Artificial intelligence-based adaptive learning path training management system and method thereof

Abstract

The invention discloses an adaptive learning path training management system and method based on artificial intelligence, and belongs to the technical field of artificial intelligence, and the method comprises the following steps: obtaining the course information of each course from a database, and analyzing the key features of each course; dividing the to-be-managed objects into different object sets; screening the learning courses of the to-be-managed objects to form associated courses of skill levels, and analyzing associated features of the skill levels; marking an adjustment object, recording a target skill level of the adjustment object, analyzing already possessed features and missing features of the adjustment object, and screening out a training course set in combination with key features of each course in a database; analyzing an optimal learning path of the adjustment object according to the training course set of the adjustment object; according to the invention, accurate matching of courses and skill levels is realized, the problem that a training path is not clear in the prior art is overcome, and the management efficiency of resource management and the adaptability of a training system are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence, and specifically relates to a training management system and method for an adaptive learning path based on artificial intelligence. Background Art

[0002] With the development of today's society, the improvement of the technological level, and the great changes in the development of information technology, these changes have had a huge impact on people's lives and social production, especially in industries such as the commercial field, the medical field, the manufacturing field, and the financial field. At the same time, it has also had a huge impact on the storage of resource data. Managing resource data by artificial intelligence can better understand the management objects, discover talents, and meet the needs of the objects, thereby building a more efficient resource management system for enterprises; However, the existing management systems only store and retrieve the data of resources. However, when personnel want to improve their skill levels, the existing management systems cannot form a clear training path to conduct planned learning and training for the improving personnel, so that the improving personnel can quickly master the knowledge required for the target skill level, reducing the efficiency of resource management; Therefore, there is an urgent need for a training management system for an adaptive learning path based on artificial intelligence to solve the above problems. Summary of the Invention

[0003] The purpose of the present invention is to provide a training management system for an adaptive learning path based on artificial intelligence to solve the problems raised in the above background art.

[0004] To solve the above technical problems, the present invention provides the following technical solutions: A training management method for an adaptive learning path based on artificial intelligence, the method includes the following steps: S1. Obtain the course information of each course from the database, analyze the key features of each course and store them in the database; obtain the skill levels of the objects to be managed from the database, and divide the objects to be managed into different object sets; S2. Obtain the learning records of each object to be managed in the object set, screen the learning courses of each object to be managed, and form associated courses of skill levels; analyze the associated features of skill levels according to the key features corresponding to the associated courses of skill levels; S3. Mark the adjustment objects, record the target skill levels of the adjustment objects; analyze the existing features of the adjustment objects according to the learning records of the adjustment objects, and analyze the missing features of the adjustment objects according to the target skill levels of the adjustment objects. Combine the key features of each course in the database to screen out a set of training courses; S4. Based on the training course set of the adjustment object, combined with all learning records in the database, analyze the optimal learning path of the adjustment object, and form a recommended course schedule to be pushed to the adjustment object.

[0005] According to the above technical solution, the step S1 includes the following: S1-1. The course information includes a course introduction and course content. Using natural language processing technology, extract keywords from the course information of each course, and use the keywords corresponding to each course as the key features of the corresponding course; extract the key features of all courses in the database and store them in the database. S1-2. The skill levels include junior, intermediate, and advanced; the object sets include a junior object set, an intermediate object set, and an advanced object set. According to the skill level of the object to be managed, divide the objects to be managed with a junior skill level into the junior object set; divide the objects to be managed with an intermediate skill level into the intermediate object set; divide the objects to be managed with a senior skill level into the senior object set. Extract course keywords through natural language processing technology to ensure the accuracy of course feature extraction and improve the accuracy of subsequent matching; classify the objects to be managed by skill level to ensure that personnel with different skill levels can form a reasonable learning set and provide basic data for subsequent learning path planning.

[0006] According to the above technical solution, the step S2 includes the following: S2-1. Each time a learning activity is carried out by an object to be managed, a learning record is generated; the learning record includes the course, the course completion rate, and the test score. S2-2. Extract all learning records of the objects to be managed in a certain object set, set a first threshold and a second threshold, and filter out the learning records with a course completion rate greater than or equal to the first threshold and a test score greater than or equal to the second threshold. Use the courses corresponding to all the filtered learning records as the associated courses of the corresponding skill level of this object set; according to each object set, obtain the associated courses of each skill level. S2-3. According to the associated courses of a certain skill level, count the key features corresponding to the associated courses of this skill level, count the number of occurrences of each key feature, and sort the key features from largest to smallest according to the number of occurrences of each key feature; use the sorted key features as the associated features of this skill level and record the serial numbers of each associated feature. By filtering learning records, ensure that the courses included in the analysis have been effectively learned, and ensure the reliability of the data; by sorting the key features, clarify the core skill requirements of different skill levels and provide data support for learning path recommendation.

[0007] According to the above technical solution, step S3 includes the following: S3-1. When a request for skill level adjustment is sent by a to-be-managed object, mark the to-be-managed object as an adjustment object; collect the target skill level of the adjustment object and store it in the database, and extract all learning records of the adjustment object from the database; S3-2. According to all the learning records of the adjustment object, screen out the learning records with a course completion rate greater than or equal to the first threshold and a test score greater than or equal to the second threshold; extract the courses corresponding to all the screened learning records and mark them as the completed courses of the adjustment object; combine the key features corresponding to each completed course and count all the key features as the features already possessed by the adjustment object; S3-3. According to the target skill level of the adjustment object, extract the associated features corresponding to the target skill level from the database, and compare them with the features already possessed by the adjustment object to screen out the associated features that are not included in the features already possessed by the adjustment object among the associated features corresponding to the target skill level; Reorder the screened associated features from front to back according to the serial numbers of each associated feature, and take the reordered associated features as the missing features of the adjustment object and record the serial numbers of the missing features; S3-4. Screen from all the courses in the database. If the key features of a certain course contain any of the missing features of the adjustment object, assign the course to the training course set; After identifying the adjustment object, ensure that the recommendation of the learning path is targeted and personalized; by comparing the features already possessed by the adjustment object and the target skill level features, accurately locate the skill gaps of the personnel and optimize the learning content; the screened training courses accurately match the missing features, ensuring the pertinence of the training and improving the learning efficiency.

[0008] According to the above technical solution, step S4 includes the following: S4-1. Extract the courses corresponding to all the learning records from the database and count the number of times each course is learned; according to the serial numbers of the missing features, sequentially screen out the courses in the training course set that correspond to each missing feature and have the most learning times; When the courses with the most learning times corresponding to different missing features are the same course, delete the missing feature with the later serial number and its serial number; S4-2. Sort the screened courses from first to last according to the serial numbers corresponding to the screened missing features, and take the sorted courses as the best learning path and form a recommended course schedule to push to the adjustment object; By screening high-frequency learning courses, ensure that the recommended courses have high practicality and recognition; by optimizing the sorting, make the learning path more reasonable and improve the learning efficiency of the objects to be adjusted; push personalized course schedules to simplify the learning process of personnel and enhance the training effect.

[0009] A training management system for an adaptive learning path based on artificial intelligence, the system includes a course analysis module, a course association module, an adjustment module and a path optimization module; The course analysis module is used to extract course keywords through natural language processing, obtain the key features of the course and store them in the database, and classify them according to skill levels to provide basic data for learning path planning; the course association module is used to screen courses with learning completion and test scores meeting the standards according to the learning records of the objects to be managed, extract the associated features of each skill level by statistically analyzing the key features of the courses, and establish the association relationship between the skill levels and the courses; the adjustment module is used to identify the objects to be adjusted in skill levels, analyze their learning records, extract the mastered key features, compare them with the associated features of the target skill levels, screen out the missing features, and match the training courses that meet the requirements to generate a set of training courses; the path optimization module is used to count the number of times all courses are learned, screen the best courses based on the missing features, sort them to form a personalized learning path, and push it to the objects to be adjusted.

[0010] According to the above technical solution, the course analysis module includes a course information unit and an object classification unit; The course information unit is used to extract the course introduction and course content from the database, and use natural language processing technology to extract keywords to form the key features of the course, and store them in the database; the object classification unit is used to divide the object set according to skill levels and provide customized training plans for the objects to be managed at different skill levels.

[0011] According to the above technical solution, the course association module includes a record screening unit and a feature analysis unit; The record screening unit is used to extract all the learning records of the objects to be managed, and screen out the learning records that meet the requirements based on the thresholds of course completion and test scores to determine the associated courses of each skill level; the feature analysis unit is used to count the number of times the key features appear in the associated courses of each skill level, sort the key features, extract the required features, and obtain the associated features of the skill levels and the courses.

[0012] According to the above technical solution, the adjustment module includes an object identification unit and a difference analysis unit; The object recognition unit is used to mark the person as an adjustment object when the object to be managed submits a request for skill level adjustment according to its own needs, record its target skill level, and extract all its learning records to prepare for subsequent learning path recommendation; the difference analysis unit is used to compare the key features already possessed by the adjustment object with the associated features of the target skill level, screen out the missing features, and screen and match the training courses from the database based on the missing features.

[0013] According to the above technical solution, the path optimization module includes a course screening unit and a path generation unit; The course screening unit is used to count the number of times all courses have been learned, and screen the training courses that meet the requirements based on the priority of the missing features; the path generation unit is used to optimize the sorting according to the screened training courses, form the best learning path, and push it to the adjustment object.

[0014] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The present invention extracts the key features of the courses through natural language processing technology, and performs intelligent classification in combination with the skill levels of the objects to be managed, realizing the precise matching of courses and skill levels, and improving the scientificity and accuracy of learning path planning; at the same time, the present invention constructs an association model between skill levels and courses based on the historical learning records of the objects to be managed, and uses key feature statistical analysis to dynamically optimize the skill level training system, enhancing the pertinence and effectiveness of training; secondly, the present invention identifies the gap between the features already possessed by the adjustment object and the target skill level requirements through intelligent difference analysis, automatically screens and supplements training courses, forms a personalized learning path, enables the adjustment object to quickly learn and master the new skill level, and shortens the learning cycle; in addition, the present invention combines historical learning data to optimize the sorting of training courses, further improving the training quality, overcoming the problem of unclear training paths in the prior art, and improving the management efficiency of resource management and the adaptability of the training system. Description of the Drawings

[0015] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings: Figure 1 It is a schematic flowchart of the training management method for the adaptive learning path based on artificial intelligence of the present invention; Figure 2 It is a schematic structural diagram of the training management system for the adaptive learning path based on artificial intelligence of the present invention. Detailed Embodiments

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0017] Please refer to Figure 1 , the present invention provides a technical solution: A training management method for an adaptive learning path based on artificial intelligence, the method comprising the following steps: S1. Obtain the course information of each course from the database, analyze the key features of each course and store them in the database; obtain the skill levels of the objects to be managed from the database, and divide the objects to be managed into different object sets; According to the above technical solution, the step S1 includes the following: S1-1. The course information includes a course introduction and course content. Using natural language processing technology, extract keywords from the course information of each course, and use the keywords corresponding to each course as the key features of the corresponding course; extract the key features of all courses in the database and store them in the database; S1-2. The skill levels include primary, intermediate, and advanced; the object sets include a primary object set, an intermediate object set, and an advanced object set; According to the skill levels of the objects to be managed, divide the objects to be managed with a primary skill level into the primary object set; divide the objects to be managed with an intermediate skill level into the intermediate object set; divide the objects to be managed with an advanced skill level into the advanced object set; Extract course keywords through natural language processing technology to ensure the accuracy of course feature extraction and improve the accuracy of subsequent matching; classify the objects to be managed by skill level to ensure that personnel with different skill levels can form a reasonable learning set and provide basic data for subsequent learning path planning.

[0018] S2. Obtain the learning records of each object to be managed in the object set, screen the learning courses of each object to be managed, and form associated courses of skill levels; analyze the associated features of skill levels according to the key features corresponding to the associated courses of skill levels; According to the above technical solution, the step S2 includes the following: S2-1. Each time an object to be managed conducts a learning activity, a learning record is generated; the learning record includes a course, a course completion degree, and a test score; S2-2. Extract all the learning records of each object to be managed in a certain object set, set a first threshold and a second threshold, and filter out the learning records whose course completion degree is greater than or equal to the first threshold and whose test scores are greater than or equal to the second threshold; Take the courses corresponding to all the filtered learning records as the associated courses of the corresponding skill level of this object set; Obtain the associated courses of each skill level according to each object set; S2-3. According to the associated courses of a certain skill level, count the key features corresponding to the associated courses of this skill level, count the number of occurrences of each key feature, and sort the key features from largest to smallest according to the number of occurrences of each key feature; Take the sorted key features as the associated features of this skill level and record the serial numbers of each associated feature; By filtering the learning records, ensure that the courses included in the analysis have been effectively studied, and ensure the reliability of the data; Through the sorting of key features, clarify the core skill requirements of different skill levels, and provide data support for learning path recommendation.

[0019] S3. Mark the adjustment object and record the target skill level of the adjustment object; According to the learning records of the adjustment object, analyze the features already possessed by the adjustment object, and according to the target skill level of the adjustment object, analyze the missing features of the adjustment object. Combine the key features of each course in the database to filter out the training course set; According to the above technical solution, the step S3 includes the following: S3-1. When a certain object to be managed sends a request for skill level adjustment, mark this object to be managed as an adjustment object; Collect the target skill level of the adjustment object and store it in the database, and extract all the learning records of the adjustment object from the database; S3-2. According to all the learning records of the adjustment object, filter out the learning records whose course completion degree is greater than or equal to the first threshold and whose test scores are greater than or equal to the second threshold; Extract the courses corresponding to all the filtered learning records and mark them as the completed courses of the adjustment object; Combine the key features corresponding to each completed course to count all the key features as the features already possessed by the adjustment object; S3-3. According to the target skill level of the adjustment object, extract the associated features corresponding to the target skill level from the database, and compare them with the features already possessed by the adjustment object, and filter out the associated features that are not included in the features already possessed by the adjustment object among the associated features corresponding to the target skill level; Re-sort the filtered associated features from front to back according to the serial numbers of each associated feature, and take the re-sorted associated features as the missing features of the adjustment object and record the serial numbers of the missing features; S3-4. Filter from all the courses in the database. If any missing feature of the adjustment object is included in the key features of a certain course, assign this course to the training course set. After identifying the adjustment object, ensure that the recommended learning path is targeted and personalized; by comparing the features already possessed by the adjustment object and the target skill level features, accurately locate the person's skill short board and optimize the learning content; the selected training courses accurately match the missing features, ensuring the pertinence of the training and improving the learning efficiency.

[0020] S4. According to the training course set of the adjustment object, combined with all the learning records in the database, analyze the best learning path of the adjustment object, and form a recommended course schedule to push to the adjustment object. According to the above technical solution, the step S4 includes the following: S4-1. Extract the courses corresponding to all the learning records from the database and count the number of times each course has been learned; according to the sequence numbers of the missing features, successively screen out the courses corresponding to each missing feature and with the most learning times in the training course set. When the courses with the most learning times corresponding to different missing features are the same course, delete the missing feature with the later sequence number and its sequence number. S4-2. Sort the screened courses in the order from the first to the last according to the sequence numbers corresponding to the screened missing features, and use the sorted courses as the best learning path, and form a recommended course schedule to push to the adjustment object. For example: The courses in the training course set include Introduction to Machine Learning, Basics of Deep Learning, and Basics of Reinforcement Learning. Among them, the key features of Introduction to Machine Learning are machine learning and deep learning, the key features of Basics of Deep Learning are deep learning and model training, and the key features of Basics of Reinforcement Learning are reinforcement learning and policy gradient; and the number of times Introduction to Machine Learning has been learned is 500, the number of times Basics of Deep Learning has been learned is 400, and the number of times Basics of Reinforcement Learning has been learned is 300. The missing features of an adjustment object A are deep learning, reinforcement learning, and policy gradient; the sequence number of deep learning is 01, the sequence number of reinforcement learning is 02, and the sequence number of policy gradient is 03. Successively screen out the courses corresponding to each missing feature and with the most learning times in the training course set. Respectively, the course corresponding to deep learning 01 is Introduction to Machine Learning; the course corresponding to reinforcement learning 02 is Basics of Reinforcement Learning; the course corresponding to policy gradient 03 is Basics of Reinforcement Learning. The courses corresponding to reinforcement learning 02 and policy gradient 03 are the same course, both being Basics of Reinforcement Learning; at this time, the sequence number of policy gradient 03 is after the sequence number of reinforcement learning 02, and delete policy gradient 03. Sort the selected courses in ascending order according to the serial numbers corresponding to the missing features after screening. The serial number of the Introduction to Machine Learning is 11, and the serial number of the Basics of Reinforcement Learning is 12.

[0021] By screening high-frequency learning courses, ensure that the recommended courses have high practicality and recognition; by optimizing the sorting, make the learning path more reasonable and improve the learning efficiency of the objects to be adjusted; push personalized course schedules, simplify the learning process of personnel, and improve the training effect.

[0022] Please refer to Figure 2 , a training management system for an adaptive learning path based on artificial intelligence, which includes a course analysis module, a course association module, an adjustment module, and a path optimization module; The course analysis module is used to extract course keywords through natural language processing, obtain the key features of the courses and store them in the database, and classify them according to skill levels to provide basic data for learning path planning; the course association module is used to screen courses with learning completion and test scores meeting the standards according to the learning records of the objects to be managed, extract the associated features of each skill level by counting the key features of the courses, and establish the association relationship between the skill levels and the courses; the adjustment module is used to identify the objects to be adjusted in skill levels, analyze their learning records, extract the mastered key features, compare them with the associated features of the target skill levels, screen out the missing features, and match the training courses that meet the requirements to generate a set of training courses; the path optimization module is used to count the number of times all courses are learned, screen the best courses based on the missing features, form a personalized learning path after sorting, and push it to the adjusted objects.

[0023] According to the above technical solution, the course analysis module includes a course information unit and an object classification unit; The course information unit is used to extract the course introduction and course content from the database, and use natural language processing technology to extract keywords to form the key features of the courses, and store them in the database; the object classification unit is used to divide the object set according to skill levels and provide customized training plans for the objects to be managed at different skill levels.

[0024] According to the above technical solution, the course association module includes a record screening unit and a feature analysis unit; The record screening unit is used to extract all the learning records of the objects to be managed, and screen out the learning records that meet the requirements based on the thresholds of course completion and test scores to determine the associated courses of each skill level; the feature analysis unit is used to count the number of times the key features appear in the associated courses of each skill level, sort the key features, extract the required features, and obtain the associated features of the skill levels and the courses.

[0025] According to the above technical solution, the adjustment module includes an object recognition unit and a difference analysis unit; The object recognition unit is used to mark the person as an adjustment object when the object to be managed submits a request for skill level adjustment according to its own needs, record its target skill level, and extract all its learning records to prepare for subsequent learning path recommendation; the difference analysis unit is used to compare the key features already possessed by the adjustment object with the associated features of the target skill level, screen out the missing features, and screen and match the training courses from the database based on the missing features.

[0026] According to the above technical solution, the path optimization module includes a course screening unit and a path generation unit; The course screening unit is used to count the number of times all courses have been learned, and screen the training courses that meet the requirements based on the priority of the missing features; the path generation unit is used to optimize the sorting according to the screened training courses, form the best learning path, and push it to the adjustment object.

[0027] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0028] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A training management method based on an adaptive learning path based on artificial intelligence, characterized by: The method comprises the following steps: S1. Obtain course information of each course from the database, analyze key features of each course and store them in the database; obtain skill levels of objects to be managed from the database, and divide the objects to be managed into different object sets; S2. Obtain the learning records of each object to be managed in the object set, screen the learning courses of each object to be managed, and form associated courses of skill levels; analyze the associated features of skill levels according to the key features corresponding to the associated courses of skill levels; S3. Mark the adjustment object and record the target skill level of the adjustment object; analyze the characteristics of the adjustment object according to the learning record of the adjustment object, and analyze the missing characteristics of the adjustment object according to the target skill level of the adjustment object, and filter out the training course set by combining the key characteristics of each course in the database; S4. Based on the training course set of the adjustment object and in combination with all learning records in the database, the best learning path for the adjustment object is analyzed, and a recommended course schedule is formed and pushed to the adjustment object.

2. The training management method of adaptive learning path based on artificial intelligence according to claim 1, characterized in that: The step S1 comprises the following: S1-1, the course information includes course introduction and course content, and the course information of each course is subjected to keyword extraction by using natural language processing technology, and the keywords corresponding to each course are used as the key features of the corresponding course; the key features of all courses in the database are extracted and stored in the database; S1-2, the skill levels include elementary, intermediate and advanced; the object set includes elementary object set, intermediate object set and advanced object set; According to the skill level of the objects to be managed, the objects to be managed with primary skill level are divided into a primary object set; Classify the objects to be managed with intermediate skill levels into the intermediate object set; The objects to be managed with advanced skill levels are classified into the advanced object set.

3. The training management method of adaptive learning path based on artificial intelligence according to claim 2, characterized in that: The step S2 comprises the following: S2-1. Each time the managed object conducts a learning activity, a learning record is generated; the learning record includes courses, course completion and test scores; S2-2, extract all learning records of each object to be managed in a certain object set, set a first threshold and a second threshold, and filter out learning records whose course completion degree is greater than or equal to the first threshold and whose test scores are greater than or equal to the second threshold; The courses corresponding to all the filtered learning records are used as the associated courses of the skill level corresponding to the object set; and the associated courses of each skill level are obtained according to each object set; S2-3. According to the associated courses of a certain skill level, the key features corresponding to the associated courses of the skill level are counted, the number of occurrences of each key feature is counted, and the key features are sorted from large to small according to the number of occurrences of each key feature; The sorted key features are used as the associated features of the skill level and the serial numbers of each associated feature are recorded.

4. The training management method of adaptive learning path based on artificial intelligence according to claim 3 is characterized by: The step S3 includes the following: S3-1. When a subject to be managed issues a request for skill level adjustment, the subject to be managed is marked as an adjustment subject; the target skill level of the adjustment subject is collected and stored in a database, and all learning records of the adjustment subject are extracted from the database; S3-2. Based on all the learning records of the adjustment object, select the learning records whose course completion degree is greater than or equal to the first threshold and whose test scores are greater than or equal to the second threshold; extract the courses corresponding to all the selected learning records and mark them as completed courses of the adjustment object; combine the key features corresponding to each completed course, and count all the key features as the features already possessed by the adjustment object; S3-3, according to the target skill level of the adjustment object, extracting the associated features corresponding to the target skill level from the database, and comparing them with the already possessed features of the adjustment object, and screening out the associated features corresponding to the target skill level that are not included in the already possessed features of the adjustment object; The selected associated features are reordered from front to back according to the serial numbers of the associated features, and the reordered associated features are used as the missing features of the adjustment object and the serial numbers of the missing features are recorded; S3-4. Screen all courses in the database. If the key feature of a course contains any missing feature of the adjustment object, assign the course to the training course set.

5. The training management method of adaptive learning path based on artificial intelligence according to claim 4 is characterized in that: The step S4 comprises the following: S4-1. Extract all courses corresponding to the learning records from the database and count the number of times each course has been learned; according to the sequence number of the missing feature, select the course corresponding to each missing feature and having the most number of learning times from the training course set in turn; When the courses with the most learning times corresponding to different missing features are the same course, the missing features with the later serial numbers and their serial numbers will be deleted; S4-2. Sort the selected courses from first to last according to the serial numbers corresponding to the missing features after screening, and use the sorted courses as the best learning path, and form a recommended course schedule and push it to the adjustment object.

6. A training management system for adaptive learning paths based on artificial intelligence, used to implement the training management method for adaptive learning paths based on artificial intelligence as claimed in any one of claims 1 to 5, characterized in that: The system includes a course analysis module, a course association module, an adjustment module and a path optimization module; The course analysis module is used to extract course keywords through natural language processing, obtain key features of the courses and store them in a database, and classify them by skill level to provide basic data for learning path planning; the course association module is used to screen courses with satisfactory learning completion and test scores based on the learning records of the objects to be managed, extract the associated features of each skill level by counting the key features of the courses, and establish an associated relationship between the skill level and the courses; the adjustment module is used to identify the object of skill level adjustment, analyze its learning records, extract the key features that have been mastered, and compare them with the associated features of the target skill level, screen the missing features, match the training courses that meet the requirements, and generate a training course set; the path optimization module is used to count the number of times all courses have been studied, and screen the best courses based on the missing features, form a personalized learning path after sorting, and push it to the adjustment object.

7. The training management system based on adaptive learning path of artificial intelligence according to claim 6, characterized in that: The course analysis module includes a course information unit and an object classification unit; The course information unit is used to extract course introduction and course content from the database, and use natural language processing technology to extract keywords to form key features of the course and store them in the database; the object classification unit is used to divide the object set according to skill level and provide customized training plans for objects to be managed with different skill levels.

8. The training management system based on adaptive learning path of artificial intelligence according to claim 6, characterized in that: The course association module includes a record screening unit and a feature analysis unit; The record screening unit is used to extract all learning records of the object to be managed, and screen out learning records that meet the requirements based on the thresholds of course completion and test scores, and determine the associated courses for each skill level; The feature analysis unit is used to count the number of occurrences of key features in the associated courses of each skill level, sort the key features, extract the required features, and obtain the associated features of the skill level and the course.

9. The training management system based on adaptive learning path of artificial intelligence according to claim 6, characterized in that: The adjustment module includes an object recognition unit and a difference analysis unit; The object identification unit is used to mark the person as an adjustment object, record his / her target skill level, and extract all his / her learning records when the object to be managed submits a request for skill level adjustment according to his / her own needs, in preparation for subsequent learning path recommendations; the difference analysis unit is used to compare the key features already possessed by the adjustment object with the associated features of the target skill level, screen out missing features, and screen matching training courses from the database based on the missing features.

10. The training management system based on adaptive learning path of artificial intelligence according to claim 6, characterized in that: The path optimization module includes a course screening unit and a path generation unit; The course screening unit is used to count the number of times all courses have been studied, and based on the priority of missing features, screen training courses that meet the needs; the path generation unit is used to optimize the order of the screened training courses, form the best learning path, and push it to the adjustment object.

Images