Simulation teaching training data management system and method based on knowledge graph

Abstract

The invention discloses an analog simulation teaching training data management system and method based on a knowledge graph, and relates to the technical field of teaching training data analysis, and the system comprises a teaching training analysis module, a knowledge graph construction module, and a learning recommendation module. The teaching training analysis module obtains task parameters in all teaching training tasks and standard operation instruction parameters corresponding to the current teaching training task content, carries out weight labeling on standard operation instructions in the teaching training task content, and is also used for carrying out score evaluation on the student teaching training tasks; the knowledge graph construction module is used for constructing a teaching training task standard knowledge graph, an analog simulation teaching training task knowledge graph and an actual training knowledge graph; and the learning recommendation module is used for periodically evaluating the achievements of the student analog simulation teaching training task and the actual teaching training task, and sending recommended learning information to the student according to the evaluation result.

Description

Technical Field

[0001] This invention relates to the field of teaching and training data analysis technology, specifically a knowledge graph-based simulation teaching and training data management system and method. Background Technology

[0002] Simulation-based teaching and training refers to constructing simulated scenarios using virtual reality, augmented reality, and other means, allowing students to operate, train, and learn in a simulated environment. This can effectively avoid safety risks in real-world environments and improve the efficiency of teaching and training. However, relying solely on simulation-based teaching and training data for learning outcome analysis lacks a comprehensive assessment of students' practical skills and theoretical knowledge. Consequently, the final learning evaluation results are unconvincing and fail to accurately reflect students' true learning status, thus hindering the provision of precise and personalized learning solutions. Summary of the Invention

[0003] The purpose of this invention is to provide a knowledge graph-based simulation teaching and training data management system and method to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: A knowledge graph-based method for managing simulation teaching and training data includes the following steps: Step S100: Obtain the task parameters of all teaching and training tasks and the standard operation instruction parameters corresponding to the content of the current teaching and training task, and assign weights to the operation instructions in each teaching and training task to construct a standard knowledge graph of teaching and training tasks; wherein, the task parameters refer to the task parameters of the students in each teaching and training task; the operation instructions refer to the operation instructions taken by the students in each teaching and training task. Step S200: Obtain the task parameters and operation instructions of the students in the simulation teaching and training tasks, evaluate the scores of each simulation teaching and training task, and construct a knowledge graph of the simulation teaching and training tasks. Step S300: Obtain the task parameters and student operation instructions for the actual teaching and training tasks, evaluate the scores of each actual teaching and training task, and construct the actual training knowledge graph using the method in step S200. Step S400: Set the data sampling period for teaching and training tasks, collect task parameters and student operation instructions in the simulated teaching and training tasks and actual teaching and training tasks of students within the period, construct the knowledge graph of simulated teaching and training tasks and actual training knowledge graph of each period, calculate the edge deviation and comprehensive deviation of the knowledge graph of simulated teaching and training tasks and actual training knowledge graph of each period, and judge and evaluate the actual training operation of students. Step S500: Send recommended learning information to trainees based on the evaluation results of their teaching and training tasks.

[0005] In the above technical solution, step S100 includes the following: Obtain task parameters from teaching and training tasks, simultaneously obtain standard operation instruction parameters corresponding to the current teaching and training task content to construct a standard operation instruction set, and assign standard weights to each standard operation instruction parameter. Using the task parameters and standard operation instructions as nodes in the teaching and training task standard knowledge graph, and the lines connecting the nodes corresponding to the task parameters and the nodes corresponding to the standard operation instructions as edges, a teaching and training task standard knowledge graph is constructed. The weights of each edge in the teaching and training task standard knowledge graph are then calculated according to the formula: ; in, The edge weights between task parameter e and operation instruction o in the standard knowledge graph of the teaching and training task are... The number of teaching and training tasks in which both the task parameter e and the operation instruction o appear simultaneously. The number of teaching and training tasks that appear in the task parameter e and operation instruction o, where t is the teaching and training task number. The standard weight of the operation instruction o in the teaching and training task t; A standard knowledge graph for teaching and training tasks is constructed based on the standard operating instructions for each task. This graph provides data references when analyzing the results of students' simulated teaching and training tasks and actual teaching and training tasks, ensuring the scientific validity and credibility of the final evaluation results. At the same time, the graph further analyzes the relationship between the parameters of each task and the operating instructions, providing a data foundation for subsequent learning recommendations.

[0006] In the above technical solution, step S200 includes the following: Obtain the task parameters and operation instructions of students in the simulated teaching and training tasks; Then, each simulation teaching and training task is evaluated using a 100-point scale. The higher the score, the better the evaluation result of the simulation teaching and training task. Then, using the task parameters and operation instructions as nodes in the simulation teaching and training task knowledge graph, and the lines connecting the nodes corresponding to the task parameters and the nodes corresponding to the operation instructions as edges, the simulation teaching and training task knowledge graph is constructed. The weights of each edge in the simulation teaching and training task knowledge graph are then calculated according to the formula: ; in, The edge weights between task parameter e and operation instruction o in the knowledge graph of the simulated teaching and training task are... The number of simulation teaching and training tasks in which both task parameter e and operation command o appear simultaneously. The number of simulation teaching and training tasks where the task parameter e and operation command o appear one or more, where t is the simulation teaching and training task number. The evaluation score for the simulated teaching and training task t is given. Let $\frac{ ... The value is 0; Set the threshold for duplicate data sampling , The value is a positive integer. If a student has repeatedly trained on the same simulated teaching and training task, the value closest to the current time will be used. The evaluation score for each task is calculated by weighting the scores of the selected tasks and using this weighted average as the evaluation score for the simulated teaching training task that the student repeats; if the number of times the same task is completed is less than... If so, then all data from the same task will be selected for calculation; The weight v for each task's evaluation score is: ; in, Let x be the time interval between the task completion time and the current time, and let x be the number of the same simulation teaching and training task. The time interval between the completion time of the simulated teaching and training task x and the current time. A detailed analysis of students' learning outcomes after completing teaching and training tasks reflects their mastery of the corresponding operational instructions for each task parameter, ensuring the accuracy of subsequent teaching recommendations.

[0007] In the above technical solution, step S400 is divided into the following steps: Step S401: Set the data sampling period for teaching and training tasks, and collect task parameters and student operation instructions in the simulated teaching and training tasks and actual teaching and training tasks within the period. Step S402: Construct a knowledge graph of the simulation teaching and training tasks for each cycle and a knowledge graph of the actual training using the methods in steps S200 and S300. Step S403: Calculate the edge deviation and overall deviation of the knowledge graph of the simulated teaching and training task and the actual training knowledge graph relative to the standard knowledge graph of the teaching and training task for each cycle. The formula for calculating the edge deviation is as follows: ; in, The offset between the nodes corresponding to the task parameter e and the operation instruction o. The edge weights of task parameter e and operation instruction o in the standard knowledge graph of teaching and training tasks. Let e ​​be the edge weights of the task parameter e and the operation instruction o in the current knowledge graph; Then according to the formula Calculate the overall deviation between knowledge graphs; Step S404: Obtain the comprehensive deviation of the knowledge graph of the simulation teaching and training tasks for each cycle and the actual training knowledge graph relative to the standard knowledge graph of the teaching and training tasks. and And evaluate the results of the teaching and training tasks within the current data sampling period of the students' teaching and training tasks; like If the user's actual teaching and training results are determined to be better than the results of the simulated teaching and training tasks, the amount of simulated teaching and training tasks will be increased in subsequent training; if If the results of the user's simulated teaching and training tasks are determined to be better than those of the actual teaching and training tasks, the amount of actual teaching and training tasks will be increased in subsequent training; where k is the evaluation coefficient of the teaching and training task results. By analyzing the deviation of students' learning outcomes from operational standards in simulated and actual teaching training, the learning effectiveness of students in different teaching training methods is evaluated. This allows for a balance in the training volume of students in different teaching training methods, ensuring that students' theoretical knowledge and practical skills improve simultaneously.

[0008] In the above technical solution, step S500 includes the following: The system obtains the evaluation results of students' teaching and training tasks within the current data sampling period, extracts the knowledge graph corresponding to teaching and training tasks with poor results, calculates the edge deviation values ​​of each teaching and training task, including the corresponding nodes of each task parameter and operation instruction, in the knowledge graph, and uses the calculation results as the recommended learning priority values ​​for each historical teaching and training task. Teaching and training tasks with larger recommended learning priority values ​​are given higher recommended learning priority, and then recommended learning information is sent to students. The recommended learning information includes teaching and training tasks with poor results and each teaching and training task sorted from high to low learning recommendation priority; wherein, the teaching and training task methods include simulation teaching and training tasks and actual teaching and training tasks.

[0009] The above-described simulation teaching and training data management method based on knowledge graphs is used to provide a simulation teaching and training data management system, which includes: a teaching and training analysis module, a knowledge graph construction module, and a learning recommendation module. The teaching and training analysis module acquires task parameters from all teaching and training tasks and standard operation command parameters corresponding to the current teaching and training task content, and assigns weights to the standard operation commands in each teaching and training task content. It is also used to evaluate the scores of students in each simulated teaching and training task and actual teaching and training task. The knowledge graph construction module is used to construct a standard knowledge graph for teaching and training tasks, a simulated teaching and training task knowledge graph, and an actual training knowledge graph. The learning recommendation module is used to evaluate the students' results in simulated teaching and training tasks and actual teaching and training tasks within each teaching and training task data sampling period, and sends recommended learning information to the students based on the evaluation results.

[0010] In the above technical solution, the teaching and training analysis module includes: a task parameter and operation instruction annotation unit, a standard operation instruction weight annotation unit, and a student teaching and training task evaluation unit. The task parameter and operation instruction annotation unit is used to annotate the task parameters in all teaching and training tasks and the standard operation instruction parameters corresponding to the current teaching and training task content; the standard operation instruction weight annotation unit is used to annotate the standard operation instructions in each teaching and training task content with weights; the student teaching and training task evaluation unit is used to evaluate the scores of each student's simulated teaching and training task and actual teaching and training task.

[0011] In the above technical solution, the knowledge graph construction module includes: a standard knowledge graph construction unit for teaching and training tasks, a knowledge graph construction unit for simulated teaching and training tasks, and a knowledge graph construction unit for actual training. The teaching and training task standard knowledge graph construction unit is used to construct the teaching and training task standard knowledge graph; the simulation teaching and training task knowledge graph construction unit is used to construct the simulation teaching and training task knowledge graph; and the actual training knowledge graph construction unit is used to construct the actual training knowledge graph construction unit.

[0012] In the above technical solution, the learning recommendation module includes: a learning outcome evaluation unit, a recommended learning priority analysis unit, and a learning recommendation unit; The deviation analysis unit is used to calculate the edge deviation and overall deviation of the knowledge graph of the simulated teaching and training task and the actual training knowledge graph relative to the standard knowledge graph of the teaching and training task in each cycle; the learning outcome evaluation unit evaluates the students' achievements in the simulated teaching and training task and the actual teaching and training task within each teaching and training task data sampling cycle; the recommended learning priority analysis unit is used to calculate the recommended learning priority value for each teaching and training task; the learning recommendation unit sends recommended learning information to the students based on the evaluation results and the recommended learning priority value for each teaching and training task.

[0013] Compared with the prior art, the beneficial effects of the present invention are: This invention constructs a standard knowledge graph for teaching and training tasks, a simulated teaching and training task knowledge graph, and an actual training knowledge graph. It then analyzes in detail the correlation between task parameters and operational instructions in each teaching and training task. Combined with a comprehensive analysis of students' teaching and training tasks and their actual completion results, this accurately reflects students' learning and mastery levels of each knowledge point in the teaching and training content under different teaching and training methods. Furthermore, this invention calculates and analyzes the deviation of each knowledge graph from the standard knowledge graph for teaching and training tasks, comprehensively assessing students' actual learning levels and providing a scientific data foundation for student learning recommendations. In addition, based on the deviation calculation results between knowledge graphs, this invention accurately provides matching teaching and training methods and tasks, offering students precise personalized learning recommendations. Attached Figure Description

[0014] Figure 1 This is a flowchart of a knowledge graph-based simulation teaching and training data management method according to the present invention. Figure 2 This is an organizational structure diagram of a knowledge graph-based simulation teaching and training data management system according to the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] Example: Please refer to Figures 1-2 This invention provides a technical solution. like Figure 1 As shown, the present invention provides a method for managing simulation teaching and training data based on knowledge graphs, comprising the following steps: Step S100: Obtain the task parameters of all teaching and training tasks and the standard operation instruction parameters corresponding to the content of the current teaching and training task, and assign weights to the operation instructions in each teaching and training task to construct a standard knowledge graph of teaching and training tasks; wherein, the task parameters refer to the task parameters of the students in each teaching and training task; the operation instructions refer to the operation instructions taken by the students in each teaching and training task. Step S200: Obtain the task parameters and operation instructions of the students in the simulation teaching and training tasks, evaluate the scores of each simulation teaching and training task, and construct a knowledge graph of the simulation teaching and training tasks. Step S300: Obtain the task parameters and student operation instructions for the actual teaching and training tasks, evaluate the scores of each actual teaching and training task, and construct the actual training knowledge graph using the method in step S200. Step S400: Set the data sampling period for teaching and training tasks, collect task parameters and student operation instructions in the simulated teaching and training tasks and actual teaching and training tasks of students within the period, construct the knowledge graph of simulated teaching and training tasks and actual training knowledge graph of each period, calculate the edge deviation and comprehensive deviation of the knowledge graph of simulated teaching and training tasks and actual training knowledge graph of each period, and judge and evaluate the actual training operation of students. Step S500: Send recommended learning information to trainees based on the evaluation results of their teaching and training tasks.

[0017] Step S100 includes the following: The system acquires task parameters from teaching and training tasks, simultaneously acquires standard operation instruction parameters corresponding to the content of the current teaching and training task to construct a standard operation instruction set, and assigns standard weights to each standard operation instruction parameter; wherein, the task parameters refer to the task parameters of the trainee in each teaching and training task; and the operation instructions refer to the operation instructions taken by the trainee in each teaching and training task. In practice, all teaching and training task information is obtained, the task parameters and standard operations of each teaching and training task are analyzed, each operation is broken down into individual operation instructions, and then unified into a set of operation instructions for all teaching and training tasks. Using the task parameters and standard operation instructions as nodes in the teaching and training task standard knowledge graph, and the lines connecting the nodes corresponding to the task parameters and the nodes corresponding to the standard operation instructions as edges, a teaching and training task standard knowledge graph is constructed. The weights of each edge in the teaching and training task standard knowledge graph are then calculated according to the formula: ; in, The edge weights between task parameter e and operation instruction o in the standard knowledge graph of the teaching and training task are... The number of teaching and training tasks in which both the task parameter e and the operation instruction o appear simultaneously. The number of teaching and training tasks that appear in the task parameter e and operation instruction o, where t is the teaching and training task number. The standard weight of the operation instruction o in the teaching and training task t; In practice, each task parameter and operation instruction are connected as edges of the knowledge graph, and the nodes at both ends of each edge are different. Then, the teaching and training task data are obtained to construct the standard knowledge graph of the teaching and training task. Among them, the standard weight of operation instruction o in training task t refers to the importance measurement value of instruction o in teaching and training task t. Regarding the above calculation formula, the following calculation example is given: Assume that there are 5 teaching and training tasks that contain at least one of the task parameter e and the operation instruction o, and 3 of the teaching and training tasks contain both the task parameter e and the operation instruction o, with standard weights of 0.8, 0.9 and 0.7 respectively. The edge weight of the task parameter e and the operation instruction o in the standard knowledge graph of the teaching and training tasks can be calculated to be 0.48.

[0018] Step S200 includes the following: Obtain the task parameters and operation instructions of students in the simulated teaching and training tasks; Then, each simulation teaching and training task is evaluated using a 100-point scale. The higher the score, the better the evaluation result of the simulation teaching and training task. Then, using the task parameters and operation instructions as nodes in the simulation teaching and training task knowledge graph, and the lines connecting the nodes corresponding to the task parameters and the nodes corresponding to the operation instructions as edges, the simulation teaching and training task knowledge graph is constructed. The weights of each edge in the simulation teaching and training task knowledge graph are then calculated according to the formula: ; in, The edge weights between task parameter e and operation instruction o in the knowledge graph of the simulated teaching and training task are... The number of simulation teaching and training tasks in which both task parameter e and operation command o appear simultaneously. The number of simulation teaching and training tasks where the task parameter e and operation command o appear one or more, where t is the simulation teaching and training task number. The evaluation score for the simulated teaching and training task t is given. Let $\frac{ ... The value is 0; Based on the above calculation formula, the following calculation example is given: Continuing with the data in the above calculation example, assuming that the student's evaluation scores for completing 3 of the teaching tasks are 90, 85 and 95 respectively, the edge weight between the task parameter e and the operation instruction o in the knowledge graph of the simulation teaching training task can be calculated to be 0.43. Set the threshold for duplicate data sampling , The value is a positive integer. If a student has repeatedly trained on the same simulated teaching and training task, the value closest to the current time will be used. The evaluation score for each task is calculated by weighting the scores of the selected tasks and using this weighted average as the evaluation score for the simulated teaching training task that the student repeats; if the number of times the same task is completed is less than... If so, then all data from the same task will be selected for calculation; The weight v for each task's evaluation score is: ; in, Let x be the time interval between the task completion time and the current time, and let x be the number of the same simulation teaching and training task. The time interval between the completion time of the simulated teaching and training task x and the current time. In practice, common sense tells us that the closer the completion time is to the current time, the more credible the task evaluation results are. Therefore, introducing a time interval parameter for multi-score weighted averaging makes the evaluation from the perspective of data results more interpretable and scientific.

[0019] Step S400 consists of the following steps: Step S401: Set the data sampling period for teaching and training tasks, and collect task parameters and student operation instructions in the simulated teaching and training tasks and actual teaching and training tasks within the period. Step S402: Construct a knowledge graph of the simulation teaching and training tasks for each cycle and a knowledge graph of the actual training using the methods in steps S200 and S300. Step S403: Calculate the edge deviation and overall deviation of the knowledge graph of the simulated teaching and training task and the actual training knowledge graph relative to the standard knowledge graph of the teaching and training task for each cycle. The formula for calculating the edge deviation is as follows: ; in, The offset between the nodes corresponding to the task parameter e and the operation instruction o. The edge weights of task parameter e and operation instruction o in the standard knowledge graph of teaching and training tasks. Let e ​​be the edge weights of the task parameter e and the operation instruction o in the current knowledge graph; Then according to the formula Calculate the overall deviation between knowledge graphs; Step S404: Obtain the comprehensive deviation of the knowledge graph of the simulation teaching and training tasks for each cycle and the actual training knowledge graph relative to the standard knowledge graph of the teaching and training tasks. and And evaluate the results of the teaching and training tasks within the current data sampling period of the students' teaching and training tasks; like If the user's actual teaching and training results are determined to be better than the results of the simulated teaching and training tasks, the amount of simulated teaching and training tasks will be increased in subsequent training; if If the results of the user's simulated teaching and training tasks are determined to be better than those of the actual teaching and training tasks, the amount of actual teaching and training tasks will be increased in subsequent training; where k is the evaluation coefficient of the teaching and training task results. In practice, trainees consolidate and deepen their theoretical knowledge through simulation-based teaching and training, and then complete the entire teaching and training process through practical operation training. Simulation-based teaching and training lacks the psychological interference of the actual environment and reflects trainees' theoretical knowledge more, while practical operation reflects trainees' practical operation level. Therefore, by comparing the teaching and training results of the two, the trainees' actual learning preferences can be revealed, thereby providing trainees with more accurate teaching recommendations. When setting the evaluation coefficient for teaching and training task results, if k=1, it means that the actual operation teaching and simulation theory teaching have the same importance, and the larger the value of k, the higher the importance of simulation theory teaching.

[0020] Step S500 includes the following: The system obtains the evaluation results of students' teaching and training tasks within the current data sampling period, extracts the knowledge graph corresponding to teaching and training tasks with poor results, calculates the edge deviation values ​​of each teaching and training task, including the corresponding nodes of each task parameter and operation instruction, in the knowledge graph, and uses the calculation results as the recommended learning priority values ​​for each historical teaching and training task. Teaching and training tasks with larger recommended learning priority values ​​are given higher recommended learning priority, and then recommended learning information is sent to students. The recommended learning information includes teaching and training tasks with poor results and each teaching and training task sorted from high to low learning recommendation priority; wherein, the teaching and training task methods include simulation teaching and training tasks and actual teaching and training tasks.

[0021] like Figure 2 As shown, the present invention also provides a knowledge graph-based simulation teaching and training data management system, the system comprising: a teaching and training analysis module, a knowledge graph construction module, and a learning recommendation module; The teaching and training analysis module acquires task parameters from all teaching and training tasks and standard operation command parameters corresponding to the current teaching and training task content, and assigns weights to the standard operation commands in each teaching and training task content. It is also used to evaluate the scores of students in each simulated teaching and training task and actual teaching and training task. The knowledge graph construction module is used to construct a standard knowledge graph for teaching and training tasks, a simulated teaching and training task knowledge graph, and an actual training knowledge graph. The learning recommendation module is used to evaluate the students' results in simulated teaching and training tasks and actual teaching and training tasks within each teaching and training task data sampling period, and sends recommended learning information to the students based on the evaluation results.

[0022] The teaching and training analysis module includes: a task parameter and operation instruction annotation unit, a standard operation instruction weight annotation unit, and a student teaching and training task evaluation unit; The task parameter and operation instruction annotation unit is used to annotate the task parameters in all teaching and training tasks and the standard operation instruction parameters corresponding to the current teaching and training task content; the standard operation instruction weight annotation unit is used to annotate the standard operation instructions in each teaching and training task content with weights; the student teaching and training task evaluation unit is used to evaluate the scores of each student's simulated teaching and training task and actual teaching and training task.

[0023] The knowledge graph construction module includes: a knowledge graph construction unit for teaching and training tasks, a knowledge graph construction unit for simulated teaching and training tasks, and a knowledge graph construction unit for actual training. The teaching and training task standard knowledge graph construction unit is used to construct the teaching and training task standard knowledge graph; the simulation teaching and training task knowledge graph construction unit is used to construct the simulation teaching and training task knowledge graph; and the actual training knowledge graph construction unit is used to construct the actual training knowledge graph construction unit.

[0024] The learning recommendation module includes: a learning outcome assessment unit, a recommended learning priority analysis unit, and a learning recommendation unit; The deviation analysis unit is used to calculate the edge deviation and overall deviation of the knowledge graph of the simulated teaching and training task and the actual training knowledge graph relative to the standard knowledge graph of the teaching and training task in each cycle; the learning outcome evaluation unit evaluates the students' achievements in the simulated teaching and training task and the actual teaching and training task within each teaching and training task data sampling cycle; the recommended learning priority analysis unit is used to calculate the recommended learning priority value for each teaching and training task; the learning recommendation unit sends recommended learning information to the students based on the evaluation results and the recommended learning priority value for each teaching and training task.

[0025] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for managing simulation teaching training data based on knowledge graph, characterized in that , the method comprises the following steps: Step S100: Obtain the task parameters in all teaching and training tasks and the standard operation instruction parameters corresponding to the current teaching and training task content, and weight the operation instructions in each teaching and training task content to construct a standard knowledge graph of teaching and training tasks; wherein, the task parameters refer to the task parameters of the trainees in each teaching and training task; the operation instructions refer to the operation instructions taken by the trainees in each teaching and training task; Step S200: Obtain the task parameters of the student's simulation teaching and training task and the student's operation instructions, evaluate the scores of each simulation teaching and training task, and construct a knowledge graph of the simulation teaching and training task; Step S300: Obtain the task parameters and operation instructions of the actual teaching and training tasks of the students, evaluate the scores of each actual teaching and training task, and construct the actual training knowledge graph using the method in step S200; Step S400: Setting a teaching and training task data sampling period, collecting task parameters and student operation instructions in the student simulation teaching and training tasks and actual teaching and training tasks within the period, constructing a knowledge graph of the simulation teaching and training tasks and an actual training knowledge graph for each period, calculating the edge deviation and comprehensive deviation of the knowledge graph of the simulation teaching and training tasks and the actual training knowledge graph for each period, and judging and evaluating the results of the student teaching and training tasks; Step S500: Send recommended learning information to students based on the evaluation results of their teaching and training tasks.

2. A method for managing simulation teaching training data based on knowledge graph according to claim 1, characterized in that: The step S100 includes the following contents: Obtain the task parameters in the teaching and training task, synchronously obtain the standard operation instruction parameters corresponding to the current teaching and training task content to construct a standard operation instruction set, and mark each standard operation instruction parameter with a standard weight; The task parameters and standard operation instructions are used as nodes of the teaching and training task standard knowledge graph, and the lines between the nodes corresponding to the task parameters and the nodes corresponding to the standard operation instructions are used as edges of the teaching and training task standard knowledge graph to construct a teaching and training task standard knowledge graph, and calculate the weights of each edge of the teaching and training task standard knowledge graph according to the formula: ； in, is the edge weight between the task parameter e and the operation instruction o in the standard knowledge graph of the teaching and training task, is the number of teaching and training tasks in which task parameters e and operation instructions o appear simultaneously, is the number of teaching and training tasks with one or more task parameters e and operation instructions o, t is the teaching and training task number, is the standard weight of operation instruction o in the teaching training task t.

3. A method for managing simulation teaching training data based on knowledge graph according to claim 1, characterized in that: The step S200 includes the following contents: Obtain the task parameters of the students' simulation teaching training tasks and the students' operation instructions; Then, each simulation teaching and training task is evaluated by a percentage system. The higher the score, the better the evaluation result of the simulation teaching and training task. Then, the task parameters and operation instructions are used as nodes of the simulation teaching and training task knowledge graph, and the lines between the nodes corresponding to the task parameters and the nodes corresponding to the operation instructions are used as edges of the simulation teaching and training task knowledge graph to construct a simulation teaching and training task knowledge graph, and calculate the weights of each edge of the simulation teaching and training task knowledge graph, according to the formula: ； in, is the edge weight between the task parameter e and the operation instruction o in the simulation teaching training task knowledge graph, is the number of simulation teaching training tasks in which task parameters e and operation instructions o appear simultaneously, is the number of simulation teaching and training tasks with one or more task parameters e and operation instructions o, t is the simulation teaching and training task number, is the evaluation score of the simulation teaching training task t, is the standard weight of operation instruction o in simulation teaching training task t; if the standard operation instruction set of simulation teaching training task t does not include operation instruction o, then The value is 0; Set the repeated data sampling threshold , is a positive integer. If the trainee has repeated training on the same simulation teaching training task, the time point closest to the current time is selected. The weighted average of the selected task evaluation scores is used as the evaluation score of the simulation teaching training task for the trainees' repeated training; if the number of times the same task is completed is less than , then all the same task data are selected for calculation; The weight v of each task evaluation score is: ； in, is the time interval between the task completion time and the current time point, x is the number of the same simulation teaching training task, It is the time interval between the task completion time point and the current time point of the simulation teaching training task x.

4. A method for managing simulation teaching training data based on knowledge graph according to claim 1, characterized in that: The step S400 is divided into the following steps: Step S401: Setting a teaching and training task data sampling period, collecting task parameters of students' simulated teaching and training tasks and actual teaching and training tasks and students' operation instructions within the period; Step S402: Use the method in step S200 and step S300 to construct a knowledge graph of simulation teaching training tasks and an actual training knowledge graph for each cycle; Step S403: Calculate the edge deviation and comprehensive deviation of the knowledge graph of each period simulation teaching and training task and the actual training knowledge graph relative to the standard knowledge graph of the teaching and training task; The edge deviation calculation formula is as follows: ； in, is the edge deviation between nodes corresponding to task parameter e and operation instruction o, is the edge weight of the task parameter e and the operation instruction o in the standard knowledge graph of the teaching and training task, is the edge weight of the task parameter e and the operation instruction o in the current knowledge graph; Then according to the formula Calculate the comprehensive deviation between knowledge graphs; Step S404: Obtain the comprehensive deviation of the knowledge graph of each period simulation teaching and training task and the actual training knowledge graph relative to the standard knowledge graph of the teaching and training task and , and evaluate the teaching and training task results of the trainees during the current teaching and training task data sampling period; like , determine that the user's actual teaching and training task results are better than the simulation teaching and training task results, and increase the simulation teaching and training task volume in subsequent training; if , determine that the user's simulation teaching and training task results are better than the actual teaching and training task results, and increase the actual teaching and training task volume in subsequent training; where k is the teaching and training task result evaluation coefficient.

5. A method for managing simulation teaching training data based on knowledge graph according to claim 4, characterized in that: The step S500 includes the following contents: Obtain the evaluation results of the students' teaching and training task achievements within the current teaching and training task data sampling period, extract the knowledge graph corresponding to the teaching and training task methods with poor training achievements, calculate the sum of the edge deviation values ​​between the nodes corresponding to each teaching and training task, including each task parameter and operation instruction, in the knowledge graph, and use the calculation result as the recommended learning priority value of each historical teaching and training task. A teaching and training task with a larger recommended learning priority value has a higher recommended learning priority, and then send recommended learning information to the students. The recommended learning information includes the teaching and training task methods with poor training achievements and the teaching and training tasks sorted from high to low according to the recommended learning priority; wherein the teaching and training task methods include simulation teaching and training tasks and actual teaching and training tasks.

6. A simulation teaching training data management system based on knowledge graph using a simulation teaching training data management method based on knowledge graph according to any one of claims 1 to 5, the system comprising: Teaching and training analysis module, knowledge graph construction module, and learning recommendation module; The teaching and training analysis module obtains the task parameters in all teaching and training tasks and the standard operation instruction parameters corresponding to the current teaching and training task content, and weights the standard operation instructions in each teaching and training task content, and is also used to evaluate the scores of each simulation teaching and training task and actual teaching and training task of the trainees; the knowledge graph construction module is used to construct a standard knowledge graph for teaching and training tasks, a knowledge graph for simulation teaching and training tasks, and an actual training knowledge graph; The learning recommendation module is used to evaluate the students' simulated teaching and training tasks and actual teaching and training task results within each teaching and training task data sampling period, and send recommended learning information to the students based on the evaluation results.

7. A simulation teaching training data management system based on knowledge graph according to claim 6, characterized in that: The teaching and training analysis module includes: a task parameter and operation instruction marking unit, a standard operation instruction weight marking unit, and a student teaching and training task evaluation unit; The task parameter and operation instruction labeling unit is used to label the task parameters in all teaching and training tasks and the standard operation instruction parameters corresponding to the current teaching and training task content; the standard operation instruction weight labeling unit is used to weight the standard operation instructions in each teaching and training task content; the student teaching and training task evaluation unit is used to score and evaluate the student's simulation teaching and training tasks and actual teaching and training tasks.

8. The simulation teaching training data management system based on knowledge graph according to claim 6 is characterized in that: The knowledge graph construction module includes: a teaching and training task standard knowledge graph construction unit, a simulation teaching and training task knowledge graph construction unit, and an actual training knowledge graph construction unit; The teaching and training task standard knowledge graph construction unit is used to construct the teaching and training task standard knowledge graph; the simulation teaching and training task knowledge graph construction unit is used to construct the simulation teaching and training task knowledge graph; the actual training knowledge graph construction unit is used to construct the actual training knowledge graph construction unit.

9. The simulation teaching training data management system based on knowledge graph according to claim 6 is characterized in that: The learning recommendation module includes: a deviation analysis unit, a learning achievement evaluation unit, a recommended learning priority analysis unit, and a learning recommendation unit; The deviation analysis unit is used to calculate the edge deviation and comprehensive deviation of the simulation teaching and training task knowledge graph and the actual training knowledge graph of each period relative to the standard knowledge graph of the teaching and training tasks; the learning outcome evaluation unit evaluates the students' simulation teaching and training tasks and actual teaching and training task results within each teaching and training task data sampling period; the recommended learning priority analysis unit is used to calculate the recommended learning priority value of each teaching and training task; the learning recommendation unit sends recommended learning information to the students based on the evaluation results and the recommended learning priority values ​​of each teaching and training task.

Images