A vocational education curriculum development method and system

Abstract

The present application provides a vocational education curriculum development method and system thereof, which obtains time series data of teacher evaluation values, project experience, course completion and skill level of students within a set historical time period; obtains the above estimated data; stores the above estimated data in course activities; synchronizes course activities to the course activity space, and generates course requirements to be assigned; establishes course resources; inputs course resources and course requirements to be assigned into an adaptive evaluation network; obtains matching evaluation results; completes association binding with students through the matching evaluation results, and generates corresponding course packages; the present application can not only strengthen the cultivation of students' professional abilities and actual project operation capabilities in this way, but also makes the course development more targeted and accurate, and can meet the rapidly changing industry needs and personalized learning needs.

Description

Technical Field

[0001] The present application relates to the technical field of curriculum development, and specifically to a vocational education curriculum development method and system thereof. Background Art

[0002] In the current vocational education field, curriculum development faces many challenges. On the one hand, traditional curriculum development methods often focus on the systematic teaching of subject knowledge, while ignoring students' professional ability and actual project operation ability. On the other hand, due to the individual data differences of each student, the existing curriculum development methods lack pertinence and lack consideration of the potential correlation between data across time and space dimensions. It can be seen that the existing curriculum development methods are difficult to meet the rapidly changing industry needs and personalized learning needs.

[0003] Therefore, the purpose of the present invention is to provide a vocational education curriculum development method and system thereof to solve the problems existing in the prior art. Summary of the invention

[0004] The purpose of this application is to provide a vocational education curriculum development method and system, which can not only strengthen the cultivation of students' professional ability and practical project operation ability, but also fully consider the correlation between data across time and space dimensions, so that the developed courses can meet the rapidly changing industry needs and personalized learning needs.

[0005] In a first aspect, an embodiment of the present application provides a vocational education curriculum development method, comprising the following steps:

[0006] Obtain the time series data of teacher evaluation values, project experience, course completion and skill level of students within a set historical time period;

[0007] After preprocessing the teacher evaluation value time series data, project experience time series data, course completion time series data and skill level time series data, the pre-trained prediction model is input to obtain the student's estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data in a future set time period;

[0008] The prediction model is obtained by training the graph heterogeneous time representation model through the time series data samples of students' history teacher evaluation values, history project experience, history course completion and history skill level.

[0009] Obtain course activities, store estimated teacher evaluation value data, estimated project experience data, estimated course completion data, and estimated skill level data in course activities, and course activities are automatically created through course requirements;

[0010] Synchronize course activities to the course activity space to generate course requirements to be assigned;

[0011] Establish course resources, which are resources built from historical project data. Course resources include real enterprise projects, technical service projects, and competition skill projects;

[0012] Input the course resources and the requirements of the courses to be assigned into the adaptive evaluation network, and perform the course matching evaluation with the course time limit as the limit constraint;

[0013] Obtaining a matching evaluation result, where the matching evaluation result is an output result of the adaptive evaluation network;

[0014] The matching evaluation results are used to complete the association with students and generate corresponding course packages for course teaching.

[0015] The method described herein pre-trains the prediction model in the following manner:

[0016] Obtain history teacher evaluation value data, history project experience data, history course completion data, and history skill level data, and compile them into aligned time series data of different monitoring durations, and obtain time series data samples of history teacher evaluation value, time series data samples of history project experience, time series data samples of history course completion, and time series data samples of history skill level respectively;

[0017] Dynamic time warping is used to align the lengths of the time series data samples of history teacher evaluation values, history project experience, history course completion, and history skill level, and the distances between samples are calculated to construct a sparse relationship graph.

[0018] The sparse relationship graph is input into the graph heterogeneous time representation model for training, and the prediction model is obtained after reaching a preset training cutoff condition.

[0019] The graph heterogeneous temporal representation model includes a sequentially connected input layer, a graph convolution layer, a temporal processing layer, an attention layer, a fusion layer and an output layer.

[0020] The step of inputting course resources and the course requirements to be assigned into the adaptive evaluation network also includes:

[0021] Call the case completion record for the assigned course requirements and course resources and generate the call results;

[0022] The matching additional factors are generated by calling the results, and the course matching evaluation compensation of the adaptive evaluation network is performed with the additional factors.

[0023] The method further comprises:

[0024] Establish a skill matching sub-network, a course subject adaptation sub-network, a time limit adaptation sub-network and a weight allocation network, and construct an adaptive evaluation network by the skill matching sub-network, the course subject adaptation sub-network, the time limit adaptation sub-network and the weight allocation network;

[0025] After the course resources and the requirements of the courses to be assigned are input into the adaptive evaluation network, the skill matching sub-network, the course subject adaptation sub-network and the time limit adaptation sub-network are used to perform data parsing and calling, and the sub-network evaluation is performed;

[0026] The weight distribution network adapts and integrates the sub-network evaluation results and outputs the matching evaluation results.

[0027] The method further comprises:

[0028] Establishing a clustering feature set, which includes time features, skill features, and course-related features;

[0029] Using the clustering feature set as matching features, multi-level granularity clustering of unit packages in the course activity space is performed to generate multi-level granularity clustering results;

[0030] Evaluate the course status of students using course resources, and if the preset threshold is met, generate a combination matching instruction;

[0031] Combined course matching is performed by controlling course resources and multi-level granularity clustering results through combined matching instructions;

[0032] Course teaching is carried out according to the combined course matching results.

[0033] The method further comprises:

[0034] Obtain the course time students attend through learning devices;

[0035] Set random verification constraints, call learning devices through random verification constraints, and perform course verification;

[0036] Obtain course verification results, including course execution progress verification results and course status verification results;

[0037] Conduct evaluation and forecast of the execution of the subsequent courses through course time and course verification results;

[0038] Carry out course adjustment management based on the execution evaluation prediction results.

[0039] The method further comprises:

[0040] Obtaining priority for course activities;

[0041] When performing evaluation prediction of sequential courses, an evaluation prediction influencing factor is generated according to the priority of the sequential courses, and a steady-state judgment of course execution is performed;

[0042] If the determination result is lower than the preset threshold, a mobilization instruction is generated;

[0043] Reset the matching according to the transfer command control sequence of courses.

[0044] The method further comprises:

[0045] Generate a first evaluation parameter based on the matching evaluation result;

[0046] generating a second evaluation parameter based on the estimated teacher evaluation value data, the estimated project experience data, the estimated course completion data, and the estimated skill level data;

[0047] Calculating the similarity between the first evaluation parameter and the second evaluation parameter;

[0048] If the similarity is greater than a preset threshold, a comprehensive evaluation parameter is obtained according to the first evaluation parameter and the second evaluation parameter.

[0049] In a second aspect, the present application embodiment provides a vocational education curriculum development system, including:

[0050] The first acquisition module is used to obtain the time series data of teacher evaluation values, project experience, course completion and skill level of students within a set historical time period;

[0051] A prediction module is used to pre-process the teacher evaluation value time series data, project experience time series data, course completion time series data and skill level time series data, and then input the pre-trained prediction model to obtain the student's estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data within a future set time period;

[0052] The prediction model is obtained by training the graph heterogeneous time representation model through the time series data samples of students' history teacher evaluation values, history project experience, history course completion and history skill level.

[0053] The second acquisition module is used to acquire course activities, and store the estimated teacher evaluation value data, the estimated project experience data, the estimated course completion data and the estimated skill level data in the course activities, and the course activities are automatically created through course requirements;

[0054] A generation module is used to synchronize course activities to the course activity space and generate course requirements to be assigned;

[0055] The construction module is used to build course resources. Course resources are resources built from historical project data. Course resources include real enterprise projects, technical service projects, and competition skill projects.

[0056] An evaluation module is used to input course resources and the requirements of the courses to be assigned into the adaptive evaluation network, and perform course matching evaluation with the course time limit as the limit constraint;

[0057] The third acquisition module is used to obtain a matching evaluation result, which is an output result of the adaptive evaluation network;

[0058] The binding module is used to complete the association binding with students through the matching evaluation results and generate corresponding course packages for course teaching.

[0059] Compared with the prior art, the present application provides a vocational education curriculum development method, comprising the following steps: obtaining the time series data of teacher evaluation values, project experience, course completion and skill level of students within a set historical time period; pre-processing the time series data of teacher evaluation values, project experience, course completion and skill level, and inputting them into a pre-trained prediction model to obtain the estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data of the students within a future set time period; the prediction model is obtained by training a graph heterogeneous time representation model with samples of the students' historical teacher evaluation value time series data, historical project experience time series data, historical course completion time series data and historical skill level time series data; obtaining course activities, and inputting the estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data into a pre-trained prediction model. Horizontal data is stored in course activities, and course activities are automatically created through course requirements; course activities are synchronized to the course activity space to generate course requirements to be assigned; course resources are established, and course resources are resources constructed from historical project data, and course resources include real enterprise projects, technical service projects, and competition skill projects; course resources and course requirements to be assigned are input into the adaptive evaluation network, and course matching evaluation is performed with the course time limit as the limit constraint; matching evaluation results are obtained, and the matching evaluation results are the output results of the adaptive evaluation network; the matching evaluation results are used to complete the association and binding with the students, and generate corresponding course packages for course teaching; it can be seen that this application can not only strengthen the cultivation of students' professional ability and actual project operation ability through this method, but also fully consider the correlation between data across time and space dimensions, so that the development of courses is more targeted and accurate, and can meet the rapidly changing industry needs and personalized learning needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0061] Figure 1 A flow chart showing a method for developing a vocational education curriculum provided by the present application is shown;

[0062] Figure 2 A schematic diagram of a vocational education curriculum development system provided by the present application is shown;

[0063] Figure 3 A schematic diagram of an electronic device provided by the present application is shown. DETAILED DESCRIPTION

[0064] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0065] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.

[0066] In addition, the terms "first" and "second" etc. are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0067] Please refer to Figure 1 , Figure 1 A vocational education curriculum development method provided in an embodiment of the present application comprises the following steps:

[0068] S101, obtaining the time series data of teacher evaluation values, project experience, course completion and skill level of students within a set historical time period;

[0069] Among them, the teacher evaluation value time series data is the time series data of the teacher evaluation values ​​in the historical time period according to the set time intervals, the project experience time series data is the time series data of the project experience values ​​in the historical time period according to the set time intervals, the course completion time series data is the time series data of the course completion degrees in the historical time period according to the set time intervals, and the skill level time series data is the time series data of the skill levels in the historical time period according to the set time intervals. The above time intervals can be set to specific time intervals such as minutes, hours, days, weeks or months;

[0070] S102, after pre-processing the teacher evaluation value time series data, project experience time series data, course completion time series data and skill level time series data, input the pre-trained prediction model to obtain the student's estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data in the future set time period;

[0071] Exemplarily, the above-mentioned data preprocessing operations include: data cleaning such as maximum value processing, minimum value processing, data averaging, and normalization processing;

[0072] The prediction model is obtained by training the graph heterogeneous time representation model through the time series data samples of students' history teacher evaluation values, history project experience, history course completion and history skill level.

[0073] S103, obtaining course activities, storing estimated teacher evaluation value data, estimated project experience data, estimated course completion data, and estimated skill level data in the course activities, and the course activities are automatically created through course requirements;

[0074] S104, synchronizing the course activities to the course activity space, and generating the course requirements to be assigned;

[0075] S105. Establish course resources. Course resources are resources constructed from historical project data. Course resources include real enterprise projects, technical service projects, and competition skill projects.

[0076] S106, inputting the course resources and the requirements of the courses to be assigned into the adaptive evaluation network, and performing the course matching evaluation with the course time limit as the limit constraint;

[0077] S107, obtaining a matching evaluation result, where the matching evaluation result is an output result of the adaptive evaluation network;

[0078] S108. Complete the association and binding with the students through the matching evaluation results, and generate the corresponding course package for course teaching.

[0079] The course activity space is a space used to store and manage course activities. It can be a database, cloud platform or a specific management system. Synchronize course activities: synchronize the created course activities to the course activity space. Course activities include: student course status, course time, course content, course difficulty, etc.

[0080] In step S102, the method described above pre-trains the prediction model in the following manner:

[0081] Obtain history teacher evaluation value data, history project experience data, history course completion data, and history skill level data, and compile them into aligned time series data of different monitoring durations, and obtain time series data samples of history teacher evaluation value, time series data samples of history project experience, time series data samples of history course completion, and time series data samples of history skill level respectively;

[0082] Dynamic time warping is used to align the lengths of the time series data samples of history teacher evaluation values, history project experience, history course completion, and history skill level, and the distances between samples are calculated to construct a sparse relationship graph.

[0083] The sparse relationship graph is input into the graph heterogeneous time representation model for training, and the prediction model is obtained after reaching a preset training cutoff condition.

[0084] The graph heterogeneous temporal representation model includes a sequentially connected input layer, a graph convolution layer, a temporal processing layer, an attention layer, a fusion layer and an output layer.

[0085] Input layer: Responsible for receiving and processing raw data, including graph node features, edge information, and timestamps or time series data. Data is preprocessed and encoded in the input layer for processing in subsequent layers.

[0086] Graph convolution layer: used to capture spatial information in the graph structure. It updates the feature representation of each node by aggregating the information of neighboring nodes. Different graph convolution methods (such as spectral-based methods, spatial-based methods, etc.) can adopt different aggregation strategies.

[0087] Temporal processing layer: responsible for processing the temporal dynamics in the data. It usually uses techniques such as recurrent neural networks, long short-term memory networks, gated recurrent units, or temporal convolutional networks to capture dependencies in time series. The temporal processing layer can be applied to the entire graph or nodes in the graph to capture their changing trends over time.

[0088] Attention layer: Introduces the attention mechanism to enhance the model's ability to capture important information. It dynamically adjusts the contribution of different parts to the final prediction result by calculating the attention weight. The attention mechanism can be applied to nodes, edges, or time series data in the graph structure.

[0089] Fusion layer: responsible for integrating and fusing information from different layers. It can concatenate, sum, or weighted sum the feature representations output by the graph convolution layer, temporal processing layer, and attention layer to generate the final fused features.

[0090] Output layer: It is the final output part of the model and is responsible for generating prediction results based on the fused features. The form of the output layer depends on the specific course type, such as node classification, graph classification, time series prediction, etc. For classification courses, the output layer usually contains a softmax activation function to output class probabilities; for regression courses, the output layer may be a linear layer to output continuous value predictions.

[0091] In some implementations of the present application, the step of inputting course resources and course requirements to be assigned into the adaptive evaluation network further includes:

[0092] Call the case completion record for the assigned course requirements and course resources and generate the call results;

[0093] The matching additional factors are generated by calling the results, and the course matching evaluation compensation of the adaptive evaluation network is performed with the additional factors.

[0094] Among them, case completion record call: extract student case completion records from course resources, including information such as student performance, completion times, and completion quality in past projects. At the same time, extract relevant requirements and standards from the course requirements to be assigned, such as project content, required skills, etc. According to the above records and requirements, match and call the course requirements and course resources to be assigned to generate a call result. The call result may include evaluation values ​​such as matching degree and student suitability. The above-mentioned additional factor can be an adjustment value used to compensate for the course matching evaluation result of the adaptive evaluation network. The course matching evaluation compensation can be specifically achieved by multiplying or adding the additional factor to the evaluation result and other existing algorithms. Through the above steps, the matching degree of the course can be evaluated more accurately, and the efficiency and accuracy of course allocation can be improved.

[0095] In some embodiments of the present application, the method further comprises:

[0096] Establish a skill matching sub-network, a course subject adaptation sub-network, a time limit adaptation sub-network and a weight allocation network, and construct an adaptive evaluation network by the skill matching sub-network, the course subject adaptation sub-network, the time limit adaptation sub-network and the weight allocation network;

[0097] After the course resources and the requirements of the courses to be assigned are input into the adaptive evaluation network, data parsing and calling are performed through the skill matching sub-network, the course subject adaptation sub-network and the time limit adaptation sub-network to perform sub-network evaluation;

[0098] The weight distribution network adapts and integrates the sub-network evaluation results and outputs the matching evaluation results.

[0099] Among them, subnetworks and weight allocation networks are defined: according to the needs of course matching evaluation, skill matching subnetworks, course subject adaptation subnetworks, time limit adaptation subnetworks and weight allocation networks are defined. Each subnetwork can be a neural network or a machine learning model for processing specific evaluation courses. The weight allocation network can be a weight allocation model for assigning corresponding weights according to different evaluation factors. The above adaptive evaluation network can be a hierarchical structure, each subnetwork is responsible for processing a specific evaluation course, and passing the result to the next subnetwork or weight allocation network for processing. Each of the above subnetworks performs a specific evaluation course according to the input course resources and the requirements of the courses to be assigned. At the same time, each subnetwork parses and calls the input data and executes the corresponding evaluation course, including the skill matching subnetwork evaluating the matching degree of students' skills and course requirements, the course subject adaptation subnetwork evaluating the compatibility of students, and the time limit adaptation subnetwork evaluating the matching degree of course time limit and course plan. Through the above steps, an adaptive evaluation network can be constructed, and the course resources and the requirements of the courses to be assigned are input into the adaptive evaluation network for evaluation. Then, the evaluation results of each sub-network are adapted and integrated to output the final matching evaluation result to guide course allocation or other related decisions.

[0100] In some embodiments of the present application, the method further comprises:

[0101] Establishing a clustering feature set, which includes time features, skill features, and course-related features;

[0102] Using the clustering feature set as matching features, multi-level granularity clustering of unit packages in the course activity space is performed to generate multi-level granularity clustering results;

[0103] Evaluate the course status of students using course resources, and if the preset threshold is met, generate a combination matching instruction;

[0104] Combined course matching is performed by controlling course resources and multi-level granularity clustering results through combined matching instructions;

[0105] Course teaching is carried out according to the combined course matching results.

[0106] Among them, a cluster feature set is established: a cluster feature set is established according to the needs and characteristics of course allocation. Among them, the time feature may include the time when the student completes the course; the skill feature may include the student's skill level, professional field, etc.; the course association feature may include the relevant information of the student's previous courses, the association between courses, etc. Then, the cluster feature set is used as a matching feature to perform multi-level granular clustering of unit packages in the course activity space. Through multi-level granular clustering, multi-level granular clustering results can be generated. In the process of multi-level granular clustering of unit packages, the course status of students is evaluated with course resources at the same time. According to the student's skill level, completion status, etc., the current course status of the student is evaluated. If the preset threshold is met, a combined matching instruction is generated. Combined course matching: According to the combined matching instruction, the course resources are combined with the multi-level granular clustering results for combined course matching. This can include matching students with specific skills with corresponding course packages. Through combined course matching, more accurate course allocation and teaching can be achieved.

[0107] In some embodiments of the present application, the method further comprises:

[0108] Obtain the course time that students attend through learning devices; learning devices may include personal computers, mobile phones or tablets, etc.;

[0109] Set random verification constraints, call learning devices through random verification constraints, and perform course verification;

[0110] Obtain course verification results, including course execution progress verification results and course status verification results;

[0111] Conduct evaluation and forecast of the execution of the subsequent courses through course time and course verification results;

[0112] Carry out course adjustment management based on the execution evaluation prediction results.

[0113] Among them, the random verification constraint can be an algorithm or program used to call the learning device to perform course verification. In the course verification process, random numbers or encryption technology are used to ensure the randomness and security of the verification process. Course verification can include verification of the execution progress and course status of the course. According to the course time participated by the students, combined with the course requirements and standards, the execution of the course is evaluated and verified. The course verification results include the course execution progress verification results and the course status verification results. These results can be evaluation and feedback on the completion of the students' courses. Execution evaluation prediction of sequential courses: According to the course completion time and course verification results, the execution evaluation of sequential courses can be further predicted. Sequential courses refer to a series of courses that need to be completed in a certain order. The execution evaluation of sequential courses is predicted by analyzing information such as students' course load and historical course execution. At the same time, according to the predicted results of the execution evaluation of sequential courses, course mobilization management is carried out, such as measures such as reallocation of courses, adjustment of priorities, and provision of support and assistance. The purpose of course mobilization management is to ensure the smooth completion of courses and improve efficiency and quality. Through the above steps, the way of course completion can be optimized and the effectiveness of project management can be improved.

[0114] In some embodiments of the present application, the method further comprises:

[0115] Obtaining priority for course activities;

[0116] When performing evaluation prediction of sequential courses, an evaluation prediction influencing factor is generated according to the priority of the sequential courses, and a steady-state judgment of course execution is performed;

[0117] If the determination result is lower than the preset threshold, a mobilization instruction is generated;

[0118] Reset the matching according to the transfer command control sequence of courses.

[0119] Among them, obtaining the priority of course activities: in the course allocation process, according to the needs of the course, time arrangement, difficulty and other factors, set the corresponding priority for each course activity. Priority can be a value or a level, which is used to indicate the urgency and importance of the course. When performing the execution evaluation prediction of the sequential courses, the influence of priority needs to be considered. The above-mentioned evaluation prediction influence factor can be a value related to the priority, which is used to indicate the contribution of the priority to the execution evaluation prediction. The course execution steady-state judgment is to evaluate and judge the execution stability of the sequential courses based on the evaluation prediction influence factor and other relevant factors (such as students' skills, historical performance, etc.). Processing when the judgment result is lower than the preset threshold: if the judgment result is lower than the preset threshold, it means that there is a large instability in the execution of the course, and corresponding processing is required. At this time, a transfer instruction can be generated to indicate operations such as resetting the matching or adjusting the priority of the course. Controlling the sequential courses to reset the matching according to the transfer instruction: according to the generated transfer instruction, the sequential courses can be controlled to reset the matching. Resetting the matching can include measures such as reallocating courses, adjusting priorities, and providing help and guidance to ensure the smooth completion of the course and the smooth progress of the project. Through the above steps, the course execution process can be better managed and the effectiveness of project management can be improved.

[0120] In some embodiments of the present application, the method further comprises:

[0121] Generate a first evaluation parameter based on the matching evaluation result; specifically, quantify the matching evaluation result, and the quantified matching evaluation result is the first evaluation parameter;

[0122] Generate a second evaluation parameter based on the estimated teacher evaluation value data, the estimated project experience data, the estimated course completion data and the estimated skill level data; specifically, set a weight for each estimated data, and calculate a comprehensive score by weighted summation or weighted average; the calculated comprehensive score is the second evaluation parameter;

[0123] Calculate the similarity between the first evaluation parameter and the second evaluation parameter; commonly used similarity calculation methods include cosine similarity, Pearson correlation coefficient, Euclidean distance, etc.

[0124] If the similarity is greater than a preset threshold, a comprehensive evaluation parameter is obtained based on the first evaluation parameter and the second evaluation parameter, so that the developed course can be objectively evaluated for back-end reference.

[0125] Compared with the prior art, the present application provides a vocational education curriculum development method, comprising the following steps: obtaining the time series data of teacher evaluation values, project experience, course completion and skill level of students within a set historical time period; pre-processing the time series data of teacher evaluation values, project experience, course completion and skill level, and inputting them into a pre-trained prediction model to obtain the estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data of the students within a future set time period; the prediction model is obtained by training a graph heterogeneous time representation model with samples of the students' historical teacher evaluation value time series data, historical project experience time series data, historical course completion time series data and historical skill level time series data; obtaining course activities, and inputting the estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data into a pre-trained prediction model. Horizontal data is stored in course activities, and course activities are automatically created through course requirements; course activities are synchronized to the course activity space to generate course requirements to be assigned; course resources are established, and course resources are resources constructed from historical project data, and course resources include real enterprise projects, technical service projects, and competition skill projects; course resources and course requirements to be assigned are input into the adaptive evaluation network, and course matching evaluation is performed with the course time limit as the limit constraint; matching evaluation results are obtained, and the matching evaluation results are the output results of the adaptive evaluation network; the matching evaluation results are used to complete the association and binding with the students, and generate corresponding course packages for course teaching; it can be seen that this application can not only strengthen the cultivation of students' professional ability and actual project operation ability through this method, but also fully consider the correlation between data across time and space dimensions, so that the development of courses is more targeted and accurate, and can meet the rapidly changing industry needs and personalized learning needs.

[0126] like Figure 2 As shown, the embodiment of the present application also provides a vocational education curriculum development system, including:

[0127] The first acquisition module is used to obtain the time series data of teacher evaluation values, project experience, course completion and skill level of students within a set historical time period;

[0128] A prediction module is used to pre-process the teacher evaluation value time series data, project experience time series data, course completion time series data and skill level time series data, and then input the pre-trained prediction model to obtain the student's estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data within a future set time period;

[0129] The prediction model is obtained by training the graph heterogeneous time representation model through the time series data samples of students' history teacher evaluation values, history project experience, history course completion and history skill level.

[0130] The second acquisition module is used to acquire course activities, and store the estimated teacher evaluation value data, the estimated project experience data, the estimated course completion data and the estimated skill level data in the course activities, and the course activities are automatically created through course requirements;

[0131] A generation module is used to synchronize course activities to the course activity space and generate course requirements to be assigned;

[0132] The construction module is used to build course resources. Course resources are resources built from historical project data. Course resources include real enterprise projects, technical service projects, and competition skill projects.

[0133] An evaluation module is used to input course resources and the requirements of the courses to be assigned into the adaptive evaluation network, and perform course matching evaluation with the course time limit as the limit constraint;

[0134] The third acquisition module is used to obtain a matching evaluation result, which is an output result of the adaptive evaluation network;

[0135] The binding module is used to complete the association binding with students through the matching evaluation results and generate corresponding course packages for course teaching.

[0136] The system provided in the embodiment of the present application and the method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0137] An embodiment of the present application also provides an electronic device corresponding to the method provided in the aforementioned embodiment, and the electronic device may be an electronic device used for a client, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the above prediction method.

[0138] Please refer to Figure 3 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 3 As shown, the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, and the processor 200, the communication interface 203 and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and when the processor 200 runs the computer program, it executes the phishing email tracing method provided in any of the aforementioned embodiments of the present application.

[0139] The memory 201 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 203 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0140] The bus 202 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs, and the processor 200 executes the programs after receiving the execution instructions. The phishing email tracing method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 200, or implemented by the processor 200.

[0141] The processor 200 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 200. The above processor 200 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.

[0142] The electronic device provided in the embodiment of the present application and the prediction method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0143] An embodiment of the present application also provides a computer-readable storage medium corresponding to the prediction method provided in the aforementioned embodiment, on which a computer program (i.e., a program product) is stored. When the computer program is executed by a processor, it will execute the prediction method provided in any of the aforementioned embodiments.

[0144] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0145] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the prediction method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application.

Claims

1. A vocational education curriculum development method, characterized in that: The following steps are involved: Obtain the time series data of teacher evaluation values, project experience, course completion and skill level of students in a set historical time period; after pre-processing the time series data of teacher evaluation values, project experience, course completion and skill level, input the pre-trained prediction model to obtain the estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data of the student in a future set time period; the prediction model is obtained by training the graph heterogeneous time representation model with the student's historical teacher evaluation value time series data samples, historical project experience time series data samples, historical course completion time series data samples and historical skill level time series data samples; Obtain course activities, store estimated teacher evaluation value data, estimated project experience data, estimated course completion data, and estimated skill level data in course activities, and course activities are automatically created through course requirements; Synchronize course activities to the course activity space to generate course requirements to be assigned; Establish course resources, which are resources constructed from historical project data. Course resources include real enterprise projects, technical service projects, and competition skill projects. Input course resources and the requirements of the courses to be assigned into the adaptive evaluation network, and perform course matching evaluation with the course time limit as the limit constraint. Obtaining the matching evaluation result, which is the output result of the adaptive evaluation network; completing the association binding with the students through the matching evaluation result, and generating the corresponding course package for course teaching; The prediction model is pre-trained in the following manner: historical teacher evaluation value data, historical project experience data, historical course completion data, and historical skill level data are obtained, and the aligned time series data of different monitoring durations are counted to obtain historical teacher evaluation value time series data samples, historical project experience time series data samples, historical course completion time series data samples, and historical skill level time series data samples, respectively; dynamic time warping is used to align the lengths of historical teacher evaluation value time series data samples, historical project experience time series data samples, historical course completion time series data samples, and historical skill level time series data samples, and the distance between samples is calculated to construct a sparse relationship graph; Inputting the sparse relationship graph into the graph heterogeneous time representation model for training, and obtaining the prediction model after reaching a preset training cutoff condition; The graph heterogeneous temporal representation model includes a sequentially connected input layer, a graph convolution layer, a temporal processing layer, an attention layer, a fusion layer and an output layer; The step of inputting the course resources and the course requirements to be assigned into the adaptive evaluation network also includes: calling the case completion record of the course requirements to be assigned and the course resources to generate a call result; generating a matching additional factor through the call result, and using the additional factor to perform course matching evaluation compensation of the adaptive evaluation network; The method further includes: establishing a skill matching sub-network, a course subject adaptation sub-network, a time limit adaptation sub-network and a weight allocation network, and constructing an adaptive evaluation network by the skill matching sub-network, the course subject adaptation sub-network, the time limit adaptation sub-network and the weight allocation network; after inputting the course resources and the course requirements to be allocated into the adaptive evaluation network, performing data parsing and calling through the skill matching sub-network, the course subject adaptation sub-network and the time limit adaptation sub-network, and executing sub-network evaluation; performing adaptation and integration of sub-network evaluation results by the weight allocation network, and outputting matching evaluation results; The method also includes: establishing a cluster feature set, the cluster feature set including time features, skill features and course-related features; using the cluster feature set as a matching feature, performing multi-level granularity clustering of unit packages in the course activity space, and generating a multi-level granularity clustering result; using course resources to evaluate the course status of students, and if a preset threshold is met, generating a combination matching instruction; controlling the course resources and the multi-level granularity clustering results to perform combined course matching through the combined matching instruction; and conducting course teaching according to the combined course matching result.

2. The method according to claim 1, characterized in that The method also includes: obtaining the course time in which the student participates through the learning device; setting random verification constraints, calling the learning device through the random verification constraints, and executing course verification; obtaining course verification results, the course verification results including course execution progress verification results and course status verification results; predicting the execution evaluation of sequential courses through the course time and the course verification results; and managing course adjustments based on the execution evaluation prediction results.

3. The method according to claim 2, characterized in that The method also includes: obtaining the priority of the course activity; when performing execution evaluation prediction of the sequential courses, generating an evaluation prediction influence factor according to the priority of the sequential courses, and performing a steady-state judgment of the course execution; if the judgment result is lower than a preset threshold, generating a mobilization instruction; and controlling the sequential courses to reset and match according to the mobilization instruction.

4. The method according to claim 1, characterized in that: The method also includes: generating a first evaluation parameter based on the matching evaluation result; generating a second evaluation parameter based on estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data; calculating the similarity between the first evaluation parameter and the second evaluation parameter; if the similarity is greater than a preset threshold, obtaining a comprehensive evaluation parameter based on the first evaluation parameter and the second evaluation parameter.

5. A vocational education curriculum development system, characterized in that: A vocational education curriculum development method as described in any one of claims 1 to 4 is implemented, comprising: a first acquisition module, used to obtain the time series data of teacher evaluation values, project experience time series data, course completion time series data and skill level time series data of students within a set historical time period; a prediction module, used to pre-process the time series data of teacher evaluation values, project experience time series data, course completion time series data and skill level time series data, and input a pre-trained prediction model to obtain the estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data of the students within a future set time period; the prediction model is obtained by training a graph heterogeneous time representation model through samples of the students' historical teacher evaluation value time series data, historical project experience time series data, historical course completion time series data and historical skill level time series data; a second acquisition module The first block is used to obtain course activities and store the estimated teacher evaluation value data, estimated project experience data, estimated course completion data and estimated skill level data in the course activities. The course activities are automatically created through course requirements; the generation module is used to synchronize course activities to the course activity space and generate course requirements to be assigned; the construction module is used to establish course resources. Course resources are resources constructed from historical project data. Course resources include real enterprise projects, technical service projects and competition skill projects; the evaluation module is used to input course resources and course requirements to be assigned into the adaptive evaluation network and perform course matching evaluation with the course time limit as the limit constraint; the third acquisition module is used to obtain the matching evaluation result. The matching evaluation result is the output result of the adaptive evaluation network; the binding module is used to complete the association binding with the students through the matching evaluation result and generate the corresponding course package for course teaching.

Images