Semantic reasoning-based postgraduate medical course optimization method and system

Abstract

The invention relates to the technical field of course optimization, and discloses a postgraduate student medical course optimization method and system based on semantic reasoning, and the method comprises the steps: obtaining a medical learning course set, constructing a learning course map, optimizing the learning course map, and obtaining an optimized learning course map, sequentially extracting a target learner course set from a plurality of target learner course sets, formulating a personalized learning course set, obtaining an optimal recommended course sequence, obtaining ideal learning courses of target learners, obtaining execution times, and if the execution times are greater than a preset execution times threshold, executing the target learners according to the optimal recommended course sequence; if yes, any optimal recommendation course in the optimal recommendation course sequence serves as an ideal learning course, the ideal learning courses are summarized to obtain an ideal learning course set, and postgraduate student medical course optimization based on semantic reasoning is completed based on the ideal learning course set. According to the method, the personalization and the accuracy of course recommendation can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of course optimization, and in particular to a method and system for optimizing a postgraduate medical course based on semantic reasoning. Background Art

[0002] Semantic reasoning refers to a technology based on knowledge representation and logical reasoning, which is used to derive new knowledge or conclusions from existing knowledge. It realizes the reasoning process by analyzing and understanding the semantics of language, so as to be able to process complex and semantically rich information. Graduate medical curriculum optimization refers to the analysis, adjustment and improvement of the curriculum system of medical graduate students through scientific methods and technical means to improve the scientificity, rationality and effectiveness of the curriculum and meet the personalized learning needs and career development goals of medical graduate students.

[0003] Traditional curriculum design is typically based on fixed syllabi and teaching plans, making it difficult to meet the individual learning needs of each graduate student. Furthermore, optimizing medical graduate courses requires considering factors such as course prerequisites, learners' knowledge base, and the frequency of course updates. Therefore, improving the personalization and accuracy of course recommendations is an urgent technical challenge. Summary of the Invention

[0004] The present invention provides a postgraduate medical course optimization method based on semantic reasoning and a computer-readable storage medium, the main purpose of which is to improve the personalization and accuracy of course recommendations and promote the development of medical education and talent training.

[0005] To achieve the above objectives, the present invention provides a method for optimizing graduate medical courses based on semantic reasoning, comprising:

[0006] identifying a medical graduate student database, and obtaining a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes a plurality of medical learning courses;

[0007] Constructing a learning course map based on the medical learning course set, optimizing the learning course map, and obtaining an optimized learning course map;

[0008] Identify a plurality of target learner course sets, wherein the target learner course set includes a plurality of target learner courses, and the target learner course sets correspond to learners one by one;

[0009] Extracting target learner course sets from multiple target learner course sets in sequence, and formulating personalized learning course sets based on the target learner course sets;

[0010] receive a medical course optimization instruction, obtain an optimal recommended course sequence according to the medical course optimization instruction, an optimized learning course graph and a personalized learning course set, wherein the optimal recommended course sequence comprises three optimal recommended courses;

[0011] obtain an ideal learning course of a target learner, and determine whether the optimal recommended course sequence contains the ideal learning course;

[0012] If the optimal recommended course sequence does not contain the ideal learning course, the ideal learning course is imported into the optimized learning course graph to obtain an updated learning course graph, the updated learning course graph is taken as the optimized learning course graph, and the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course graph and the personalized learning course set is returned;

[0013] obtain the number of times of executing the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course graph and the personalized learning course set, and compare the number of times with a preset number of times threshold;

[0014] If the number of times is greater than the preset number of times threshold, any one of the optimal recommended courses in the optimal recommended course sequence is taken as the ideal learning course;

[0015] aggregate the ideal learning courses to obtain an ideal learning course set, and complete postgraduate medical course optimization based on semantic reasoning based on the ideal learning course set.

[0016] Optionally, the learning course graph is constructed according to the medical learning course set, comprising:

[0017] one medical learning course is extracted from the medical learning course set in sequence, and the following operations are performed on the extracted one medical learning course:

[0018] the extracted one medical learning course is excluded from the medical learning course set to obtain a simplified learning course set;

[0019] one simplified learning course is extracted from the simplified learning course set in sequence, medical course learner lists and simplified course learner lists are obtained according to the extracted medical learning course and the extracted simplified learning course, and common learner list sets and all learner list sets are confirmed according to the medical course learner lists and the simplified course learner lists;

[0020] course similarity is calculated according to the common learner list sets and the all learner list sets, wherein the course similarity is the ratio of the number of common learner lists in the common learner list sets to the number of all learners in the all learner list sets;

[0021] Collecting learning course score sets and streamlined learning course score sets corresponding to the medical learning course and streamlined learning course respectively, and calculating the average learning course score and the average streamlined learning course score based on the learning course score sets and the streamlined learning course score sets;

[0022] Calculate the modified cosine similarity based on the average learning course rating, the average condensed learning course rating, the learning course rating set, and the condensed learning course rating set;

[0023] Obtain comprehensive similarity based on course similarity and modified cosine similarity, summarize the comprehensive similarities to obtain a comprehensive similarity set, and determine whether there is a comprehensive similarity greater than a preset comprehensive similarity threshold in the comprehensive similarity set;

[0024] If there is no comprehensive similarity greater than the preset comprehensive similarity threshold in the comprehensive similarity set, returning to the step of sequentially extracting medical learning courses from the medical learning course set until the medical learning course set is an empty set;

[0025] If there is a comprehensive similarity greater than a preset comprehensive similarity threshold in the comprehensive similarity set, the medical learning courses and streamlined learning courses corresponding to the comprehensive similarity are integrated to obtain a related learning course group;

[0026] The associated learning course groups are aggregated to obtain an associated learning course group set, and a learning course map is constructed according to the associated learning course group set, wherein the learning course map includes: multiple learning courses.

[0027] Optionally, the calculation formula of the modified cosine similarity is as follows:

[0028]

[0029] Among them, X represents the modified cosine similarity, E a,i represents the i-th learning course rating in the learning course rating set, E b,j represents the jth streamlined learning course rating in the streamlined learning course rating set, represents the average learning course rating, represents the average streamlined learning course rating, n represents the number of learning course ratings in the learning course rating set, m represents the number of streamlined learning course ratings in the streamlined learning course rating set, i represents the index of the learning course rating, and j represents the index of the streamlined learning course rating.

[0030] Optionally, optimizing the learning course map to obtain an optimized learning course map includes:

[0031] Perform the following operations for each learning course in the learning course map:

[0032] Obtain course books based on the course, obtain the name of the research major based on the course books, retrieve a set of school names based on the name of the research major, and query a set of similar study textbooks with the same name as the research major in the set of school names;

[0033] If the similar learning textbook set is an empty set, the name of the research major is expanded to obtain an updated major name, the updated major name is used as the research major name, and the process returns to the step of retrieving the set of school names based on the research major name until the similar learning textbook set is not an empty set;

[0034] If the similar learning textbook set is not an empty set, obtaining a similar learning course set based on the similar learning textbook set, and combining each similar learning course in the similar learning course set with the learning course to obtain an associated similar course group;

[0035] The related similar course groups are aggregated to obtain a related similar course group set, and an optimized learning course map is constructed based on the related similar course group set and the learning course map.

[0036] Optionally, the step of formulating a personalized learning course set based on the target learner's course set includes:

[0037] Obtain undergraduate majors based on the target learner course set, and obtain course grade group sets based on the target learner course set, wherein the course grade groups in the course grade group set correspond one-to-one to the learner courses in the target learner course set;

[0038] Classify the course score groups to obtain a basic course score set, a professional course score set, and a practical course score set, and calculate the highest basic course score and the lowest basic course score based on the basic course score set;

[0039] Calculate the highest and lowest professional course scores based on the professional course score set, and calculate the highest and lowest practical course scores based on the practical course score set;

[0040] Obtain advantaged courses and disadvantaged courses based on the highest basic course score, the lowest basic course score, the highest professional course score, the lowest professional course score, the highest practical course score, and the lowest practical course score;

[0041] Obtain professional data based on undergraduate majors and research directions, conduct cross-disciplinary judgment on the professional data, and obtain judgment data, wherein the judgment data is cross-disciplinary data or non-cross-disciplinary data;

[0042] If the data is determined to be cross-disciplinary data, the professional span value is obtained to determine whether the professional span value is greater than a preset professional span threshold. If the professional span value is greater than the preset professional span threshold, a cross-disciplinary learning course set is formulated based on the advantageous courses and the disadvantageous courses.

[0043] If the data is judged to be non-interdisciplinary data, a non-interdisciplinary learning course set will be developed based on the strong and weak courses;

[0044] A cross-disciplinary learning course set or a non-cross-disciplinary learning course set is regarded as a personalized learning course set, wherein the personalized learning course set includes one or more personalized learning courses.

[0045] Optionally, obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set includes:

[0046] According to the medical course optimization instructions, the recommended courses are extracted from the optimized learning course map in sequence, the course matching degree is calculated based on the personalized learning course set and the recommended courses, and the course matching degree is compared with the preset course matching degree threshold;

[0047] If the course matching degree is greater than the preset course matching degree threshold, the course to be recommended will be used as a recommended course;

[0048] If the course matching degree is less than or equal to the preset course matching degree threshold, then return to the step of sequentially extracting the courses to be recommended from the optimized learning course map until all the courses to be recommended in the optimized learning course map are extracted;

[0049] Summarize the recommended courses to obtain the recommended course group, and obtain the optimal recommended course sequence based on the recommended course group.

[0050] Optionally, calculating the course matching degree based on the personalized learning course set and the courses to be recommended includes:

[0051] Extracting personalized learning courses from the personalized learning course set, obtaining personalized course knowledge point groups of the personalized learning courses, summarizing the personalized course knowledge point groups, and obtaining a personalized course knowledge point group set;

[0052] Obtain the knowledge point set of the recommended course, calculate the knowledge point overlap ratio based on the knowledge point set and the personalized course knowledge point group set, perform course difficulty analysis on the recommended course, and obtain the difficulty value of the recommended course;

[0053] Performing a course difficulty analysis on each personalized learning course in the personalized learning course set to obtain a personalized learning course difficulty value set, and calculating an average personalized course difficulty value based on the personalized learning course difficulty value set;

[0054] Calculate the course difficulty difference based on the difficulty value of the recommended course and the average individual course difficulty value, where the course difficulty difference is the absolute difference between the difficulty value of the recommended course and the average individual course difficulty value;

[0055] Use the pre-built NLP model to perform vector conversion on the recommended courses and personalized learning course sets to obtain the embedding vectors of the recommended courses and the embedding vector sets of personalized courses. In the personalized course embedding vector set, the embedding vector sets of personalized courses correspond one to one with the personalized learning courses.

[0056] The average semantic distance is calculated based on the embedding vectors of the recommended courses and the embedding vectors of the personalized courses. The course synergy effect value of the recommended courses and the personalized learning courses is calculated based on the average semantic distance, the recommended courses and the personalized learning courses to obtain the course adjustment factor.

[0057] The course matching degree is calculated based on the knowledge point overlap ratio, course difficulty difference, course synergy effect value and course adjustment factor.

[0058] Optionally, obtaining the course adjustment factor includes:

[0059] Obtaining a knowledge point set of an advantageous course and a knowledge point set of an inferior course, calculating the similarity of the first course based on the knowledge point set and the knowledge point set of the advantageous course, and calculating the similarity of the second course based on the knowledge point set and the knowledge point set of the inferior course;

[0060] Mapping the first course similarity using a pre-built logic function and a preset numerator adjustment factor to obtain a first mapped similarity;

[0061] The second course similarity is mapped using the logic function to obtain a second mapping similarity, and a course adjustment factor is calculated according to the first mapping similarity and the second mapping similarity, wherein the course adjustment factor is the product of the first mapping similarity and the second mapping similarity.

[0062] Optionally, the calculation formula for the course matching degree is as follows:

[0063]

[0064] Among them, M represents the course matching degree, Indicates the Cth r The difficulty value of the personalized learning course, H represents the number of difficulty values ​​of the personalized learning course in the difficulty value set, d c represents the difficulty value of the recommended course, Z represents the knowledge point overlap ratio, T represents the course synergy effect value, and Q represents the course adjustment factor. Indicates the course difficulty difference, C r Represents the index of the difficulty value of the personalized learning course in the personalized learning course difficulty value set.

[0065] To achieve the above objectives, the present invention further provides a postgraduate medical course optimization system based on semantic reasoning, comprising:

[0066] a course map construction module, configured to identify a medical graduate student database, obtain a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes multiple medical learning courses, construct a learning course map based on the medical learning course set, and optimize the learning course map to obtain an optimized learning course map;

[0067] A personalized learning course formulation module is used to identify multiple target learner course sets, wherein the target learner course set includes multiple target learner courses, and the target learner course set corresponds to the learner one by one, sequentially extract the target learner course sets from the multiple target learner course sets, and formulate a personalized learning course set based on the target learner course sets;

[0068] The optimal recommended course acquisition module is used to receive medical course optimization instructions, obtain the optimal recommended course sequence based on the medical course optimization instructions, the optimized learning course map, and the personalized learning course set, where the optimal recommended course sequence includes three optimal recommended courses, obtain the ideal learning course for the target learner, and determine whether there is an ideal learning course in the optimal recommended course sequence;

[0069] The course optimization completion module is used to import the ideal learning course into the optimized learning course map if there is no ideal learning course in the optimal recommended course sequence, obtain an updated learning course map, use the updated learning course map as the optimized learning course map, return to the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set, obtain the number of executions of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set, compare the number of executions with a preset execution number threshold, and if the number of executions is greater than the preset execution number threshold, use any optimal recommended course in the optimal recommended course sequence as the ideal learning course, summarize the ideal learning courses, obtain the ideal learning course set, and complete the postgraduate medical course optimization based on semantic reasoning based on the ideal learning course set.

[0070] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0071] a memory storing at least one instruction;

[0072] The processor executes the instructions stored in the memory to implement the above-mentioned graduate medical curriculum optimization method based on semantic reasoning.

[0073] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned graduate medical course optimization method based on semantic reasoning.

[0074] The application confirms a medical postgraduate database, obtains a medical learning course set based on the medical postgraduate database, wherein the medical learning course set includes multiple medical learning courses, integrates scattered student learning information and course information, forms a unified data source, constructs a learning course graph based on the medical learning course set, optimizes the learning course graph, and obtains an optimized learning course graph. The learning course graph presents the semantic relationship between medical learning courses in a graphical manner, making the complex relationship between courses intuitive and easy to understand. Through optimization of the learning course graph, potential semantic relationships between courses can be mined, and some previously unnoticed course combinations or knowledge expansion paths can be discovered, providing a new idea for course optimization and adjustment. A plurality of target learner course sets are confirmed, wherein the target learner course set includes a plurality of target learner courses, and the target learner course set corresponds to a learner one by one. The application can accurately reflect the courses that each learner has learned or plans to learn, which provides a basis for subsequent development of personalized learning course sets for each learner. Target learner course sets are sequentially extracted from the plurality of target learner course sets, and personalized learning course sets are developed based on the target learner course sets. The application can fully consider the existing knowledge and learning goals of learners to tailor suitable learning courses for them, which helps to improve the learning interest and learning effect of learners, makes the courses more in line with the actual needs of learners, receives medical course optimization instructions, obtains an optimal recommended course sequence based on the medical course optimization instructions, the optimized learning course graph and the personalized learning course set, wherein the optimal recommended course sequence includes three optimal recommended courses. The application can provide course recommendations that are most in line with the needs and course system logic of learners by combining the optimized learning course graph and the personalized learning course set, improving the accuracy and effectiveness of course recommendations. The ideal learning course of the target learner is obtained, and it is determined whether the optimal recommended course sequence has the ideal learning course. The application can ensure that the recommended courses meet the personalized expectations of learners by determining whether the optimal recommended course sequence has the ideal learning course of the target learner. If the optimal recommended course sequence does not have the ideal learning course, the ideal learning course is imported into the optimized learning course graph to obtain an updated learning course graph. The updated learning course graph is used as the optimized learning course graph, and the step of obtaining the optimal recommended course sequence based on the medical course optimization instructions, the optimized learning course graph and the personalized learning course set is returned. The application can improve the accuracy and adaptability of course recommendations by continuously updating and optimizing the course graph, ensuring that the recommended courses are more in line with the expectations of learners, continuously optimizing the results of course recommendations, and improving the satisfaction of learners.Obtain the execution times of the optimal recommended course sequence obtained according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set, compare the execution times with the preset execution times threshold, the present invention sets the execution times threshold to avoid falling into an infinite loop recommendation process when the ideal learning course cannot be found, and improves the efficiency and stability of the algorithm. If the execution times are greater than the preset execution times threshold, any optimal recommended course in the optimal recommended course sequence is used as the ideal learning course, and the ideal learning courses are summarized to obtain the ideal learning course set. The postgraduate medical course optimization based on semantic reasoning is completed based on the ideal learning course set. The present invention completes course optimization based on the ideal learning course set, which can improve the quality and applicability of medical postgraduate courses, make the courses more in line with students' learning needs and professional development requirements, and help cultivate more outstanding medical professionals. Therefore, the present invention can improve the personalization and accuracy of course recommendations, promote the development of medical education and talent training. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A flowchart of a method for optimizing a postgraduate medical course based on semantic reasoning according to an embodiment of the present invention;

[0076] Figure 2 A functional module diagram of a postgraduate medical course optimization system based on semantic reasoning provided by one embodiment of the present invention;

[0077] Figure 3 A schematic diagram of the structure of an electronic device for implementing the method for optimizing graduate medical courses based on semantic reasoning provided by an embodiment of the present invention;

[0078] Figure 4 A learning course map for implementing the semantic reasoning-based graduate medical course optimization method provided in one embodiment of the present invention.

[0079] Description of reference numerals:

[0080] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0081] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0082] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0083] The embodiment of the present application provides a method for optimizing graduate medical courses based on semantic reasoning. The execution subject of the method for optimizing graduate medical courses based on semantic reasoning includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for optimizing graduate medical courses based on semantic reasoning can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0084] Reference Figure 1 FIG. 1 is a flow chart of a method for optimizing a medical course for postgraduates based on semantic reasoning according to an embodiment of the present invention. In this embodiment, the method for optimizing a medical course for postgraduates based on semantic reasoning includes:

[0085] S1. Identify a medical graduate student database, and obtain a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes multiple medical learning courses.

[0086] It should be explained that the medical graduate student database refers to a database containing information related to medical graduate students, which stores data such as their study records, course selections, grades, research directions, etc.

[0087] S2. Construct a learning course map based on the medical learning course set, optimize the learning course map, and obtain an optimized learning course map.

[0088] In detail, the construction of a learning course map based on a medical learning course set includes:

[0089] Extract one medical learning course from the medical learning course set in turn, and perform the following operations on each extracted medical learning course:

[0090] Eliminate the extracted medical learning course from the medical learning course set to obtain a streamlined learning course set;

[0091] Extracting one streamlined learning course from the streamlined learning course set in sequence, obtaining a list of medical course learners and a list of streamlined course learners based on the extracted medical learning course and the extracted streamlined learning course, and confirming a common learner list set and a list set of all learners based on the list of medical course learners and the list of streamlined course learners;

[0092] Calculate the course similarity based on the common learner list set and the all learner list set, where the course similarity is the ratio of the number of common learner lists in the common learner list set to the number of all learners in the all learner list set;

[0093] Collecting learning course score sets and streamlined learning course score sets corresponding to the medical learning course and streamlined learning course respectively, and calculating the average learning course score and the average streamlined learning course score based on the learning course score sets and the streamlined learning course score sets;

[0094] Calculate the modified cosine similarity based on the average learning course rating, the average condensed learning course rating, the learning course rating set, and the condensed learning course rating set;

[0095] Obtain comprehensive similarity based on course similarity and modified cosine similarity, summarize the comprehensive similarities to obtain a comprehensive similarity set, and determine whether there is a comprehensive similarity greater than a preset comprehensive similarity threshold in the comprehensive similarity set;

[0096] If there is no comprehensive similarity greater than the preset comprehensive similarity threshold in the comprehensive similarity set, returning to the step of sequentially extracting medical learning courses from the medical learning course set until the medical learning course set is an empty set;

[0097] If there is a comprehensive similarity greater than a preset comprehensive similarity threshold in the comprehensive similarity set, the medical learning courses and streamlined learning courses corresponding to the comprehensive similarity are integrated to obtain a related learning course group;

[0098] The associated learning course groups are aggregated to obtain an associated learning course group set, and a learning course map is constructed according to the associated learning course group set, wherein the learning course map includes: multiple learning courses.

[0099] It should be explained that a medical learning course refers to a medical course in the medical learning course set. A streamlined learning course refers to a course extracted from the streamlined learning course set. The streamlined learning course set refers to a subset obtained by gradually eliminating the extracted medical learning courses from the medical learning course set. The present invention extracts only one medical learning course from the medical learning course set each time. This method allows the system to perform detailed analysis and processing on the currently extracted course at each step, rather than processing all courses at once. This ensures that each course receives sufficient attention and avoids inaccurate processing or omissions due to excessive data volume. At the same time, by extracting only one medical learning course each time, the similarity between the course and each streamlined learning course in the streamlined learning course set can be calculated more accurately. Through gradual extraction and calculation, the system can analyze the relationship between courses more carefully, thereby more accurately constructing a learning course map. For example, a medical course set is (Medical Course 1, Medical Course 2, Medical Course 3). If Medical Course 1 is extracted from the medical course set, then after removing Medical Course 1 from the set, the resulting medical course set (Medical Course 2, Medical Course 3) is obtained. This removed medical course set (Medical Course 2, Medical Course 3) is then used as the streamlined course set. A medical course learner list is a list of all students taking a particular medical course. A streamlined course learner list is a list of all students taking a streamlined course. A co-learner list is a set of all students taking two courses simultaneously. A list of all learners is a set of all students taking two courses. A course rating set is a list of ratings for all students taking a particular course. A streamlined course rating set is a list of ratings for all students taking a streamlined course. An average course rating is the average of all ratings for a course. An average streamlined course rating is the average of all ratings for a particular streamlined course. The scoring described in the embodiment of the present invention means that the scores in the learning course scoring set and the streamlined learning course scoring set are all the evaluation scores of the course by each learner in the past. Optionally, the students' evaluation scores for each course are collected in the form of a questionnaire. Comprehensive similarity refers to the value obtained by adding the course similarity and the modified cosine similarity. Comprehensive similarity set refers to a set consisting of all comprehensive similarities. Comprehensive similarity threshold refers to a pre-set value used to judge whether two courses are similar enough to decide whether to establish a connection between them. Associated learning course groups refer to medical learning courses and streamlined learning courses corresponding to comprehensive similarities greater than the preset comprehensive similarity threshold. Associated learning course group set refers to a set consisting of all associated learning course groups.Constructing a learning course graph based on the associated learning course group set involves treating each learning course in the associated learning course group set as a node to obtain all nodes, connecting each associated learning course group in the associated learning course group set to form edges to obtain all edges, and constructing a learning course graph based on all nodes and all edges. Integration involves placing medical learning courses and streamlined learning courses into a single set.

[0100] In detail, the calculation formula of the modified cosine similarity is as follows:

[0101]

[0102] Among them, X represents the modified cosine similarity, E a,i represents the i-th learning course rating in the learning course rating set, E b,j represents the jth streamlined learning course rating in the streamlined learning course rating set, represents the average learning course rating, represents the average streamlined learning course rating, n represents the number of learning course ratings in the learning course rating set, m represents the number of streamlined learning course ratings in the streamlined learning course rating set, i represents the index of the learning course rating, and j represents the index of the streamlined learning course rating.

[0103] It should be explained that the corrected cosine similarity is measured by calculating the cosine similarity of the rating vectors of two courses and centering the rating vectors (subtracting the average rating).

[0104] In detail, the optimizing the learning course map to obtain the optimized learning course map includes:

[0105] Perform the following operations for each learning course in the learning course map:

[0106] Obtain course books based on the course, obtain the name of the research major based on the course books, retrieve a set of school names based on the name of the research major, and query a set of similar study textbooks with the same name as the research major in the set of school names;

[0107] If the similar learning textbook set is an empty set, the name of the research major is expanded to obtain an updated major name, the updated major name is used as the research major name, and the process returns to the step of retrieving the set of school names based on the research major name until the similar learning textbook set is not an empty set;

[0108] If the similar learning textbook set is not an empty set, obtaining a similar learning course set based on the similar learning textbook set, and combining each similar learning course in the similar learning course set with the learning course to obtain an associated similar course group;

[0109] The related similar course groups are aggregated to obtain a related similar course group set, and an optimized learning course map is constructed based on the related similar course group set and the learning course map.

[0110] It should be explained that the study course book refers to the textbook required for each study course. The name of the research major refers to the name of the graduate professional field to which the study course book belongs. The set of school names refers to the set of all schools that offer courses in this research major. The set of similar study textbooks refers to the teaching materials used for courses with the same name as the research major offered in different schools. The said expansion of the name of the research major refers to expanding the name of the research major to a broader name of the major. Updating the name of the major refers to using the expanded name of the major as the new name of the research major. For example, the name of the research major is "Ophthalmology (professional code 100212) under the branch of Clinical Medicine (professional code 1002)". The name of the research major is expanded to obtain the updated name of "Clinical Medicine (professional code 1002)". The associated similar course group is the combination obtained by combining each similar study course in the similar study course set with the study course when the similar study course set is not an empty set. The set of associated similar course groups refers to the set of all associated similar course groups. The construction of an optimized learning course map based on the associated similar course group set and the learning course map means that if some courses have already established associations in the learning course map and are associated again in the associated similar course group set, an edge is added to the learning course map and the weight of the edge is increased by using the association weight coefficient. If some courses have not established associations in the learning course map, associations are established for the courses to construct a new learning course map. The new learning course map is the optimized learning course map. The learning course map of the present invention is as follows: Figure 4 As shown, 0.25 represents the association weight coefficient. Since course C contains four edges, the association weight coefficient is 1 / 4. If two edges are added between course C and course B, the association weight coefficient is 1 / 6, and the association weight coefficient between course C and course B is 3 / 6. The association weight coefficient is related to the number of edges between different nodes.

[0111] S3. Identify multiple target learner course sets, where the target learner course set includes multiple target learner courses, and the target learner course set corresponds to the learner one by one.

[0112] It should be explained that target learner courses are courses that are relevant to specific learners (medical postgraduates) and meet their learning needs and goals. These courses are determined based on the learners' professional direction, research interests, and career plans.

[0113] S4. Extract target learner course sets from multiple target learner course sets in sequence, and formulate personalized learning course sets based on the target learner course sets.

[0114] Specifically, the process of formulating a personalized learning course set based on the target learner's course set includes:

[0115] Obtain undergraduate majors based on the target learner course set, and obtain course grade group sets based on the target learner course set, wherein the course grade groups in the course grade group set correspond one-to-one to the learner courses in the target learner course set;

[0116] Classify the course score groups to obtain a basic course score set, a professional course score set, and a practical course score set, and calculate the highest basic course score and the lowest basic course score based on the basic course score set;

[0117] Calculate the highest and lowest professional course scores based on the professional course score set, and calculate the highest and lowest practical course scores based on the practical course score set;

[0118] Obtain advantaged courses and disadvantaged courses based on the highest basic course score, the lowest basic course score, the highest professional course score, the lowest professional course score, the highest practical course score, and the lowest practical course score;

[0119] Obtain professional data based on undergraduate majors and research directions, conduct cross-disciplinary judgment on the professional data, and obtain judgment data, wherein the judgment data is cross-disciplinary data or non-cross-disciplinary data;

[0120] If the data is determined to be cross-disciplinary data, the professional span value is obtained to determine whether the professional span value is greater than a preset professional span threshold. If the professional span value is greater than the preset professional span threshold, a cross-disciplinary learning course set is formulated based on the advantageous courses and the disadvantageous courses.

[0121] If the data is judged to be non-interdisciplinary data, a non-interdisciplinary learning course set will be developed based on the strong and weak courses;

[0122] A cross-disciplinary learning course set or a non-cross-disciplinary learning course set is regarded as a personalized learning course set, wherein the personalized learning course set includes one or more personalized learning courses.

[0123] It should be explained that the target learner's course set refers to the set of all courses a learner has taken. Undergraduate major refers to the learner's undergraduate major. Research direction refers to the learner's current or future research direction. The basic course score set refers to the learner's scores in basic courses. The professional course score set refers to the learner's scores in professional courses. The practical course score set refers to the learner's scores in practical courses. The highest basic course score and the lowest basic course score are the highest and lowest scores in the basic course score set, respectively. The highest professional course score and the lowest professional course score are the highest and lowest scores in the professional course score set, respectively. The highest practical course score and the lowest practical course score are the highest and lowest scores in the practical course score set. A strong course refers to a course in which a learner's score is higher than that of other courses in a certain category. A weak course refers to a course in which a learner's score is the lowest among all courses. Professional data refers to data related to a learner's undergraduate major and research direction. For example, learner A's professional data = {Undergraduate major: Medicine, Research direction: Cardiovascular disease research}. The obtaining of professional span value refers to the use of a certain quantitative method (such as professional similarity calculation) to measure the difference between undergraduate majors and research directions. The TF-IDF algorithm is used to extract the undergraduate major name and research major name from the undergraduate major and research direction respectively, and the pre-trained Word2Vec model is used to convert the extracted undergraduate major name and research major name into numerical undergraduate major name word vectors and research major name word vectors. The cosine similarity is calculated using the undergraduate major name word vector and the cosine similarity of the research major name word vector. The cosine similarity indicates the degree of similarity between the undergraduate major and the research direction. The greater the cosine similarity, the more similar the undergraduate major and the research direction are, and the smaller the professional span. In order to make the professional span value positively correlated with the cosine similarity, the reciprocal of the cosine similarity value is taken as the professional span value. The greater the value after taking the reciprocal, the smaller the cosine similarity, indicating that the difference between the undergraduate major and the research direction is greater. The professional span threshold refers to a pre-set value used to determine whether the professional span is less than the professional span threshold. The method of formulating a cross-disciplinary learning course set based on strong and weak courses refers to selecting courses related to weak courses based on strong and weak courses, combined with the learner's undergraduate major and research direction, to help learners make up for knowledge gaps, select advanced courses or interdisciplinary courses related to strong courses, further improve the learner's knowledge level in the strong field, and select courses that can help learners smoothly transition from undergraduate majors to graduate research directions. Therefore, it is necessary to supplement basic knowledge, bridge courses and advanced courses in the target field. The method of formulating a non-cross-disciplinary learning course set based on strong and weak courses is the same as the method of formulating a cross-disciplinary learning course set based on strong and weak courses, and will not be repeated here. A non-cross-disciplinary learning course set refers to a course plan designed for non-cross-disciplinary learners.The cross-disciplinary learning course set and the non-cross-disciplinary learning course set described in the embodiment of the present invention both include one or more learning courses. A personalized learning course refers to a personalized course plan formulated based on the learner's strengths and weaknesses and cross-disciplinary / non-cross-disciplinary learning plans. For example, if a student has good grades in basic medicine courses but poor grades in clinical practice courses, it means that the student may have strong theoretical knowledge but needs to improve practical operation skills, and needs to supplement clinical practice courses and practical operation courses. Course matching refers to calculating the degree of matching between a learner and a certain course based on the learner's personalized learning needs. The embodiment of the present invention includes the following steps for quantifying the difficulty value of a personalized learning course: obtaining a number of students who study the same personalized learning course and have studied the same personalized learning course for the same length of time, wherein the number of students is determined by an operator and the number of selected students must be representative; conducting a personalized learning course learning difficulty test on the number of students using a personalized learning course test; arranging the obtained test scores in descending order, and presenting a top A% ratio of test scores and a bottom A% ratio of test scores, wherein A% is a proposed ratio preset by the operator; wherein 100 is taken as the full score of the test score, the numerical values ​​of the test scores obtained after the elimination operation are extracted, and the numerical value 100 is taken as the maximum value of the personalized learning course difficulty value; the numerical value of the test score obtained after the elimination operation is subtracted from the numerical value 100 to obtain the personalized learning course difficulty value corresponding to each numerical value of the test score; summing up all the obtained personalized learning course difficulty values ​​to obtain a personalized learning course difficulty value set; averaging the personalized learning course difficulty value set to obtain an average value, and using the average value as the average personalized course difficulty value. Developing a cross-disciplinary learning course set based on strong and weak courses involves obtaining all knowledge points in strong courses and all knowledge points in weak courses, searching for courses that contain 60% of the knowledge points in strong courses and 80% of the knowledge points in weak courses, selecting these courses as cross-disciplinary learning courses, and aggregating the cross-disciplinary learning courses to obtain a cross-disciplinary learning course set. S5. Receive a medical course optimization instruction, and obtain an optimal recommended course sequence based on the medical course optimization instruction, the optimized learning course map, and the personalized learning course set.

[0124] Specifically, the optimal recommended course sequence includes three optimal recommended courses.

[0125] In detail, the method of obtaining the optimal recommended course sequence based on the medical course optimization instructions, the optimized learning course map, and the personalized learning course set includes:

[0126] According to the medical course optimization instructions, the recommended courses are extracted from the optimized learning course map in sequence, the course matching degree is calculated based on the personalized learning course set and the recommended courses, and the course matching degree is compared with the preset course matching degree threshold;

[0127] If the course matching degree is greater than the preset course matching degree threshold, the course to be recommended will be used as a recommended course;

[0128] If the course matching degree is less than or equal to the preset course matching degree threshold, then return to the step of sequentially extracting the courses to be recommended from the optimized learning course map until all the courses to be recommended in the optimized learning course map are extracted;

[0129] Summarize the recommended courses to obtain the recommended course group, and obtain the optimal recommended course sequence based on the recommended course group.

[0130] It should be explained that the medical course optimization instruction is an instruction for triggering the course recommendation process. The courses to be recommended refer to the learning courses extracted in sequence from the optimized learning course map. The course matching threshold refers to a pre-set value used to determine whether the courses to be recommended match the learner's personalized learning course set. Recommended courses refer to the courses to be recommended whose course matching is higher than the course matching threshold. The recommended course group refers to the set of all recommended courses. The said obtaining the optimal recommended course sequence according to the recommended course group refers to extracting the three recommended courses with the highest course matching from the recommended course group, and sorting the recommended courses to obtain the optimal recommended course sequence. The said extracting the courses to be recommended in sequence from the optimized learning course map according to the medical course optimization instruction means that when the system receives the optimization instruction, it will start an automated process to extract courses from the optimized learning course map, and screen and recommend them according to the learner's personalized needs.

[0131] Specifically, the course matching degree is calculated based on the personalized learning course set and the courses to be recommended, including:

[0132] Extracting personalized learning courses from the personalized learning course set, obtaining personalized course knowledge point groups of the personalized learning courses, summarizing the personalized course knowledge point groups, and obtaining a personalized course knowledge point group set;

[0133] Obtain the knowledge point set of the recommended course, calculate the knowledge point overlap ratio based on the knowledge point set and the personalized course knowledge point group set, perform course difficulty analysis on the recommended course, and obtain the difficulty value of the recommended course;

[0134] Performing a course difficulty analysis on each personalized learning course in the personalized learning course set to obtain a personalized learning course difficulty value set, and calculating an average personalized course difficulty value based on the personalized learning course difficulty value set;

[0135] Calculate the course difficulty difference based on the difficulty value of the recommended course and the average individual course difficulty value, where the course difficulty difference is the absolute difference between the difficulty value of the recommended course and the average individual course difficulty value;

[0136] Use the pre-built NLP model to perform vector conversion on the recommended courses and personalized learning course sets to obtain the embedding vectors of the recommended courses and the embedding vector sets of personalized courses. In the personalized course embedding vector set, the embedding vector sets of personalized courses correspond one to one with the personalized learning courses.

[0137] The average semantic distance is calculated based on the embedding vectors of the recommended courses and the embedding vectors of the personalized courses. The course synergy effect value of the recommended courses and the personalized learning courses is calculated based on the average semantic distance, the recommended courses and the personalized learning courses to obtain the course adjustment factor.

[0138] The course matching degree is calculated based on the knowledge point overlap ratio, course difficulty difference, course synergy effect value and course adjustment factor.

[0139] It should be explained that the personalized course knowledge point group for obtaining the personalized learning course refers to extracting knowledge points from the course content (such as the course outline, introduction, and teaching objectives). The knowledge points described in the embodiment of the present invention refer to the core concepts, theories, formulas, theorems, professional terms, etc. in the course content, and the knowledge points are extracted from the personalized learning course or the course to be recommended through natural language processing technology. Knowledge point overlap means that the knowledge points shared in the two courses have the same meaning. For example, the knowledge points in the personalized learning course include: {cardiovascular system, pathology, cell division}, and the knowledge points in the course to be recommended include: {cardiovascular system, pathology, genetic variation}, then the knowledge points overlap between the personalized learning course and the course to be recommended is {cardiovascular system, pathology}. The knowledge point set of the course to be recommended refers to the set consisting of all knowledge points covered by the course to be recommended. The personalized course knowledge point group refers to the set consisting of knowledge points extracted from the personalized learning course. The personalized course knowledge point group set refers to the set of all personalized course knowledge point groups. The calculation of the knowledge point overlap ratio based on the knowledge point set and the personalized course knowledge point group set refers to obtaining all personalized course knowledge points based on the personalized course knowledge point group set, obtaining all knowledge points of the course to be recommended based on the knowledge point set, obtaining an overlapping knowledge point set based on all personalized course knowledge points and all knowledge points of the course to be recommended, and dividing the overlapping knowledge point set by all knowledge points of the course to be recommended to obtain the knowledge point overlap ratio. The overlapping knowledge point set refers to the intersection of all personalized course knowledge points and all knowledge points of the course to be recommended. The course difficulty analysis of the recommended course refers to the course difficulty analysis of the recommended course using the hierarchical analysis method. The method of performing course difficulty analysis on each personalized learning course in the personalized learning course set is the same as the method of performing course difficulty analysis on the recommended course, and will not be repeated here. The difficulty value of the course to be recommended refers to the quantitative value of the course difficulty obtained after analysis. The personalized learning course difficulty value set refers to the set consisting of all personalized learning course difficulty values. The personalized learning course difficulty value refers to the quantitative value of the personalized learning course difficulty obtained after analysis.

[0140] Importantly, the average personalized course difficulty value refers to the average value of the personalized learning course difficulty value set. The NLP model refers to a pre-trained model for natural language processing, which is used to convert text into an embedding vector to facilitate the calculation of semantic similarity. For example, the NLP model is BERT, Word2Vec, etc. The embedding vector of the course to be recommended refers to the numerical vector after the content of the course to be recommended is converted by the NLP model. The personalized course embedding vector set refers to the set of numerical vectors after the content of each personalized learning course in the personalized learning course set is converted by the NLP model. The said calculation of the average semantic distance based on the embedding vector of the course to be recommended and the personalized course embedding vector set refers to calculating the cosine similarity between the embedding vector of the course to be recommended and the embedding vector of each personalized course in the personalized course embedding vector set, obtaining a cosine similarity set, calculating the average value of the cosine similarity set, and taking the average value of the cosine similarity set as the average semantic distance. The cosine similarity set refers to a set composed of all cosine similarities. The calculation formula of the course synergy effect value in the step of calculating the course synergy effect value of the course to be recommended and the personalized learning course set based on the average semantic distance, the course to be recommended and the personalized learning course set is as follows:

[0141]

[0142] Among them, T represents the course synergy effect value, exp(*) represents the exponential function, and H represents the number of individual learning course difficulty levels in the individual learning course difficulty set. represents the average semantic distance, v c represents the embedding vector of the course to be recommended, Represents the Cth set of personalized course embedding vectors o Individual course embedding vector groups, C o Represents the index of the personalized course embedding vector in the personalized course embedding vector group, and || || 2 represents the modulus length.

[0143] In detail, obtaining the course adjustment factor includes:

[0144] Obtaining a knowledge point set of an advantageous course and a knowledge point set of an inferior course, calculating the similarity of the first course based on the knowledge point set and the knowledge point set of the advantageous course, and calculating the similarity of the second course based on the knowledge point set and the knowledge point set of the inferior course;

[0145] Mapping the first course similarity using a pre-built logic function and a preset numerator adjustment factor to obtain a first mapped similarity;

[0146] The second course similarity is mapped using the logic function to obtain a second mapping similarity, and a course adjustment factor is calculated according to the first mapping similarity and the second mapping similarity, wherein the course adjustment factor is the product of the first mapping similarity and the second mapping similarity.

[0147] It should be explained that the method of obtaining the knowledge point set of the advantageous courses and the knowledge point set of the disadvantageous courses is the same as the method of obtaining the knowledge point set of the courses to be recommended and the personalized course knowledge point group of the personalized learning courses, and will not be repeated here. The knowledge point set of the advantageous courses refers to a set of knowledge points extracted from the advantageous courses. The knowledge point set of the disadvantageous courses refers to a set of knowledge points extracted from the disadvantageous courses. The calculation of the first course similarity based on the knowledge point set and the knowledge point set of the advantageous courses refers to calculating the first course similarity using the Jaccard similarity calculation formula. The calculation of the second course similarity based on the knowledge point set and the knowledge point set of the disadvantageous courses refers to calculating the second course similarity using the Jaccard similarity calculation formula. The first course similarity refers to the similarity between the course to be recommended and the learner's advantageous courses. The second course similarity refers to the similarity between the course to be recommended and the learner's disadvantageous courses.

[0148] It should be explained that the logical function refers to a function that maps input values ​​to a specific output range, which is used to adjust the similarity value. The similarity value is mapped to a specific range (such as 0 to 1) to better reflect its importance. The first mapping similarity refers to the similarity after the first course similarity is mapped by the logical function and the numerator adjustment factor. The second mapping similarity refers to the similarity after the second course similarity is mapped by the logical function. The numerator adjustment factor refers to a pre-set value. For example, the numerator adjustment factor is 2. The numerator adjustment factor is to expand the adjustment range of the advantage course from [0, 1] to [0, 2], so as to achieve a reasonable enhancement of the matching degree when there is a high degree of similarity, rather than just maintaining neutrality. The course adjustment factor is used to adjust the course matching degree to ensure that the recommended courses not only match the learner's advantage courses, but also help improve the learning effect of the disadvantaged courses.

[0149] In detail, the calculation formula of the course matching degree is as follows:

[0150]

[0151] Among them, M represents the course matching degree, Indicates the Cth r The difficulty value of the personalized learning course, H represents the number of difficulty values ​​of the personalized learning course in the difficulty value set, d c represents the difficulty value of the recommended course, Z represents the knowledge point overlap ratio, T represents the course synergy effect value, and Q represents the course adjustment factor. Indicates the course difficulty difference, C r Represents the index of the difficulty value of the personalized learning course in the personalized learning course difficulty value set.

[0152] It should be explained that the course synergy value refers to the synergy between the recommended course and the personalized learning course, that is, their complementarity in the learning path. Course matching refers to the degree of matching between the recommended course and the learner, calculated after comprehensively considering the knowledge point overlap ratio, course difficulty difference, course synergy value and course adjustment factor. If the course matching degree is too low, it means that the course is not suitable for the learner and the span is too large, which is not suitable for the learner to learn. Therefore, a step-by-step learning course needs to be set up. Learners first learn simple courses, and then it will be easier to learn more difficult courses. The course difficulty value is calculated by the scores obtained by different learners in the course examination process to evaluate the difficulty of different learners when learning the course, that is, it can represent the universal situation of the course and the learner. Different learners have different understandings or perceptions of different courses. Therefore, when recommending courses to learners, we must not only consider the universal difficulty of the course, but also the suitability of the course for the learner, that is, we must also consider the knowledge point overlap ratio, course difficulty difference, course synergy effect value and course adjustment factor. By considering these factors, we can jointly calculate the matching situation between the course and different learners, which reflects the adaptability of the course to the learner under objective conditions.

[0153] S6. Obtain the target learner's ideal learning course and determine whether the optimal recommended course sequence contains the ideal learning course.

[0154] It should be explained that the ideal study course refers to the course that the target learners (medical postgraduates) expect to study.

[0155] S7. If the optimal recommended course sequence does not contain an ideal learning course, the ideal learning course is imported into the optimized learning course map to obtain an updated learning course map. The updated learning course map is used as the optimized learning course map, and the process returns to the step of obtaining the optimal recommended course sequence based on the medical course optimization instruction, the optimized learning course map, and the personalized learning course set.

[0156] It should be explained that updating the learning course map refers to importing the ideal learning course into the optimized learning course map when the optimal recommended course sequence does not exist. The updated learning course map will replace the original optimized learning course map and be used for the next round of course optimization to ensure that the course recommendations are more closely aligned with the needs of the target learners.

[0157] S8. Obtain the number of executions of the optimal recommended course sequence obtained according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set, compare the number of executions with a preset execution number threshold, and if the number of executions is greater than the preset execution number threshold, select any optimal recommended course in the optimal recommended course sequence as an ideal learning course.

[0158] It should be explained that the execution count is used to determine whether the system needs to stop the optimization process to avoid an infinite loop. The execution count threshold is a pre-set value used to limit the maximum number of times the system can execute optimization operations.

[0159] S9. Summarize the ideal learning courses to obtain the ideal learning course set, and complete the semantic reasoning-based graduate medical course optimization based on the ideal learning course set.

[0160] It should be explained that the ideal learning course set refers to the set of all ideal learning courses for the target learners.

[0161] The present invention solves the problems described in the background technology. The present invention identifies a medical graduate student database and obtains a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes multiple medical learning courses. By identifying the medical graduate student database, the present invention can integrate scattered student learning information, course information, etc. to form a unified data source, construct a learning course map based on the medical learning course set, optimize the learning course map, and obtain an optimized learning course map. The learning course map of the present invention presents the semantic relationship between medical learning courses in a graphical manner, making the complex relationship between courses intuitive and easy to understand. By optimizing the learning course map, the potential semantic connection between courses can be excavated. Discovering some previously unnoticed course combinations or knowledge expansion paths provides new ideas for course optimization and adjustment, and confirming multiple target learner course sets, wherein the target learner course set includes multiple target learner courses, and the target learner course set corresponds to the learner one-to-one. In the present invention, each target learner course set corresponds to the learner one-to-one, which can accurately reflect the courses that each learner has learned or plans to learn. This provides a basis for subsequently formulating personalized learning course sets for each learner, extracting target learner course sets from multiple target learner course sets in sequence, and formulating personalized learning course sets based on the target learner course sets. The present invention formulates personalized learning course sets based on the target learner course sets of each learner, which can Taking full account of the learner's existing knowledge and learning goals, tailor-made learning courses for them will help improve the learner's learning interest and learning effect, make the course more in line with the learner's actual needs, receive medical course optimization instructions, and obtain the optimal recommended course sequence according to the medical course optimization instructions, the optimized learning course map and the personalized learning course set. Among them, the optimal recommended course sequence includes three optimal recommended courses. The present invention obtains the optimal recommended course sequence by combining the optimized learning course map and the personalized learning course set, and can provide learners with course recommendations that best meet their needs and the logic of the course system, improve the accuracy and effectiveness of course recommendations, obtain the ideal learning course for the target learner, and judge whether the optimal recommended course sequence has an ideal Learning courses, the present invention can ensure that the recommended courses meet the learner's personalized expectations by judging whether there is an ideal learning course for the target learner in the optimal recommended course sequence. If the ideal learning course does not exist in the optimal recommended course sequence, the ideal learning course is imported into the optimized learning course map to obtain an updated learning course map, and the updated learning course map is used as the optimized learning course map, and the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set is returned. By continuously updating and optimizing the course map, the present invention can improve the accuracy and adaptability of course recommendations, ensure that the recommended courses are more in line with the learner's expectations, continuously optimize the results of course recommendations, and improve learner satisfaction.Obtain the execution times of the optimal recommended course sequence obtained according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set, compare the execution times with the preset execution times threshold, the present invention sets the execution times threshold to avoid falling into an infinite loop recommendation process when the ideal learning course cannot be found, and improves the efficiency and stability of the algorithm. If the execution times are greater than the preset execution times threshold, any optimal recommended course in the optimal recommended course sequence is used as the ideal learning course, and the ideal learning courses are summarized to obtain the ideal learning course set. The postgraduate medical course optimization based on semantic reasoning is completed based on the ideal learning course set. The present invention completes course optimization based on the ideal learning course set, which can improve the quality and applicability of medical postgraduate courses, make the courses more in line with students' learning needs and professional development requirements, and help cultivate more outstanding medical professionals. Therefore, the present invention can improve the personalization and accuracy of course recommendations, promote the development of medical education and talent training.

[0162] like Figure 2 FIG. 1 is a functional module diagram of a graduate medical course optimization system based on semantic reasoning provided by an embodiment of the present invention.

[0163] The postgraduate medical course optimization system 100 based on semantic reasoning of the present invention can be installed in an electronic device. According to the functions to be implemented, the postgraduate medical course optimization system 100 based on semantic reasoning can include a course map construction module 101, a personalized learning course formulation module 102, an optimal recommended course acquisition module 103 and a course optimization completion module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, which are stored in the memory of the electronic device;

[0164] The course map construction module 101 is configured to identify a medical graduate student database, obtain a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes a plurality of medical learning courses, construct a learning course map based on the medical learning course set, and optimize the learning course map to obtain an optimized learning course map;

[0165] The personalized learning course formulation module 102 is used to identify multiple target learner course sets, wherein the target learner course set includes multiple target learner courses, and the target learner course set corresponds to the learner one by one, sequentially extract the target learner course sets from the multiple target learner course sets, and formulate the personalized learning course set based on the target learner course sets;

[0166] The optimal recommended course acquisition module 103 is configured to receive a medical course optimization instruction, acquire an optimal recommended course sequence based on the medical course optimization instruction, the optimized learning course map, and the personalized learning course set, wherein the optimal recommended course sequence includes three optimal recommended courses, acquire the target learner's ideal learning course, and determine whether there is an ideal learning course in the optimal recommended course sequence;

[0167] The course optimization completion module 104 is used to import the ideal learning course into the optimized learning course map if there is no ideal learning course in the optimal recommended course sequence, obtain an updated learning course map, use the updated learning course map as the optimized learning course map, return to the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set, obtain the number of executions of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set, compare the number of executions with a preset execution number threshold, and if the number of executions is greater than the preset execution number threshold, use any optimal recommended course in the optimal recommended course sequence as the ideal learning course, summarize the ideal learning courses, obtain the ideal learning course set, and complete the postgraduate medical course optimization based on semantic reasoning based on the ideal learning course set.

[0168] In detail, the modules in the postgraduate medical course optimization system 100 based on semantic reasoning in the embodiment of the present invention are used in the same manner as above. Figure 1 The technical means are the same as the postgraduate medical course optimization method based on semantic reasoning described in, and can produce the same technical effects, so I will not go into details here.

[0169] like Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing a method for optimizing a postgraduate medical course based on semantic reasoning, provided by an embodiment of the present invention.

[0170] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a program for optimizing a postgraduate medical curriculum based on semantic reasoning.

[0171] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Furthermore, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed on the electronic device 1, such as the code of the graduate medical course optimization method program based on semantic reasoning, but can also be used to temporarily store data that has been output or is to be output.

[0172] In some embodiments, the processor 10 may be composed of an integrated circuit, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and circuits. It executes or runs programs or modules stored in the memory 11 (such as a program for optimizing graduate medical courses based on semantic reasoning, etc.), and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0173] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0174] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0175] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering the various components. Preferably, the power source may be logically connected to the at least one processor 10 via a power management device, thereby implementing functions such as charging management, discharging management, and power consumption management through the power management device. The power source may further include any components such as one or more DC or AC power sources, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0176] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0177] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0178] The program of the postgraduate medical curriculum optimization method based on semantic reasoning stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve the following:

[0179] identifying a medical graduate student database, and obtaining a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes a plurality of medical learning courses;

[0180] Constructing a learning course map based on the medical learning course set, optimizing the learning course map, and obtaining an optimized learning course map;

[0181] Identify a plurality of target learner course sets, wherein the target learner course set includes a plurality of target learner courses, and the target learner course sets correspond to learners one by one;

[0182] Extracting target learner course sets from multiple target learner course sets in sequence, and formulating personalized learning course sets based on the target learner course sets;

[0183] receiving a medical course optimization instruction, and obtaining an optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set, wherein the optimal recommended course sequence includes three optimal recommended courses;

[0184] Obtain the target learner's ideal learning course and determine whether the optimal recommended course sequence contains the ideal learning course;

[0185] If the optimal recommended course sequence does not contain an ideal learning course, the ideal learning course is imported into the optimized learning course map to obtain an updated learning course map, and the updated learning course map is used as the optimized learning course map, and the process returns to the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set;

[0186] Obtaining the number of executions of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set, and comparing the number of executions with a preset execution number threshold;

[0187] If the execution times are greater than a preset execution times threshold, any optimal recommended course in the optimal recommended course sequence is used as an ideal learning course;

[0188] The ideal learning courses are summarized to obtain the ideal learning course set, and the semantic reasoning-based graduate medical course optimization is completed based on the ideal learning course set.

[0189] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 4 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0190] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0191] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0192] identifying a medical graduate student database, and obtaining a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes a plurality of medical learning courses;

[0193] Constructing a learning course map based on the medical learning course set, optimizing the learning course map, and obtaining an optimized learning course map;

[0194] Identify a plurality of target learner course sets, wherein the target learner course set includes a plurality of target learner courses, and the target learner course sets correspond to learners one by one;

[0195] Extracting target learner course sets from multiple target learner course sets in sequence, and formulating personalized learning course sets based on the target learner course sets;

[0196] receiving a medical course optimization instruction, and obtaining an optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set, wherein the optimal recommended course sequence includes three optimal recommended courses;

[0197] Obtain the target learner's ideal learning course and determine whether the optimal recommended course sequence contains the ideal learning course;

[0198] If the optimal recommended course sequence does not contain an ideal learning course, the ideal learning course is imported into the optimized learning course map to obtain an updated learning course map, and the updated learning course map is used as the optimized learning course map, and the process returns to the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set;

[0199] Obtaining the number of executions of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set, and comparing the number of executions with a preset execution number threshold;

[0200] If the execution times are greater than a preset execution times threshold, any optimal recommended course in the optimal recommended course sequence is used as an ideal learning course;

[0201] The ideal learning courses are summarized to obtain the ideal learning course set, and the semantic reasoning-based graduate medical course optimization is completed based on the ideal learning course set.

[0202] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary, and actual implementations may have other division methods.

[0203] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0204] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0205] 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 present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0206] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for optimizing graduate medical courses based on semantic reasoning, characterized in that: The method comprises: identifying a medical graduate student database, and obtaining a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes a plurality of medical learning courses; Constructing a learning course map based on the medical learning course set, optimizing the learning course map, and obtaining an optimized learning course map; Identify a plurality of target learner course sets, wherein the target learner course set includes a plurality of target learner courses, and the target learner course sets correspond to learners one by one; Extracting target learner course sets from multiple target learner course sets in sequence, and formulating personalized learning course sets based on the target learner course sets; receiving a medical course optimization instruction, and obtaining an optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set, wherein the optimal recommended course sequence includes three optimal recommended courses; Obtain the target learner's ideal learning course and determine whether the optimal recommended course sequence contains the ideal learning course; If the optimal recommended course sequence does not contain an ideal learning course, the ideal learning course is imported into the optimized learning course map to obtain an updated learning course map, and the updated learning course map is used as the optimized learning course map, and the process returns to the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set; Obtaining the number of executions of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map, and the personalized learning course set, and comparing the number of executions with a preset execution number threshold; If the execution times are greater than a preset execution times threshold, any optimal recommended course in the optimal recommended course sequence is used as an ideal learning course; The ideal learning courses are summarized to obtain the ideal learning course set, and the semantic reasoning-based graduate medical course optimization is completed based on the ideal learning course set.

2. The method for optimizing graduate medical courses based on semantic reasoning according to claim 1, characterized in that: The construction of a learning course map based on the medical learning course set includes: Extract one medical learning course from the medical learning course set in turn, and perform the following operations on each extracted medical learning course: Eliminate the extracted medical learning course from the medical learning course set to obtain a streamlined learning course set; Extracting one streamlined learning course from the streamlined learning course set in sequence, obtaining a list of medical course learners and a list of streamlined course learners based on the extracted medical learning course and the extracted streamlined learning course, and confirming a common learner list set and a list set of all learners based on the list of medical course learners and the list of streamlined course learners; Calculate the course similarity based on the common learner list set and the all learner list set, where the course similarity is the ratio of the number of common learner lists in the common learner list set to the number of all learners in the all learner list set; Collecting learning course score sets and streamlined learning course score sets corresponding to the medical learning course and streamlined learning course respectively, and calculating the average learning course score and the average streamlined learning course score based on the learning course score sets and the streamlined learning course score sets; Calculate the modified cosine similarity based on the average learning course rating, the average condensed learning course rating, the learning course rating set, and the condensed learning course rating set; Obtain comprehensive similarity based on course similarity and modified cosine similarity, summarize the comprehensive similarities to obtain a comprehensive similarity set, and determine whether there is a comprehensive similarity greater than a preset comprehensive similarity threshold in the comprehensive similarity set; If there is no comprehensive similarity greater than the preset comprehensive similarity threshold in the comprehensive similarity set, returning to the step of sequentially extracting medical learning courses from the medical learning course set until the medical learning course set is an empty set; If there is a comprehensive similarity greater than a preset comprehensive similarity threshold in the comprehensive similarity set, the medical learning courses and streamlined learning courses corresponding to the comprehensive similarity are integrated to obtain a related learning course group; The associated learning course groups are aggregated to obtain an associated learning course group set, and a learning course map is constructed according to the associated learning course group set, wherein the learning course map includes: multiple learning courses.

3. The method for optimizing graduate medical courses based on semantic reasoning according to claim 2, characterized in that: The calculation formula of the modified cosine similarity is as follows: Among them, X represents the modified cosine similarity, E a,i represents the i-th learning course rating in the learning course rating set, E b,j represents the jth streamlined learning course rating in the streamlined learning course rating set, represents the average learning course rating, represents the average streamlined learning course rating, n represents the number of learning course ratings in the learning course rating set, m represents the number of streamlined learning course ratings in the streamlined learning course rating set, i represents the index of the learning course rating, and j represents the index of the streamlined learning course rating.

4. The method for optimizing graduate medical courses based on semantic reasoning according to claim 3, wherein: The optimizing the learning course map to obtain the optimized learning course map includes: Perform the following operations for each learning course in the learning course map: Obtain course books based on the course, obtain the name of the research major based on the course books, retrieve a set of school names based on the name of the research major, and query a set of similar study textbooks with the same name as the research major in the school name set; If the similar learning textbook set is an empty set, the name of the research major is expanded to obtain an updated major name, the updated major name is used as the research major name, and the process returns to the step of retrieving the set of school names based on the research major name until the similar learning textbook set is not an empty set; If the similar learning textbook set is not an empty set, obtaining a similar learning course set based on the similar learning textbook set, and combining each similar learning course in the similar learning course set with the learning course to obtain an associated similar course group; The related similar course groups are aggregated to obtain a related similar course group set, and an optimized learning course map is constructed based on the related similar course group set and the learning course map.

5. The method for optimizing graduate medical courses based on semantic reasoning according to claim 4, wherein: The method of formulating a personalized learning course set based on the target learner course set includes: Obtain undergraduate majors based on the target learner course set, and obtain course grade group sets based on the target learner course set, wherein the course grade groups in the course grade group set correspond one-to-one to the learner courses in the target learner course set; Classify the course score groups to obtain a basic course score set, a professional course score set, and a practical course score set, and calculate the highest basic course score and the lowest basic course score based on the basic course score set; Calculate the highest and lowest professional course scores based on the professional course score set, and calculate the highest and lowest practical course scores based on the practical course score set; Obtain advantaged courses and disadvantaged courses based on the highest basic course score, the lowest basic course score, the highest professional course score, the lowest professional course score, the highest practical course score, and the lowest practical course score; Obtain professional data based on undergraduate majors and research directions, conduct cross-disciplinary judgment on the professional data, and obtain judgment data, wherein the judgment data is cross-disciplinary data or non-cross-disciplinary data; If the data is determined to be cross-disciplinary data, the professional span value is obtained to determine whether the professional span value is greater than a preset professional span threshold. If the professional span value is greater than the preset professional span threshold, a cross-disciplinary learning course set is formulated based on the advantageous courses and the disadvantageous courses. If the data is judged to be non-interdisciplinary data, a non-interdisciplinary learning course set will be developed based on the strong and weak courses; A cross-disciplinary learning course set or a non-cross-disciplinary learning course set is regarded as a personalized learning course set, wherein the personalized learning course set includes one or more personalized learning courses.

6. The method for optimizing graduate medical courses based on semantic reasoning according to claim 5, characterized in that: The method of obtaining the optimal recommended course sequence based on the medical course optimization instructions, the optimized learning course map, and the personalized learning course set includes: According to the medical course optimization instructions, the recommended courses are extracted from the optimized learning course map in sequence, the course matching degree is calculated based on the personalized learning course set and the recommended courses, and the course matching degree is compared with the preset course matching degree threshold; If the course matching degree is greater than the preset course matching degree threshold, the course to be recommended will be used as a recommended course; If the course matching degree is less than or equal to the preset course matching degree threshold, then return to the step of sequentially extracting the courses to be recommended from the optimized learning course map until all the courses to be recommended in the optimized learning course map are extracted; Summarize the recommended courses to obtain the recommended course group, and obtain the optimal recommended course sequence based on the recommended course group.

7. The method for optimizing graduate medical courses based on semantic reasoning according to claim 6, wherein: The course matching degree is calculated based on the personalized learning course set and the recommended courses, including: Extracting personalized learning courses from the personalized learning course set, obtaining personalized course knowledge point groups of the personalized learning courses, summarizing the personalized course knowledge point groups, and obtaining a personalized course knowledge point group set; Obtain the knowledge point set of the recommended course, calculate the knowledge point overlap ratio based on the knowledge point set and the personalized course knowledge point group set, perform course difficulty analysis on the recommended course, and obtain the difficulty value of the recommended course; Performing a course difficulty analysis on each personalized learning course in the personalized learning course set to obtain a personalized learning course difficulty value set, and calculating an average personalized course difficulty value based on the personalized learning course difficulty value set; Calculate the course difficulty difference based on the difficulty value of the recommended course and the average individual course difficulty value, where the course difficulty difference is the absolute difference between the difficulty value of the recommended course and the average individual course difficulty value; Use the pre-built NLP model to perform vector conversion on the recommended courses and personalized learning course sets to obtain the embedding vectors of the recommended courses and the embedding vector sets of personalized courses. In the personalized course embedding vector set, the embedding vector sets of personalized courses correspond one to one with the personalized learning courses. The average semantic distance is calculated based on the embedding vectors of the recommended courses and the embedding vectors of the personalized courses. The course synergy effect value of the recommended courses and the personalized learning courses is calculated based on the average semantic distance, the recommended courses and the personalized learning courses to obtain the course adjustment factor. The course matching degree is calculated based on the knowledge point overlap ratio, course difficulty difference, course synergy effect value and course adjustment factor.

8. The method for optimizing graduate medical courses based on semantic reasoning according to claim 7, wherein: The obtaining of the course adjustment factor includes: Obtaining a knowledge point set of an advantageous course and a knowledge point set of an inferior course, calculating the similarity of the first course based on the knowledge point set and the knowledge point set of the advantageous course, and calculating the similarity of the second course based on the knowledge point set and the knowledge point set of the inferior course; Mapping the first course similarity using a pre-built logic function and a preset numerator adjustment factor to obtain a first mapped similarity; The second course similarity is mapped using the logic function to obtain a second mapping similarity, and a course adjustment factor is calculated according to the first mapping similarity and the second mapping similarity, wherein the course adjustment factor is the product of the first mapping similarity and the second mapping similarity.

9. The method for optimizing graduate medical courses based on semantic reasoning according to claim 8, wherein: The calculation formula for the course matching degree is as follows: Among them, M represents the course matching degree, Indicates the Cth r The difficulty value of the personalized learning course, H represents the number of difficulty values ​​of the personalized learning course in the difficulty value set, d c represents the difficulty value of the recommended course, Z represents the knowledge point overlap ratio, T represents the course synergy effect value, and Q represents the course adjustment factor. Indicates the course difficulty difference, C r Represents the index of the difficulty value of the personalized learning course in the personalized learning course difficulty value set.

10. A postgraduate medical course optimization system based on semantic reasoning, characterized by: The system comprises: a course map construction module, configured to identify a medical graduate student database, obtain a medical learning course set based on the medical graduate student database, wherein the medical learning course set includes multiple medical learning courses, construct a learning course map based on the medical learning course set, and optimize the learning course map to obtain an optimized learning course map; A personalized learning course formulation module is used to identify multiple target learner course sets, wherein the target learner course set includes multiple target learner courses, and the target learner course set corresponds to the learner one by one, sequentially extract the target learner course sets from the multiple target learner course sets, and formulate a personalized learning course set based on the target learner course sets; The optimal recommended course acquisition module is used to receive medical course optimization instructions, obtain the optimal recommended course sequence based on the medical course optimization instructions, the optimized learning course map, and the personalized learning course set, where the optimal recommended course sequence includes three optimal recommended courses, obtain the ideal learning course for the target learner, and determine whether there is an ideal learning course in the optimal recommended course sequence; The course optimization completion module is used to import the ideal learning course into the optimized learning course map if there is no ideal learning course in the optimal recommended course sequence, obtain an updated learning course map, use the updated learning course map as the optimized learning course map, return to the step of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set, obtain the number of executions of obtaining the optimal recommended course sequence according to the medical course optimization instruction, the optimized learning course map and the personalized learning course set, compare the number of executions with a preset execution number threshold, and if the number of executions is greater than the preset execution number threshold, use any optimal recommended course in the optimal recommended course sequence as the ideal learning course, summarize the ideal learning courses, obtain the ideal learning course set, and complete the postgraduate medical course optimization based on semantic reasoning based on the ideal learning course set.

Images