An outcome-oriented continuous improvement teaching knowledge graph construction and application method and system

Abstract

The application discloses a result-oriented continuous improvement teaching knowledge graph construction and application method and system, constructs a course content knowledge graph and a course target knowledge graph, then updates the achievement attribute of a learning result entity instance corresponding to a corresponding inspection mode in the course target knowledge graph based on the class entity instance corresponding to the current selected class corresponding to the class achievement data of the different inspection modes, and further updates the achievement degree attribute of the corresponding course target entity instance, so that the course target achievement analysis result of the current selected class is formed, and in addition, a teaching process knowledge graph is constructed, so that the knowledge mastery rate of the corresponding course knowledge point entity instance is calculated based on the learning result entity instance connected with each course knowledge point entity instance in the teaching process knowledge graph, the teaching process analysis result is formed, and the teaching improvement suggestion of the current selected class is generated, so that more accurate teaching improvement suggestions can be given more targetedly and flexibly.

Description

Technical Field

[0001] This invention belongs to the field of knowledge graph construction and application, and more specifically, relates to an outcome-oriented, continuously improving teaching knowledge graph construction and application method and system. Background Technology

[0002] With the development of artificial intelligence technology, knowledge graph technology, which is centered on knowledge, has been widely applied in search engines, personalized recommendations, intelligent question answering, knowledge explanation, and decision support, improving people's efficiency in obtaining information. Knowledge graphs are computational models of relationships between objects, capable of organizing massive amounts of complex knowledge and visually representing it in a clear logical hierarchy. This facilitates knowledge understanding and mastery, and its application in education can improve teaching efficiency and the quality of talent cultivation. Therefore, knowledge graphs, along with deep learning and big data, are considered key research areas in the education era.

[0003] Outcome-based education, which focuses on learning outcomes and employs a reverse approach to curriculum development, is widely used in engineering education reform. However, current applications of knowledge graphs in curriculum development primarily focus on organizing specific course knowledge points and clarifying the relationships between courses within a course group. Few researchers have conducted research on integrating outcome-based education with knowledge graphs in curriculum teaching. How to construct a multi-level knowledge graph for the entire teaching process, guided by outcome-based principles and supported by knowledge graphs, and how to provide more dynamic, personalized, and precise teaching improvement suggestions based on this graph remain urgent problems to be solved. Summary of the Invention

[0004] In view of the above-mentioned deficiencies or improvement needs of existing technologies, this invention provides an outcome-oriented method and system for constructing and applying a continuous improvement teaching knowledge graph, thereby solving the technical problem of how to provide more dynamic, personalized and precise teaching improvement suggestions.

[0005] To achieve the above objectives, according to a first aspect of the present invention, a result-oriented, continuously improving method for constructing and applying instructional knowledge graphs is provided, comprising: S1. Extract chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances from the course teaching text, as well as the hierarchical relationship between the chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances, in order to construct a course content knowledge graph. S2, identify course target entity instances from the course teaching text, identify learning outcome entity instances corresponding to different testing methods of different courses from the exercise list exported by the course platform, and match the descriptive attributes of each course target entity instance with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course target entity instances and the learning outcome entity instances, so as to construct a course target knowledge graph. S3, extract class entity instances and student entity instances, as well as the membership relationships between the student entity instances and the class entity instances, from the student information record text, and calculate the class performance data corresponding to different verification methods for each student entity instance that belongs to the same class entity instance based on the performance attributes of each student entity instance corresponding to different verification methods. Update the performance attributes of the learning outcome entity instances corresponding to the corresponding verification methods in the course objective knowledge graph based on the class performance data corresponding to the class entity instances of the currently selected class. S4, update the achievement attribute of the corresponding course objective entity instance by using the performance attribute of the learning outcome entity instance connected to the course objective entity instance in the course objective knowledge graph, and extract the achievement attribute of the course objective entity instance to form the course objective achievement analysis result of the currently selected class. S5, match the descriptive attributes of each learning outcome entity instance in the course objective knowledge graph with the descriptive attributes of the knowledge point content entity instances connected to each course knowledge point entity instance in the course content knowledge graph to obtain the association between the learning outcome entity instance and the course knowledge point entity instance, so as to construct a teaching process knowledge graph based on the learning outcome entity instance, the course knowledge point entity instance and the association between the two. S6. Based on the learning outcome entity instances connected to the entity instances of each course knowledge point in the knowledge graph of the teaching process, calculate the knowledge mastery rate of the corresponding course knowledge point entity instances, form the teaching process situation analysis results, and generate teaching improvement suggestions for the currently selected class based on the teaching process situation analysis results and the course goal achievement analysis results.

[0006] Based on the aforementioned outcome-oriented continuous improvement teaching knowledge graph construction and application method, course objective entity instances are identified from the course teaching text, and learning outcome entity instances corresponding to different testing methods are identified from the exercise list exported from the course platform. The descriptive attributes of each course objective entity instance are matched with the descriptive attributes of each learning outcome entity instance corresponding to different testing methods to obtain the support relationships between the course objective entity instances and the learning outcome entity instances, specifically including: Extract the overall course objective entity instance, sub-objective entity instances, and hierarchical relationships between the overall course objective entity instance and the sub-objective entity instances from the course teaching text; the overall course objective entity instance and the sub-objective entity instance include at least hierarchical attributes, descriptive attributes, and achievement attributes, and the sub-objective entity instance also includes final exam achievement attribute, daily performance achievement attribute, sub-objective weight attribute, final exam weight attribute, and daily performance weight attribute; wherein, the initial values ​​of the achievement attributes, the final exam achievement attribute, and the daily performance achievement attribute are preset values; Export a list of exercises with different assessment methods from the course platform; the assessment methods include classroom exercises, assignments, experiments, and final exams. The learning outcome entity instances corresponding to different assessment methods generated during the teaching process of different courses are identified from the exercise list. The learning outcome entity instances include class practice entity instances, single class practice entity instances, and class practice question entity instances with hierarchical relationships; class assignment entity instances, chapter assignment entity instances, and assignment question entity instances with hierarchical relationships; experiment entity instances; and class exam entity instances, test type entity instances, and test question entity instances with hierarchical relationships. Each type of learning outcome entity instance includes at least a descriptive attribute and a performance attribute. The performance attribute includes the average score and the full score, and the initial value of the average score is a preset value. The descriptive attributes of each course sub-goal entity instance are matched with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course sub-goal entity instances and each learning outcome entity instance.

[0007] Based on the aforementioned outcome-oriented continuous improvement teaching knowledge graph construction and application method, class entity instances and student entity instances, as well as the membership relationships between student entity instances and class entity instances, are extracted from student information records. Then, based on the performance attributes of each student entity instance belonging to the same class entity instance and corresponding to different testing methods, the class performance data for that class entity instance under different testing methods is calculated. Finally, based on the class performance data for the class entity instances corresponding to the currently selected class and corresponding to different testing methods, the performance attributes of the learning outcome entity instances corresponding to the corresponding testing methods in the course objective knowledge graph are updated. Specifically, this includes: Identify student entity instances, course entity instances, and class entity instances with hierarchical relationships from the student information record text, and extract the membership relationship between the student entity instances and the class entity instances using rule matching; the student entity instances include at least grade attributes corresponding to different verification methods; For each class entity instance, calculate the class score data corresponding to different validation methods for each student entity instance that belongs to the corresponding class entity instance based on the score attributes of each student entity instance corresponding to different validation methods. Obtain the course entity instance connected to the class entity instance corresponding to the currently selected class, determine the course sub-target entity instance that matches the course entity instance in the course target knowledge graph, and the learning outcome entity instance connected to the matched course sub-target entity instance, so as to construct the completion relationship between the class entity instance corresponding to the currently selected class and the learning outcome entity instance connected to the matched course sub-target entity instance. The course objective knowledge graph updates the performance attributes of learning outcome entity instances that have a completion relationship with the class entity instance corresponding to the currently selected class based on the class performance data corresponding to different testing methods.

[0008] Based on the aforementioned outcome-oriented continuous improvement teaching knowledge graph construction and application method, the achievement attribute of the corresponding course objective entity instance is updated using the performance attribute of the learning outcome entity instance connected to the course objective entity instance in the course objective knowledge graph. The achievement attribute of the course objective entity instance is then extracted to form the course objective achievement analysis results for the currently selected class, specifically including: Extract the course entity instance that is connected to the class entity instance corresponding to the currently selected class and match the course sub-target entity instance in the course target knowledge graph, and use it as the course sub-target entity instance to be analyzed. For each sub-target entity instance of the course to be analyzed, based on the average score and full score of the class exam entity instances connected to the corresponding sub-target entity instance, update the final exam achievement attribute of the corresponding sub-target entity instance in the course target knowledge graph; based on the average score and full score of the class classroom exercise entity instances, class homework entity instances, and experiment entity instances connected to the corresponding sub-target entity instance, update the daily performance achievement attribute of the corresponding sub-target entity instance in the course target knowledge graph. For each sub-target entity instance of the course to be analyzed, a weighted sum is performed based on the final exam achievement attribute, the daily performance achievement attribute, the final exam weight attribute, and the daily performance weight attribute of the corresponding sub-target entity instance of the course to be analyzed, so as to update the achievement attribute of the corresponding sub-target entity instance of the course to be analyzed. The achievement attributes and weight attributes of each sub-goal entity instance of the course to be analyzed are weighted and summed to update the achievement attribute of the connected total course goal entity instance. The achievement analysis results of the course goal achievement of the currently selected class are generated based on the achievement attributes of each sub-goal entity instance of the course to be analyzed and the achievement attributes of the connected total course goal entity instance.

[0009] Based on the aforementioned outcome-oriented continuous improvement teaching knowledge graph construction and application method, and based on the learning outcome entity instances connected to each course knowledge point entity instance in the teaching process knowledge graph, the knowledge mastery rate of the corresponding course knowledge point entity instances is calculated, forming a teaching process situation analysis result. Based on the teaching process situation analysis result and the course objective achievement analysis result, teaching improvement suggestions for the currently selected class are generated, specifically including: Obtain the average and full scores of the learning outcome entity instances corresponding to different testing methods connected to the entity instances of each course knowledge point in the knowledge graph of the teaching process; For each course knowledge point entity instance, based on the average score and full score of the learning outcome entity instances connected to the corresponding course knowledge point entity instances using different testing methods, the mastery rate of the corresponding course knowledge point entity instances under different testing methods is calculated. The mastery rates of the corresponding course knowledge point entity instances under different testing methods are then integrated to obtain the knowledge point mastery rate of the corresponding course knowledge point entity instances, and the teaching process analysis results are formed. The course sub-goal entity instances whose achievement attribute is lower than a preset threshold in the course goal achievement analysis results are connected to the learning outcome entity instances in the course goal knowledge graph, and the course knowledge point entity instances connected to the learning outcome entity instances in the teaching process knowledge graph. If the mastery rate of the knowledge point entity instance in the course is lower than a preset threshold, teaching improvement suggestions are generated for the knowledge point entity instance in the course.

[0010] Based on the aforementioned outcome-oriented continuous improvement teaching knowledge graph construction and application method, chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances are extracted from the course teaching text, along with the hierarchical relationships between these entities, to construct a course content knowledge graph. Specifically, this includes: Extract chapter title entity instances and course knowledge point entity instances contained under the corresponding chapter title entity instances from the course teaching text; Extract the knowledge point content entity instances corresponding to each course knowledge point entity instance contained in the teaching file corresponding to each chapter title entity instance. Extract keywords from the description attributes of each course knowledge point entity instance, search for the latest content that matches the corresponding course knowledge point entity instance, and update the knowledge point content entity instance corresponding to the corresponding course knowledge point entity instance based on the latest content that matches the corresponding course knowledge point entity instance.

[0011] According to a second aspect of the present invention, an outcome-oriented, continuously improving teaching knowledge graph construction and application system is provided, comprising: The course content knowledge graph construction module is used to extract chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances from course teaching texts, as well as the hierarchical relationship between the chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances, in order to construct a course content knowledge graph. The course objective knowledge graph construction module is used to identify course objective entity instances from the course teaching text, identify learning outcome entity instances corresponding to different testing methods of different courses from the exercise list exported by the course platform, and match the descriptive attributes of each course objective entity instance with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course objective entity instances and the learning outcome entity instances, so as to construct a course objective knowledge graph. The grade attribute update module is used to extract class entity instances and student entity instances, as well as the membership relationships between the student entity instances and the class entity instances, from the student information record text. Based on the grade attributes of each student entity instance belonging to the same class entity instance corresponding to different verification methods, it calculates the class grade data corresponding to different verification methods for the class entity instance. Based on the class grade data corresponding to different verification methods for the class entity instances of the currently selected class, it updates the grade attributes of the learning outcome entity instances corresponding to the corresponding verification methods in the course objective knowledge graph. The course objective achievement analysis module is used to update the achievement attribute of the corresponding course objective entity instance by using the performance attribute of the learning outcome entity instance connected to the course objective entity instance in the course objective knowledge graph, and extract the achievement attribute of the course objective entity instance to form the course objective achievement analysis result of the currently selected class. The teaching process knowledge graph construction module is used to match the descriptive attributes of each learning outcome entity instance in the course objective knowledge graph with the descriptive attributes of the knowledge point content entity instances connected to each course knowledge point entity instance in the course content knowledge graph, so as to obtain the association relationship between the learning outcome entity instance and the course knowledge point entity instance, and construct the teaching process knowledge graph based on the learning outcome entity instance, the course knowledge point entity instance, and the association relationship between the two. The teaching analysis and improvement module is used to calculate the knowledge mastery rate of the corresponding course knowledge point entity instances based on the learning outcome entity instances connected to the knowledge point entity instances of each course in the teaching process knowledge graph, form the teaching process situation analysis results, and generate teaching improvement suggestions for the currently selected class based on the teaching process situation analysis results and the course goal achievement analysis results.

[0012] According to a third aspect of the present invention, an electronic device is provided, comprising: a computer-readable storage medium and a processor; The computer-readable storage medium is used to store executable instructions; The processor is configured to read executable instructions stored in the computer-readable storage medium and execute the method as described in the first aspect.

[0013] According to a fourth aspect of the invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to perform the method as described in the first aspect.

[0014] According to a fifth aspect of the invention, a computer program product is provided, comprising a computer program or instructions that, when executed by a processor, implement the method as described in the first aspect.

[0015] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects: By constructing a course content knowledge graph containing chapter title entity instances, course knowledge point entity instances, knowledge point content entity instances, and their hierarchical relationships, and a course objective knowledge graph containing course objective entity instances, learning outcome entity instances, and their supporting relationships, the course objective knowledge graph is then constructed. Based on the class score data corresponding to different testing methods for the currently selected class entity instance, the score attributes of the learning outcome entity instances corresponding to the testing methods in the course objective knowledge graph are updated. Finally, the achievement attributes of the corresponding course objective entity instances are updated using the score attributes of the learning outcome entity instances connected to the course objective entity instances in the updated course objective knowledge graph, thus forming a comprehensive knowledge graph for the current course objective. The analysis results of the course objective achievement of the selected classes are used to construct a teaching process knowledge graph that includes learning outcome entity instances, course knowledge point entity instances, and the relationships between them. Based on the learning outcome entity instances connected to each course knowledge point entity instance in the teaching process knowledge graph, the knowledge mastery rate of the corresponding course knowledge point entity instances is calculated, forming the teaching process situation analysis results. Based on the above teaching process situation analysis results and course objective achievement analysis results, teaching improvement suggestions for the currently selected classes are generated. This enables more effective and accurate teaching evaluation under the outcome orientation, and thus provides more targeted and flexible more precise teaching improvement suggestions. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating an outcome-oriented, continuous improvement method for constructing and applying a teaching knowledge graph, as provided in an embodiment of the present invention.

[0017] Figure 2 This is a schematic diagram of the structure of an outcome-oriented, continuously improving teaching knowledge graph construction and application system provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0019] This invention provides an outcome-oriented method for constructing and applying a continuous improvement teaching knowledge graph, such as... Figure 1 As shown, it includes: S1. Extract chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances from the course teaching text, as well as the hierarchical relationship between the chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances, in order to construct a course content knowledge graph. S2, identify course target entity instances from the course teaching text, identify learning outcome entity instances corresponding to different testing methods of different courses from the exercise list exported by the course platform, and match the descriptive attributes of each course target entity instance with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course target entity instances and the learning outcome entity instances, so as to construct a course target knowledge graph. S3, extract class entity instances and student entity instances, as well as the membership relationships between the student entity instances and the class entity instances, from the student information record text, and calculate the class performance data corresponding to different verification methods for each student entity instance that belongs to the same class entity instance based on the performance attributes of each student entity instance corresponding to different verification methods. Update the performance attributes of the learning outcome entity instances corresponding to the corresponding verification methods in the course objective knowledge graph based on the class performance data corresponding to the class entity instances of the currently selected class. S4, update the achievement attribute of the corresponding course objective entity instance by using the performance attribute of the learning outcome entity instance connected to the course objective entity instance in the course objective knowledge graph, and extract the achievement attribute of the course objective entity instance to form the course objective achievement analysis result of the currently selected class. S5, match the descriptive attributes of each learning outcome entity instance in the course objective knowledge graph with the descriptive attributes of the knowledge point content entity instances connected to each course knowledge point entity instance in the course content knowledge graph to obtain the association between the learning outcome entity instance and the course knowledge point entity instance, so as to construct a teaching process knowledge graph based on the learning outcome entity instance, the course knowledge point entity instance and the association between the two. S6. Based on the learning outcome entity instances connected to the entity instances of each course knowledge point in the knowledge graph of the teaching process, calculate the knowledge mastery rate of the corresponding course knowledge point entity instances, form the teaching process situation analysis results, and generate teaching improvement suggestions for the currently selected class based on the teaching process situation analysis results and the course goal achievement analysis results.

[0020] Specifically, the course teaching text of one or more courses is first obtained, such as course syllabus text, to extract the corresponding chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances, as well as the hierarchical relationship between the chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances, and then a course content knowledge graph is constructed based on the above-mentioned entity instances and the hierarchical relationship between them.

[0021] In some embodiments, chapter title entity instances and course knowledge point entity instances contained under the corresponding chapter title entity instances can be extracted from the course teaching text to construct a hierarchical relationship between the chapter title entity instances and the course knowledge point entity instances contained under them. That is, the chapter title entity instance is the parent node, and the course knowledge point entity instance is the child node. Subsequently, the knowledge point content entity instances corresponding to each course knowledge point entity instance contained in the corresponding chapter title entity instance are extracted from the teaching file corresponding to each chapter title entity instance. Here, the teaching file can be the teaching PPT file corresponding to the corresponding chapter title entity instance. After extracting the knowledge point content entity instances corresponding to each course knowledge point entity instance, a hierarchical relationship between the course knowledge point entity instances and the knowledge point content entity instances is constructed. That is, the course knowledge point entity instance is the parent node, and the knowledge point content entity instance is the child node. Further, keywords in the descriptive attributes (which describe the basic content of the corresponding knowledge point) of each course knowledge point entity instance are extracted, and the latest content matching the corresponding course knowledge point entity instance is searched. Here, the latest content with a matching degree higher than a preset threshold and a corresponding publication volume higher than a preset threshold can be searched from the Internet or a specific database. The knowledge point content entity instance corresponding to the corresponding course knowledge point entity instance is updated based on the latest content matched with the knowledge point entity instance of the corresponding course to ensure the timeliness and accuracy of each course knowledge point in the course content knowledge graph.

[0022] Furthermore, the system identifies course objective entity instances from course teaching texts and learning outcome entity instances corresponding to different assessment methods in different courses from exercise lists exported from the course platform. It then matches the descriptive attributes of each course objective entity instance with the descriptive attributes of each learning outcome entity instance to obtain the support relationships between them, thus constructing a course objective knowledge graph. Here, each course objective entity instance corresponds to the teaching objective of the corresponding course, and each learning outcome entity instance corresponding to any assessment method corresponds to the learning outcome of a specific class within a specific course for that assessment method. The course objective knowledge graph consists of each course objective entity instance, each learning outcome entity instance, and the support relationships between them. By matching the descriptive attributes of each course objective entity instance with the descriptive attributes of each learning outcome entity instance, the system can obtain the matching learning outcome entity instances for any given course objective entity instance. Based on the learning outcomes reflected in these matching learning outcome entity instances and the teaching objectives reflected in the course objective entity instance, the system can analyze whether the teaching objective has been achieved or to what extent, thereby helping to evaluate teaching effectiveness and provide suggestions for improvement.

[0023] In some embodiments, to construct a course objective knowledge graph, instances of the overall course objective, instances of sub-objectives, and hierarchical relationships between them can be extracted from the course teaching text. The overall course objective instance corresponds to the overall teaching objective of the corresponding course, while the various sub-objectives connected to the overall course objective instance correspond to more specific and granular teaching sub-objectives broken down from the course. Both the overall course objective instance and the sub-objectives instance include at least hierarchical attributes (to distinguish them), descriptive attributes (describing the corresponding teaching objective), and achievement attributes. Additionally, sub-objectives instances also include final exam achievement attributes, daily performance achievement attributes, sub-objective weight attributes, final exam weight attributes, and daily performance weight attributes. The initial values ​​of the achievement attributes, final exam achievement attributes, and daily performance achievement attributes are preset values ​​(e.g., 0), and will be updated after subsequent class selection.

[0024] In addition, a list of exercises with different assessment methods is exported from the course platform. These assessment methods can include classroom exercises, assignments, experiments, and final exams. Then, learning outcome entity instances corresponding to different assessment methods generated during the teaching process of different courses are identified from the exercise list. In some embodiments, learning outcome entity instances include hierarchical class classroom exercise entity instances, single classroom exercise entity instances, and classroom exercise question entity instances (corresponding to the classroom exercise assessment method); hierarchical class assignment entity instances, chapter assignment entity instances, and assignment question entity instances (corresponding to the assignment assessment method); experiment entity instances (corresponding to the experiment assessment method); and hierarchical class exam entity instances, question type entity instances, and question entity instances (corresponding to the final exam assessment method). Each type of learning outcome entity instance includes at least a descriptive attribute (describing the specific assessment content of the corresponding assessment method) and a performance attribute. The performance attribute includes average score and full score. The initial value of the average score is a preset value (e.g., 0), which will be updated after subsequent class selection.

[0025] Here, a class practice instance corresponds to the overall learning outcome of all class practice exercises conducted in a specific class within a course. The average score can be obtained by averaging the scores of all students in that class for each class practice exercise. A single class practice instance corresponds to the learning outcome of a specific class practice exercise conducted in a specific class. The average score can be obtained by averaging the scores of all students in that class for that specific class practice exercise. A class practice question instance corresponds to the learning outcome of a specific question in a specific class practice exercise conducted in a specific class. The average score can be obtained by averaging the scores of all students in that specific question in that class practice exercise. A class assignment instance corresponds to the overall learning outcome of all assignments conducted in a specific class within a course. The average score can be obtained by averaging the scores of all students in that specific assignment in that class. A chapter assignment instance corresponds to the learning outcome of a specific chapter assignment conducted in a specific class. The average score can be obtained by averaging the scores of all students in that specific chapter assignment in that class. A homework question instance corresponds to the learning outcome of a specific homework question in a specific chapter assignment conducted in a specific class. The average score can be obtained by averaging the scores of all students in that specific homework question in that chapter assignment in that class. An experiment entity instance corresponds to the learning outcome of an experiment conducted in a specific class within a specific course. The average score can be obtained by averaging the scores of all students in that class for that experiment. A class exam entity instance corresponds to the learning outcome of a final exam conducted in a specific class within a specific course. The average score can be obtained by averaging the scores of all students in that class for the final exam. A question type entity instance corresponds to the learning outcome of a specific type of question in a specific class's final exam. The average score can be obtained by averaging the scores of all students in that class for that type of question. A question entity instance corresponds to the learning outcome of a specific question within a specific question type in a specific class. The average score can be obtained by averaging the scores of all students in that class for that specific question within that question type.

[0026] The descriptive attributes of each course sub-goal entity instance are matched with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course sub-goal entity instances and each learning outcome entity instance.

[0027] Extract class entity instances, student entity instances, and membership relationships between student and class entity instances from student information records (e.g., student grade records). In some embodiments, student entity instances and hierarchical course and class entity instances can be identified from the student information records, and membership relationships between student and class entity instances can be extracted using rule matching. One course entity instance can correspond to multiple class entity instances, and one class entity instance corresponds to a class participating in a given course. Each student entity instance includes at least a performance attribute corresponding to different testing methods, representing the student's performance in each testing method within their class, including scores for each in-class exercise, assignment, experiment, and final exam.

[0028] Based on the performance attributes of each student entity instance belonging to the same class entity instance, the class performance data corresponding to different testing methods is calculated. The class performance data for any testing method should correspond to the meaning of the average score of the successful learning entity instances corresponding to that testing method. In some embodiments, for the testing method of classroom exercises, there are class classroom exercise entity instances, single classroom exercise entity instances, and classroom exercise question entity instances. Therefore, based on the scores of each student entity instance for each classroom exercise, the average score of all student entity instances for all classroom exercises, the average score of all student entity instances for a single classroom exercise, and the average score of all student entity instances for a single exercise question can be calculated. These scores are then respectively correlated with the average scores of the class classroom exercise entity instances, single classroom exercise entity instances, and classroom exercise question entity instances, serving as the class performance data for the classroom exercise testing method for that class entity instance. Similarly, calculate the average score of all student entity instances for all assignments, the average score of all student entity instances for a single chapter assignment, and the average score of all student entity instances for a single assignment question. These scores are then correlated with the average scores of class assignment entity instances, chapter assignment entity instances, and assignment question entity instances, respectively, serving as the class performance data for this assignment-based testing method for the class entity instances. Calculate the average score of all student entity instances in the corresponding experiments, correlating it with experiment entity instances, serving as the class performance data for this experiment-based testing method for the class entity instances. Calculate the average score of all student entity instances in the final exam, the average score of all student entity instances in a single question type, and the average score of all student entity instances in a single test question. These scores are then correlated with the class exam entity instances, question type entity instances, and test question entity instances, respectively, serving as the class performance data for this final exam-based testing method for the class entity instances.

[0029] Subsequently, the performance attributes of learning outcome entity instances corresponding to different testing methods in the course objective knowledge graph can be updated based on the class performance data corresponding to the class entity instance of the currently selected class for different testing methods. In some embodiments, course entity instances that have a hierarchical relationship with the class entity instance of the currently selected class can be obtained, and the course sub-objective entity instances that match the course entity instance in the course objective knowledge graph (i.e., the same courses corresponding to the course entity instance) and the learning outcome entity instances connected to the aforementioned matched course sub-objective entity instances can be determined to construct a completion relationship between the class entity instance of the currently selected class and the learning outcome entity instances connected to the aforementioned matched course sub-objective entity instances. Then, the performance attributes of learning outcome entity instances that have a completion relationship with the class entity instance of the currently selected class in the course objective knowledge graph are updated based on the class performance data corresponding to the class entity instance of the currently selected class for different testing methods, resulting in an updated course objective knowledge graph for the currently selected class.

[0030] Based on the updated curriculum objective knowledge graph, the achievement attribute of the corresponding curriculum objective entity instance is updated using the performance attribute of the learning outcome entity instances connected to the curriculum objective entity instances. This achievement attribute represents the degree of completion of the corresponding curriculum objective. Based on the achievement attribute of the above curriculum objective entity instances, the analysis results of the curriculum objective achievement of the currently selected class can be generated.

[0031] In some embodiments, the course sub-target entity instances that match the course entity instances connected to the class entity instance corresponding to the currently selected class in the course objective knowledge graph can be extracted as the course sub-target entity instances to be analyzed. For each course sub-target entity instance to be analyzed, on the one hand, based on the average score A of the class exam entity instances connected to the corresponding course sub-target entity instance to be analyzed... exam With a perfect score of F exam Update the final grade achievement attribute of the corresponding sub-objective entity instance of the course to be analyzed in the course objective knowledge graph. For example, the average score A mentioned above can be calculated. exam With a perfect score of F examThe ratio is used to update the final grade achievement attribute. On the other hand, based on the average and full marks of the class practice entity instances, class assignment entity instances, and experiment entity instances connected to the corresponding sub-goal entity instances of the course to be analyzed, the daily performance achievement attribute of the corresponding sub-goal entity instances of the course to be analyzed in the course goal knowledge graph is updated. For example, the average scores of the above class practice entity instances, class assignment entity instances, and experiment entity instances can be weighted and summed based on the weights corresponding to the class practice entity instances, class assignment entity instances, and experiment entity instances to obtain the daily performance score. Then, the full marks of the above class practice entity instances, class assignment entity instances, and experiment entity instances can be weighted and summed based on the weights corresponding to the class practice entity instances, class assignment entity instances, and experiment entity instances to obtain the daily performance full mark. Finally, the ratio between the daily performance score and the daily performance full mark is calculated to update the daily performance achievement attribute of the corresponding sub-goal entity instance of the course to be analyzed.

[0032] For each sub-goal entity instance of the course to be analyzed, a weighted sum is performed based on the final exam achievement rate attribute, daily performance achievement rate attribute, final exam weight attribute, and daily performance weight attribute of the corresponding sub-goal entity instance to update the achievement rate attribute of the corresponding sub-goal entity instance. Furthermore, a weighted sum can also be performed based on the achievement rate attribute and sub-goal weight attribute of each sub-goal entity instance to update the achievement rate attribute of the connected overall course goal entity instance. Finally, based on the achievement rate attributes of each sub-goal entity instance and the achievement rate attributes of the connected overall course goal entity instance, the course goal achievement analysis results for the currently selected class are generated.

[0033] To accurately assess the mastery of knowledge points in each course during the teaching process and promote teaching improvement, the descriptive attributes of each learning outcome entity instance in the course objective knowledge graph can be matched with the descriptive attributes of the knowledge point content entity instances connected to each course knowledge point entity instance in the course content knowledge graph. This yields the association between learning outcome entity instances and course knowledge point entity instances, thereby constructing a teaching process knowledge graph based on the learning outcome entity instances, course knowledge point entity instances, and the association between them.

[0034] Based on the learning outcome entity instances connected to each course knowledge point entity instance in the knowledge graph of the teaching process, the knowledge mastery rate of the corresponding course knowledge point entity instances is calculated, forming the teaching process situation analysis results. Specifically, for classroom exercises as the assessment method, a course knowledge point entity instance may be connected to one or more classroom exercise question entity instances; for homework as the assessment method, a course knowledge point entity instance may be connected to one or more homework question entity instances; for the final exam as the assessment method, a course knowledge point entity instance may be connected to one or more exam question entity instances. In some embodiments, the average score and full score of the learning outcome entity instances connected to each course knowledge point entity instance in the knowledge graph corresponding to different assessment methods can be obtained. For each course knowledge point entity instance, based on the average score and full score of the learning outcome entity instances connected to the corresponding course knowledge point entity instance for different assessment methods, the mastery rate of the corresponding course knowledge point entity instance under different assessment methods is calculated. In some embodiments, for any testing method, if any course knowledge point entity instance is connected to multiple learning outcome entity instances under that testing method (e.g., connected to multiple classroom exercise entity instances), the average of the ratios between the average score of the multiple learning outcome entity instances and their full score can be calculated as the mastery rate of the course knowledge point entity instance under that testing method. Subsequently, the mastery rates of the course knowledge point entity instances under different testing methods are fused (either by directly calculating the average or by weighted summation) to obtain the knowledge point mastery rate of the course knowledge point entity instances, thereby forming the teaching process analysis results.

[0035] Based on the analysis results of the teaching process and the achievement of course objectives in the currently selected class, which reflect the mastery of knowledge points and the achievement of course objectives, teaching improvement suggestions are generated for the currently selected class. In some embodiments, it is possible to identify the learning outcome entity instances connected to course sub-objective entity instances with achievement attributes below a preset threshold in the course objective knowledge graph, and the course knowledge point entity instances connected to these learning outcome entity instances in the teaching process knowledge graph. If the knowledge point mastery rate of the aforementioned course knowledge point entity instances is below a preset threshold, teaching improvement suggestions can be generated for those course knowledge point entity instances. For example, it can be suggested to add more focused explanations of the knowledge points represented by the course knowledge point entity instances during the teaching process. In addition, if the course knowledge point entity instance lacks connections to learning outcome entity instances corresponding to one or more verification methods in the teaching process knowledge graph, it can also be suggested to add corresponding verification methods during the teaching process, thereby achieving teaching improvement.

[0036] In summary, the method provided by this invention constructs a course content knowledge graph containing chapter title entity instances, course knowledge point entity instances, knowledge point content entity instances, and their hierarchical relationships; it also constructs a course objective knowledge graph containing course objective entity instances, learning outcome entity instances, and their supporting relationships. Then, based on the class score data corresponding to different testing methods for the class entity instance of the currently selected class, the method updates the score attributes of the learning outcome entity instances corresponding to the testing methods in the course objective knowledge graph. Finally, it uses the score attributes of the learning outcome entity instances connected to the course objective entity instances in the updated course objective knowledge graph to update the achievement of the corresponding course objective entity instances. The system uses degree attributes to form an analysis result of the achievement of course objectives for the currently selected class. In addition, it constructs a teaching process knowledge graph that includes learning outcome entity instances, course knowledge point entity instances, and the relationships between them. Based on the learning outcome entity instances connected to each course knowledge point entity instance in the teaching process knowledge graph, it calculates the knowledge mastery rate of the corresponding course knowledge point entity instances, forming a teaching process situation analysis result. Based on the above teaching process situation analysis result and the course objective achievement analysis result, it generates teaching improvement suggestions for the currently selected class, which can achieve more effective and accurate teaching evaluation under the outcome orientation, and thus provide more targeted and flexible more precise teaching improvement suggestions.

[0037] The following describes the outcome-oriented continuous improvement teaching knowledge graph construction and application system provided by this invention. The outcome-oriented continuous improvement teaching knowledge graph construction and application system described below can be referred to in correspondence with the outcome-oriented continuous improvement teaching knowledge graph construction and application method described above.

[0038] This invention provides an outcome-oriented, continuous improvement teaching knowledge graph construction and application system, such as... Figure 2 As shown, it includes: The course content knowledge graph construction module 210 is used to extract chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances from the course teaching text, as well as the hierarchical relationship between the chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances, in order to construct a course content knowledge graph. The course objective knowledge graph construction module 220 is used to identify course objective entity instances from the course teaching text, identify learning outcome entity instances corresponding to different testing methods of different courses from the exercise list exported by the course platform, and match the descriptive attributes of each course objective entity instance with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course objective entity instances and the learning outcome entity instances, so as to construct a course objective knowledge graph. The grade attribute update module 230 is used to extract class entity instances and student entity instances, as well as the membership relationship between the student entity instances and the class entity instances, from the student information record text, and calculate the class grade data corresponding to different verification methods for each student entity instance that belongs to the same class entity instance based on the grade attributes corresponding to different verification methods for each student entity instance. Based on the class grade data corresponding to different verification methods for the class entity instances of the currently selected class, the module updates the grade attributes of the learning outcome entity instances corresponding to the corresponding verification methods in the course objective knowledge graph. The course objective achievement analysis module 240 is used to update the achievement attribute of the corresponding course objective entity instance by using the performance attribute of the learning outcome entity instance connected to the course objective entity instance in the course objective knowledge graph, and extract the achievement attribute of the course objective entity instance to form the course objective achievement analysis result of the currently selected class. The teaching process knowledge graph construction module 250 is used to match the descriptive attributes of each learning outcome entity instance in the course objective knowledge graph with the descriptive attributes of the knowledge point content entity instances connected to each course knowledge point entity instance in the course content knowledge graph, so as to obtain the association relationship between the learning outcome entity instance and the course knowledge point entity instance, and to construct the teaching process knowledge graph based on the learning outcome entity instance, the course knowledge point entity instance and the association relationship between the two. The teaching analysis and improvement module 260 is used to calculate the knowledge mastery rate of the corresponding course knowledge point entity instances based on the learning outcome entity instances connected to the knowledge point entity instances of each course in the teaching process knowledge graph, form the teaching process situation analysis results, and generate teaching improvement suggestions for the currently selected class based on the teaching process situation analysis results and the course goal achievement analysis results.

[0039] This invention provides an electronic device, including: a computer-readable storage medium and a processor; The computer-readable storage medium is used to store executable instructions; The processor is configured to read executable instructions stored in the computer-readable storage medium and execute the method as described in any of the above embodiments.

[0040] This invention provides a computer-readable storage medium storing computer instructions that cause a processor to perform the method described in any of the above embodiments.

[0041] This invention provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the method described in any of the above embodiments.

[0042] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A results-oriented method for constructing and applying a continuous improvement teaching knowledge graph, characterized in that, include: S1. Extract chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances from the course teaching text, as well as the hierarchical relationship between the chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances, in order to construct a course content knowledge graph. S2, identify course target entity instances from the course teaching text, identify learning outcome entity instances corresponding to different testing methods of different courses from the exercise list exported by the course platform, and match the descriptive attributes of each course target entity instance with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course target entity instances and the learning outcome entity instances, so as to construct a course target knowledge graph. S3, extract class entity instances and student entity instances, as well as the membership relationships between the student entity instances and the class entity instances, from the student information record text, and calculate the class performance data corresponding to different verification methods for each student entity instance that belongs to the same class entity instance based on the performance attributes of each student entity instance corresponding to different verification methods. Update the performance attributes of the learning outcome entity instances corresponding to the corresponding verification methods in the course objective knowledge graph based on the class performance data corresponding to the class entity instances of the currently selected class. S4, update the achievement attribute of the corresponding course objective entity instance by using the performance attribute of the learning outcome entity instance connected to the course objective entity instance in the course objective knowledge graph, and extract the achievement attribute of the course objective entity instance to form the course objective achievement analysis result of the currently selected class. S5, match the descriptive attributes of each learning outcome entity instance in the course objective knowledge graph with the descriptive attributes of the knowledge point content entity instances connected to each course knowledge point entity instance in the course content knowledge graph to obtain the association between the learning outcome entity instance and the course knowledge point entity instance, so as to construct a teaching process knowledge graph based on the learning outcome entity instance, the course knowledge point entity instance and the association between the two. S6. Based on the learning outcome entity instances connected to the entity instances of each course knowledge point in the knowledge graph of the teaching process, calculate the knowledge mastery rate of the corresponding course knowledge point entity instances, form the teaching process situation analysis results, and generate teaching improvement suggestions for the currently selected class based on the teaching process situation analysis results and the course goal achievement analysis results.

2. The outcome-oriented, continuous improvement teaching knowledge graph construction and application method as described in claim 1, characterized in that, The process involves identifying course objective entity instances from the course teaching text, identifying learning outcome entity instances corresponding to different testing methods from the exercise list exported from the course platform, and matching the descriptive attributes of each course objective entity instance with the descriptive attributes of each learning outcome entity instance corresponding to different testing methods to obtain the support relationship between the course objective entity instances and the learning outcome entity instances. Specifically, this includes: Extract the overall course objective entity instance, sub-objective entity instances, and hierarchical relationships between the overall course objective entity instance and the sub-objective entity instances from the course teaching text; the overall course objective entity instance and the sub-objective entity instance include at least hierarchical attributes, descriptive attributes, and achievement attributes, and the sub-objective entity instance also includes final exam achievement attribute, daily performance achievement attribute, sub-objective weight attribute, final exam weight attribute, and daily performance weight attribute; wherein, the initial values ​​of the achievement attributes, the final exam achievement attribute, and the daily performance achievement attribute are preset values; Export a list of exercises with different assessment methods from the course platform; the assessment methods include classroom exercises, assignments, experiments, and final exams. The learning outcome entity instances corresponding to different assessment methods generated during the teaching process of different courses are identified from the exercise list. The learning outcome entity instances include class practice entity instances, single class practice entity instances, and class practice question entity instances with hierarchical relationships; class assignment entity instances, chapter assignment entity instances, and assignment question entity instances with hierarchical relationships; experiment entity instances; and class exam entity instances, test type entity instances, and test question entity instances with hierarchical relationships. Each type of learning outcome entity instance includes at least a descriptive attribute and a performance attribute. The performance attribute includes the average score and the full score, and the initial value of the average score is a preset value. The descriptive attributes of each course sub-goal entity instance are matched with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course sub-goal entity instances and each learning outcome entity instance.

3. The outcome-oriented, continuous improvement teaching knowledge graph construction and application method as described in claim 2, characterized in that, Extract class entity instances and student entity instances, as well as the membership relationships between the student entity instances and the class entity instances, from the student information records. Calculate the class performance data for each class entity instance corresponding to different validation methods based on the performance attributes of each student entity instance belonging to the same class entity instance. Update the performance attributes of the learning outcome entity instances corresponding to the corresponding validation methods in the course objective knowledge graph based on the class performance data for the class entity instances of the currently selected class. Specifically, this includes: Identify student entity instances, course entity instances, and class entity instances with hierarchical relationships from the student information record text, and extract the membership relationship between the student entity instances and the class entity instances using rule matching; the student entity instances include at least grade attributes corresponding to different verification methods; For each class entity instance, calculate the class score data corresponding to different validation methods for each student entity instance that belongs to the corresponding class entity instance based on the score attributes of each student entity instance corresponding to different validation methods. Obtain the course entity instance connected to the class entity instance corresponding to the currently selected class, determine the course sub-target entity instance that matches the course entity instance in the course target knowledge graph, and the learning outcome entity instance connected to the matched course sub-target entity instance, so as to construct the completion relationship between the class entity instance corresponding to the currently selected class and the learning outcome entity instance connected to the matched course sub-target entity instance. The course objective knowledge graph updates the performance attributes of learning outcome entity instances that have a completion relationship with the class entity instance corresponding to the currently selected class based on the class performance data corresponding to different testing methods.

4. The outcome-oriented continuous improvement teaching knowledge graph construction and application method as described in claim 3, characterized in that, The achievement attribute of the corresponding course objective entity instance is updated using the performance attribute of the learning outcome entity instance connected to the course objective entity instance in the course objective knowledge graph. The achievement attribute of the course objective entity instance is then extracted to form the course objective achievement analysis results for the currently selected class, specifically including: Extract the course entity instance that is connected to the class entity instance corresponding to the currently selected class and match the course sub-target entity instance in the course target knowledge graph, and use it as the course sub-target entity instance to be analyzed. For each sub-target entity instance of the course to be analyzed, based on the average score and full score of the class exam entity instances connected to the corresponding sub-target entity instance, update the final exam achievement attribute of the corresponding sub-target entity instance in the course target knowledge graph; based on the average score and full score of the class classroom exercise entity instances, class homework entity instances, and experiment entity instances connected to the corresponding sub-target entity instance, update the daily performance achievement attribute of the corresponding sub-target entity instance in the course target knowledge graph. For each sub-target entity instance of the course to be analyzed, a weighted sum is performed based on the final exam achievement attribute, the daily performance achievement attribute, the final exam weight attribute, and the daily performance weight attribute of the corresponding sub-target entity instance of the course to be analyzed, so as to update the achievement attribute of the corresponding sub-target entity instance of the course to be analyzed. The achievement attributes and weight attributes of each sub-goal entity instance of the course to be analyzed are weighted and summed to update the achievement attribute of the connected total course goal entity instance. The achievement analysis results of the course goal achievement of the currently selected class are generated based on the achievement attributes of each sub-goal entity instance of the course to be analyzed and the achievement attributes of the connected total course goal entity instance.

5. The outcome-oriented continuous improvement teaching knowledge graph construction and application method as described in claim 2, characterized in that, Based on the learning outcome entity instances connected to the entity instances of each course knowledge point in the knowledge graph of the teaching process, the knowledge mastery rate of the corresponding course knowledge point entity instances is calculated, forming a teaching process situation analysis result. Based on the teaching process situation analysis result and the course objective achievement analysis result, teaching improvement suggestions for the currently selected class are generated, specifically including: Obtain the average and full scores of the learning outcome entity instances corresponding to different testing methods connected to the entity instances of each course knowledge point in the knowledge graph of the teaching process; For each course knowledge point entity instance, based on the average score and full score of the learning outcome entity instances connected to the corresponding course knowledge point entity instances using different testing methods, the mastery rate of the corresponding course knowledge point entity instances under different testing methods is calculated. The mastery rates of the corresponding course knowledge point entity instances under different testing methods are then integrated to obtain the knowledge point mastery rate of the corresponding course knowledge point entity instances, and the teaching process analysis results are formed. The course sub-goal entity instances whose achievement attribute is lower than a preset threshold in the course goal achievement analysis results are connected to the learning outcome entity instances in the course goal knowledge graph, and the course knowledge point entity instances connected to the learning outcome entity instances in the teaching process knowledge graph. If the mastery rate of the knowledge point entity instance in the course is lower than a preset threshold, teaching improvement suggestions are generated for the knowledge point entity instance in the course.

6. The method for constructing and applying outcome-oriented, continuous improvement teaching knowledge graphs as described in claim 1, characterized in that, Extracting chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances from the course teaching text, as well as the hierarchical relationships between these entities, to construct a course content knowledge graph, specifically including: Extract chapter title entity instances and course knowledge point entity instances contained under the corresponding chapter title entity instances from the course teaching text; Extract the knowledge point content entity instances corresponding to each course knowledge point entity instance contained in the teaching file corresponding to each chapter title entity instance. Extract keywords from the description attributes of each course knowledge point entity instance, search for the latest content that matches the corresponding course knowledge point entity instance, and update the knowledge point content entity instance corresponding to the corresponding course knowledge point entity instance based on the latest content that matches the corresponding course knowledge point entity instance.

7. An outcome-oriented, continuous improvement teaching knowledge graph construction and application system, characterized in that, include: The course content knowledge graph construction module is used to extract chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances from course teaching texts, as well as the hierarchical relationship between the chapter title entity instances, course knowledge point entity instances, and knowledge point content entity instances, in order to construct a course content knowledge graph. The course objective knowledge graph construction module is used to identify course objective entity instances from the course teaching text, identify learning outcome entity instances corresponding to different testing methods of different courses from the exercise list exported by the course platform, and match the descriptive attributes of each course objective entity instance with the descriptive attributes of each learning outcome entity instance to obtain the support relationship between the course objective entity instances and the learning outcome entity instances, so as to construct a course objective knowledge graph. The grade attribute update module is used to extract class entity instances and student entity instances, as well as the membership relationships between the student entity instances and the class entity instances, from the student information record text. Based on the grade attributes of each student entity instance belonging to the same class entity instance corresponding to different verification methods, it calculates the class grade data corresponding to different verification methods for the class entity instance. Based on the class grade data corresponding to different verification methods for the class entity instances of the currently selected class, it updates the grade attributes of the learning outcome entity instances corresponding to the corresponding verification methods in the course objective knowledge graph. The course objective achievement analysis module is used to update the achievement attribute of the corresponding course objective entity instance by using the performance attribute of the learning outcome entity instance connected to the course objective entity instance in the course objective knowledge graph, and extract the achievement attribute of the course objective entity instance to form the course objective achievement analysis result of the currently selected class. The teaching process knowledge graph construction module is used to match the descriptive attributes of each learning outcome entity instance in the course objective knowledge graph with the descriptive attributes of the knowledge point content entity instances connected to each course knowledge point entity instance in the course content knowledge graph, so as to obtain the association relationship between the learning outcome entity instance and the course knowledge point entity instance, and construct the teaching process knowledge graph based on the learning outcome entity instance, the course knowledge point entity instance, and the association relationship between the two. The teaching analysis and improvement module is used to calculate the knowledge mastery rate of the corresponding course knowledge point entity instances based on the learning outcome entity instances connected to the knowledge point entity instances of each course in the teaching process knowledge graph, form the teaching process situation analysis results, and generate teaching improvement suggestions for the currently selected class based on the teaching process situation analysis results and the course goal achievement analysis results.

8. An electronic device, characterized in that, include: Computer-readable storage media and processors; The computer-readable storage medium is used to store executable instructions; The processor is used to read executable instructions stored in the computer-readable storage medium and execute the outcome-oriented continuous improvement teaching knowledge graph construction and application method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to execute the outcome-oriented, continuous improvement teaching knowledge graph construction and application method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by the processor, they implement the outcome-oriented continuous improvement teaching knowledge graph construction and application method as described in any one of claims 1-6.

Images