust the planned cycle of the course content push task to obtain the resource placement adjustment result; Call the load status data of student number 1. For example, the behavior load status value from 10:00 to 11:00 is relatively high, and the load status value from 11:00 to 12:00 is relatively low. Further call the current planned push time of each course content in the recommendation list. For example, the current push time of the "Functional Defect Analysis" knowledge point is 11:00 on December 28, 2024, and the "Test Case Design" knowledge point is 12:00 on December 28, 2024. By performing a one-by-one comparison of the behavior load status value and the corresponding push time, adjust the subsequent push content corresponding to the time period from 10:00 to 11:00 with a relatively high behavior load status value. Push the content originally scheduled to be pushed at 11:00 to 10:30 in advance, and postpone the course push content corresponding to the time period from 11:00 to 12:00 with a relatively low behavior load status value from 12:00 to 12:30. Complete the above push plan cycle adjustment calculation operation one by one. The actual push time after adjustment is shown in Table 6 specifically: Table 6 Resource Placement Adjustment Result Table:

[0041] As shown in Table 6, all adjusted push times are summarized to form the resource delivery adjustment result.

[0042] A system for recommending higher vocational course content based on big data analysis, which is used to implement the higher vocational course content recommendation method based on big data analysis, and includes: The course intention parsing module obtains the task target verbs, behavior result keywords and cognitive level description phrases in the teaching task text of the higher vocational course, constructs the course intention label structure tuple, compares the label structure tuple with each knowledge point in the course outline and calculates the matching degree, screens the knowledge points, and establishes a task-based knowledge point set; The job competency analysis module extracts the number of tasks, number of operation processes and independent authority levels in the job responsibility text based on the task-based knowledge point set, identifies the operation complexity and responsibility control scope of each responsibility item, defines the job competency level boundary, and generates job classification thresholds; The behavioral silence diagnosis module identifies the task content of each job level based on the job classification threshold, and collects the students' online learning task execution log data, including clicks, interactions, and submissions, compares the preset behavior types in the task stage with the behavior log trigger status, marks untriggered behaviors, and obtains silent behavior records; The knowledge decay assessment module extracts the last trigger time, operation times and skill maintenance interval parameters of each knowledge point corresponding to the course content of the student based on the task-based knowledge point set and silent behavior records, calculates the decay degree of the skills corresponding to the knowledge point, dynamically adjusts the recommendation priority of the course content associated with the knowledge point, and obtains the adjustment record of the recommendation list; The load status control module adjusts the records based on the recommendation list, extracts the students' operation intensity parameters, resource call frequency and stay period per unit time, identifies the students' learning behavior load status, and adjusts the planned cycle of the course content push task to generate resource delivery adjustment results.

[0043] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for recommending higher vocational course content based on big data analysis, characterized in that, It includes the following steps: S1: Obtain the task objective verbs, behavioral result keywords, and cognitive level description phrases in the higher vocational curriculum teaching task text, construct a curriculum intention label structure tuple, compare it with each knowledge point in the curriculum syllabus, calculate the matching degree, and obtain the task-based knowledge point set; S2: Invoke the task-based knowledge point set, extract the number of tasks, the number of operation processes, and the independent permission level in the job responsibility text, identify the operation complexity and responsibility control scope of each responsibility item, delimit the job ability level boundary, and generate the job grading threshold; S3: Invoke the job grading threshold, identify the task content of each job level, collect the click, interaction, and submission records of each student in the learning task execution log, compare the preset behavior types in the task stage with the behavior log trigger status, mark the untriggered behaviors, and obtain the silent behavior record; S4: According to the task-based knowledge point set and the silent behavior record, extract the last trigger time, operation times, and skill maintenance interval parameters of the corresponding curriculum content for each knowledge point of the student, evaluate the attenuation degree of the corresponding ability, and adjust the recommended priority of the corresponding curriculum content to obtain the recommended list adjustment record.

2. The method for recommending higher vocational course content based on big data analysis according to claim 1, wherein The task-based knowledge point set includes task objective type labels, cognitive level labels, and achievement result type labels. The job grading threshold is specifically the job ability level interval, task level boundary parameter, and curriculum docking label. The silent behavior record includes the untriggered behavior stage number, behavior type missing label, and task stagnation duration parameter. The recommended list adjustment record includes the knowledge point recommended weight value, compensation priority sorting value, and ability attenuation marking item.

3. The method for recommending higher vocational course content based on big data analysis according to claim 1, characterized in that The specific steps for obtaining the task-based knowledge point set are as follows: S111: Obtain the task objective verbs, behavioral result keywords, and cognitive level description phrases in the higher vocational curriculum teaching task text, construct a curriculum intention label structure tuple, and obtain the task semantic label set; S112: According to the task semantic label set, extract the title field of each knowledge point in the curriculum syllabus, compare the similarity of the meanings of the keywords in each label tuple and the words in the knowledge point title, calculate the label coverage intensity value, analyze the label matching degree of each knowledge point, and obtain the label coverage intensity coefficient set; S113: Invoke the label coverage intensity coefficient set, compare the coverage intensity value of the title field of each knowledge point in the curriculum syllabus with the task label recognition threshold, divide them into task-based knowledge points and non-task-based knowledge points, and obtain the task-based knowledge point set.

4. The method for recommending higher vocational course content based on big data analysis according to claim 3, wherein The specific steps for obtaining the job grading threshold are as follows: S211: Invoke the task-based knowledge point set, extract the number of tasks, the number of operation processes, and the independent permission level in the job responsibility text, perform a structural combination of the process length, operation level, and permission level extracted from each job task, establish a task ability index composition set, and obtain the job task intensity parameter set; S212: According to the set of post task intensity parameters, analyze the ability level requirement boundaries of each job responsibility task, extract the operation process length, authority level, collaboration role weight value, number of post tasks, task operation granularity level, and course recommendation level, calculate the post task intensity level value, combine the task number distribution interval within the post, obtain the level boundary switching condition, and acquire the post ability level boundary coefficient group; S213: According to the post ability level boundary coefficient group, call the course content structure tags in the task-based knowledge point set, and based on the matching relationship between the course content tag level and the boundary interval, match the required course content for the recommended path of the corresponding post ability level to obtain the post grading threshold.

5. The method for recommending higher vocational course content based on big data analysis according to claim 4, wherein The specific steps for obtaining the silent behavior record are as follows: S311: Call the post grading threshold, identify the task content of each post level, extract the task identification field and the task stage number field, and establish the index mapping between the post level and the stage task number to obtain the post task stage index set; S312: According to the post task stage index set, collect the click, interaction, and submission records of each student in the learning task execution log, extract the task-bound behavior type and the actual behavior trigger status, calculate the behavior missing degree value of the student in each task stage, and record the missing item type, task number, and behavior deviation degree to obtain the task stage behavior missing parameter set; S313: According to the task stage behavior missing parameter set, calculate the behavior missing duration of each student to obtain the silent behavior record.

6. The method for recommending higher vocational course content based on big data analysis according to claim 5, characterized in that, The specific steps for obtaining the recommended list adjustment record are as follows: S411: According to the task-based knowledge point set and the silent behavior record, extract the last trigger time, number of operations, and skill maintenance interval parameters of the course content corresponding to each knowledge point of the student to obtain the knowledge point execution basic parameter set; S412: According to the knowledge point execution basic parameter set, compare the last trigger time and the skill maintenance interval parameter of each knowledge point, calculate the ratio of the number of knowledge point operations deviating from the maintenance benchmark value, evaluate the attenuation degree of the ability corresponding to each knowledge point of the target student, and obtain the ability attenuation degree value; S413: According to the ability attenuation degree value, adjust the priority of the target course content in the recommended list according to the course content mapped by the knowledge point to obtain the recommended list adjustment record.

7. The method for recommending higher vocational course content based on big data analysis according to claim 1, characterized in that, The method further includes: S5: Call the recommended list adjustment record, extract the operation intensity parameter, resource call frequency, and stay period of the student within a unit time, identify the learning behavior load status, and adjust the planned period of the course content push task to generate a resource delivery adjustment result; The resource delivery adjustment result includes the push cycle delay value, task queue adjustment position, and resource rhythm control parameter.

8. The method for recommending higher vocational curriculum content based on big data analysis according to claim 7, wherein, The specific steps for obtaining the resource delivery adjustment result are as follows: S511: Call the recommended list adjustment record, extract the number of click operations, course resource call frequency, and page stay period of the student within a unit time to obtain the original behavior load parameter set; S512: According to the original parameter set of the behavior load, analyze the learning behavior activity of multiple students based on the number of click operations, the frequency of resource calls, and the page stay period, calculate the learning behavior load status, and obtain the learning behavior load status value; S513: According to the learning behavior load status value, combine the current planned push time of each course content in the recommendation list, adjust the planned period of the course content push task, and obtain the resource placement adjustment result.

9. A higher vocational course content recommendation system based on big data analysis, characterized in that, The system is used to implement the higher vocational course content recommendation method based on big data analysis according to any one of claims 1-8. The system includes: The course intention parsing module obtains the task target verb, the behavior result keyword, and the cognitive level description phrase in the higher vocational course teaching task text, constructs the course intention label structure tuple, compares and calculates the matching degree of the label structure tuple with each knowledge point in the course syllabus, filters the knowledge points, and establishes the task-based knowledge point set; The job ability analysis module extracts the number of tasks, the number of operation processes, and the independent permission level in the job responsibility text based on the task-based knowledge point set, identifies the operation complexity and the job control scope of each responsibility item, delimits the job ability level boundary, and generates the job grading threshold; The behavior silence diagnosis module identifies the task content of each job level based on the job grading threshold, collects the online learning task execution log data of students, including clicks, interactions, and submissions, compares the preset behavior types with the behavior log trigger status in the task stage, marks the untriggered behaviors, and obtains the silence behavior record; The knowledge decay evaluation module extracts the last trigger time, the number of operations, and the skill maintenance interval parameters of the course content corresponding to each knowledge point of the student based on the task-based knowledge point set and the silence behavior record, calculates the decay degree of the skill corresponding to the knowledge point, dynamically adjusts the recommendation priority of the course content associated with the knowledge point, and obtains the recommendation list adjustment record; The load status regulation module extracts the operation intensity parameter, the resource call frequency, and the stay period of the student within a unit time based on the recommendation list adjustment record, identifies the learning behavior load status of the student, and adjusts the planned period of the course content push task to generate the resource placement adjustment result.

Images