Training subject management method and system based on knowledge classification

Abstract

The invention relates to the technical field of educational training, and discloses a training subject management method and system based on knowledge classification. A knowledge classification unit, a knowledge evaluation unit and a matching management unit; knowledge is accurately divided into a basic class, an advanced class and an application class through a unique algorithm and technology, for example, the basic knowledge is compared with a keyword library, the advanced knowledge constructs a knowledge graph to calculate the correlation degree, and the application knowledge is combined with actual case analysis, so that a solid foundation is laid for subsequent training; a standardized evaluation process is designed for different types of knowledge, so that the knowledge level of a trainer can be comprehensively known; different recommendation strategies are formulated according to the level of each knowledge type of the trainee, for example, a basic superior person focuses on advanced and application knowledge and recommends a large-scale project to an application knowledge superior person, so that the learning requirements of different trainees can be met, the problem of mismatching of learning contents is avoided, and the training effect and efficiency are improved; and the knowledge and application ability of the trainee can be improved more efficiently.

Description

Technical Field

[0001] The present invention relates to the technical field of education and training, and specifically relates to a training subject management method and system based on knowledge classification. Background Art

[0002] In today's era of fierce competition and rapid knowledge iteration, various training and learning activities are crucial for the development of individuals and organizations. Whether it is vocational skill training, academic education, or enterprise internal training, they all face the challenge of how to efficiently manage training subjects to improve the training effect and learning efficiency.

[0003] Traditional training subject management methods are often relatively extensive, lacking in-depth analysis and reasonable classification of knowledge content. In terms of knowledge classification, it is usually simply divided according to disciplines or curriculum modules, and it is impossible to accurately identify different levels of knowledge such as basic, advanced, and applied knowledge, resulting in an unclear and imperfect construction of the knowledge system. For example, in some vocational skill trainings, for complex professional knowledge, there is no clear distinction between the basic concepts, theories, and operation specifications that beginners must master, the advanced knowledge that further improves on the basis of the basics, and the applied knowledge that is closely combined with the actual work scenario. This makes the arrangement of training content lack systematicness and logic, and trainees are prone to confusion during the learning process and difficult to gradually master knowledge.

[0004] Therefore, there is an urgent need for a training subject management method and system based on knowledge classification to improve the scientificity, pertinence, and effectiveness of training subject management. Summary of the Invention

[0005] The purpose of the present invention is to provide a training subject management method and system based on knowledge classification, which solves the technical problems raised in the background art.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A training subject management method based on knowledge classification includes:

[0008] The first step, knowledge classification: classifying the knowledge content in the text related to all training subjects, and classifying it into basic knowledge, advanced knowledge, and applied knowledge;

[0009] The second step, knowledge assessment: evaluating the knowledge level of the trainee based on basic knowledge, advanced knowledge, and applied knowledge, and determining the knowledge level grades of the trainee in basic knowledge, advanced knowledge, and applied knowledge respectively;

[0010] Step 3, Matching Management: Based on the knowledge level grades of the trainer in basic knowledge, advanced knowledge, and applied knowledge respectively, and in combination with the pre-set knowledge content recommendation rules, perform matching recommendations for the corresponding knowledge content of the trainer and the training subjects.

[0011] As a further solution of the present invention: The classification processing method is as follows:

[0012] Step F1, Basic Knowledge Classification:

[0013] Step F1.1, Extract the knowledge content corresponding to the basic concepts, basic theories, and basic operation specifications from all the knowledge content in all the texts related to the training subjects.

[0014] Step F1.2, Establish a basic knowledge keyword library, and use the text matching algorithm to compare the extracted knowledge content with the keyword library:

[0015] If the keyword library contains the extracted relevant knowledge content, then determine the extracted relevant knowledge content as basic knowledge.

[0016] Step F1.3, Combine all the basic knowledge into a basic knowledge set.

[0017] Step F2, Advanced Knowledge Classification:

[0018] Step F2.1, Select a knowledge content, and through natural language processing technology, extract the key concepts and relationship statements in the knowledge content. Then, use the key concepts as nodes and the relationship statements as edges between the nodes to construct a knowledge graph.

[0019] Step F2.2, Mark the knowledge content as E∈{e j}, j = 1, 2, …… v, where v represents the number of key concepts in the knowledge content;

[0020] At the same time, mark the basic knowledge set as B∈{b i}, i = 1, 2, …… n, where n represents the number of all the basic knowledge in the basic knowledge set, and b i represents the i-th basic knowledge in the basic knowledge set;

[0021] Step F2.3, Count the number of times the key concepts in the knowledge content and each basic knowledge appear together in each statement in the relevant text, and mark it as N(e j , b i );

[0022] At the same time, count the total number of times the key concepts in the knowledge content appear in each statement in the relevant text, and mark it as N(b i )

[0023] Step F2.4: By: calculate the correlation degree R(e j , b i ) between the key concepts and basic knowledge in the knowledge content;

[0024] Step F2.5: Compare the correlation degree R(e j , b i ) between the key concepts and basic knowledge in the knowledge content with the preset correlation degree threshold RY:

[0025] When R(e j , b i ) ≥ RY, then determine the key concept in the extracted knowledge content as advanced knowledge; otherwise, it is not advanced knowledge;

[0026] Step F2.6: Then form an advanced knowledge set with all the advanced knowledge;

[0027] Step F3: Apply knowledge classification:

[0028] Step F3.1: Collect the actual application cases related to the training subjects and store them in the pre-established case database;

[0029] Step F3.2: Use the semantic analysis matching method to match each knowledge content with the actual application cases in the case database;

[0030] Step F3.3: Count the number of times each knowledge content appears in each actual application case in the case database and mark it as K(P t , A g );

[0031] Step F3.4: By calculate the application frequency F(Pt) of the t-th knowledge content;

[0032] Step F3.5: Compare the application frequency F(P t ) of each knowledge content with the preset application frequency threshold FY:

[0033] When F(P t ) ≥ FY, then determine the extracted knowledge content as application knowledge, otherwise it is not application knowledge;

[0034] Step F3.6: Form an application knowledge set with all the application knowledge.

[0035] As a further solution of the present invention: The matching method in Step F3.2 is as follows:

[0036] Semantically encode the knowledge content and actual application cases respectively using semantic analysis tools in natural language processing technology, and convert the text into semantic vectors that can be understood by a computer;

[0037] Calculate the similarity between the semantic vector of the knowledge content and the semantic vector of the actual application case through the cosine similarity formula;

[0038] When its similarity exceeds the preset similarity threshold, it is determined that the knowledge content appears in the actual application case.

[0039] As a further solution of the present invention: Among them, the cosine similarity formula is

[0040]

[0041] In the formula, Sim(P t , A g ) is the similarity between the semantic vector of the knowledge content and the semantic vector of the actual application case, P t is the semantic vector of the knowledge content, t = 1, 2,... r, r represents the number of knowledge contents in the relevant text, A g is the semantic vector of the actual application case, g = 1, 2,... c, c represents the number of actual application cases in the case database.

[0042] As a further solution of the present invention: The knowledge level assessment method is as follows:

[0043] Select basic knowledge for knowledge level assessment;

[0044] Step G1.1: Design a test question bank covering each basic knowledge according to the determined set of basic knowledge; Randomly select a specified number of test questions from the test question bank to form a test paper, and let the trainer complete the answer within a specified time;

[0045] Step G1.2: Score the trainer's test answer sheet according to the standard answers corresponding to the test questions, obtain the score of the trainer, and mark it as DF1. At the same time, extract the total score of the test paper and mark it as ZF1;

[0046] Step G1.3: Pass: Calculate the basic knowledge level score SP1;

[0047] Step G1.4: According to the preset rating rules, divide the basic knowledge level of the trainer into different levels;

[0048] Among them, the knowledge level assessment methods for advanced knowledge and applied knowledge are the same as those for basic knowledge.

[0049] As a further solution of the present invention: The rating rules are as follows:

[0050] SP1≥80 indicates that the basic knowledge level is excellent; SP2≥80 indicates that the advanced knowledge level of the trainer is excellent; SP3≥80 indicates that the applied knowledge level of the trainer is excellent;

[0051] 60≤SP1<80 indicates that the basic knowledge level of the trainer is good; 60≤SP2<80 indicates that the advanced knowledge level of the trainer is good; 60≤SP3<80 indicates that the applied knowledge level of the trainer is good;

[0052] 40≤SP1<60 indicates that the basic knowledge level of the trainer is medium; 40≤SP2<60 indicates that the advanced knowledge level of the trainer is medium; 40≤SP3<60 indicates that the applied knowledge level of the trainer is medium;

[0053] SP1<40 indicates that the basic knowledge level of the trainer is poor; SP2<40 indicates that the advanced knowledge level of the trainer is poor; SP3<40 indicates that the applied knowledge level of the trainer is poor.

[0054] As a further solution of the present invention: the knowledge content recommendation rules are as follows:

[0055] Step P1, based on the knowledge level of basic knowledge:

[0056] When the basic knowledge level of the trainer is excellent, the advanced knowledge and applied knowledge are recommended to the trainer according to the knowledge content recommendation ratio of 1:4;

[0057] When the basic knowledge level of the trainer is good, the basic knowledge and advanced knowledge are recommended to the trainer according to the knowledge content recommendation ratio of 3:7;

[0058] When the basic knowledge level of the trainer is medium, the basic knowledge and advanced knowledge are recommended to the trainer according to the knowledge content recommendation ratio of 4:1;

[0059] When the basic knowledge level of the trainer is poor, the knowledge content at the basic knowledge level is recommended to the trainer;

[0060] Step P2, based on the knowledge level of advanced knowledge:

[0061] When the advanced knowledge level of the trainer is excellent, the advanced knowledge and applied knowledge are recommended to the trainer according to the knowledge content recommendation ratio of 4:1;

[0062] When the advanced knowledge level of the trainer is good, the advanced knowledge and applied knowledge are recommended to the trainer according to the knowledge content recommendation ratio of 1:1;

[0063] When the advanced knowledge level of the trainee is medium, basic knowledge and advanced knowledge are recommended to the trainee according to the knowledge content recommendation ratio of 2:3.

[0064] When the advanced knowledge level of the trainee is poor, basic knowledge and advanced knowledge are recommended to the trainee according to the knowledge content recommendation ratio of 4:1.

[0065] Step P3: Based on the knowledge level grade of applied knowledge:

[0066] When the advanced knowledge level of the trainee is excellent, the trainee is recommended to participate in large-scale practical application projects.

[0067] When the advanced knowledge level of the trainee is good, the trainee is recommended to participate in small-scale practical application projects, and at the same time, the knowledge content corresponding to the applied knowledge level is recommended to the trainee.

[0068] When the advanced knowledge level of the trainee is medium, the knowledge content corresponding to the applied knowledge level is recommended to the trainee, and the trainee is recommended to participate in the practical courses corresponding to the application projects.

[0069] When the advanced knowledge level of the trainee is poor, basic knowledge, advanced knowledge and applied knowledge are given to the trainee according to the knowledge content recommendation ratio of 5:3:2.

[0070] A training subject management system based on knowledge classification, which is implemented by a training subject management method based on knowledge classification. The system includes:

[0071] A knowledge classification unit for classifying the knowledge content in the text related to all training subjects and classifying it into basic knowledge, advanced knowledge and applied knowledge.

[0072] A knowledge evaluation unit for evaluating the knowledge level of the trainee based on basic knowledge, advanced knowledge and applied knowledge, and determining the knowledge level grades of the trainee in basic knowledge, advanced knowledge and applied knowledge respectively.

[0073] A matching management unit for matching and recommending the corresponding knowledge content of the trainee and the training subject according to the knowledge level grades of the trainee in basic knowledge, advanced knowledge and applied knowledge respectively.

[0074] The beneficial effects of the present invention:

[0075] In the present invention, through a detailed and systematic classification method, the knowledge content in the text related to training subjects is classified into basic knowledge, advanced knowledge, and applied knowledge. Among them, for the classification of basic knowledge, by using a keyword library and a text matching algorithm, basic concepts, theories, and operation specifications can be accurately extracted; for the classification of advanced knowledge, by means of methods such as knowledge graphs and correlation calculations, the correlation between the knowledge content and basic knowledge is deeply analyzed to effectively distinguish advanced knowledge; for the classification of applied knowledge, by combining actual application cases and semantic analysis matching methods, and determining applied knowledge according to the application frequency, the knowledge classification is more in line with the actual training needs, providing a solid foundation for subsequent training.

[0076] In the present invention, scientific evaluation methods are respectively designed for basic knowledge, advanced knowledge, and applied knowledge. By designing a test question bank covering various knowledge types, randomly extracting test questions to form a test paper, answering within a specified time and grading according to the standard answers, then calculating the knowledge level score according to a specific formula, and finally dividing the levels according to the preset rating rules, it is possible to comprehensively and accurately evaluate the level of the trainer at different knowledge levels, providing a basis for personalized training.

[0077] In the present invention, according to the different level grades of the trainer in basic knowledge, advanced knowledge, and applied knowledge, a detailed matching management strategy is formulated. For trainers with different basic knowledge levels, different knowledge contents are recommended in different proportions; for trainers with different advanced knowledge levels, corresponding knowledge contents are also recommended according to the level differences; for trainers with different applied knowledge levels, not only knowledge contents are recommended, but also different-scale actual application projects or practice courses are recommended according to the levels. This personalized matching management can better meet the learning needs of the trainer, improve the training effect and efficiency, and achieve individualized teaching.

[0078] In the present invention, through scientific knowledge classification, accurate knowledge level evaluation, and personalized matching management, the trainer can obtain training content suitable for their knowledge level, avoiding the situation where the learning content is too difficult or too easy, helping the trainer to more efficiently improve their knowledge level and application ability, thereby improving the overall training effect and efficiency and enhancing the training quality.

[0079] In the present invention, during the classification process of applied knowledge, actual application cases are collected and the knowledge content is matched with the cases by using the semantic analysis matching method. In the matching management, actual application projects are recommended according to the applied knowledge level, making the training content closely combined with the actual application scenario, enhancing the trainer's ability to apply knowledge to practice, and cultivating talents more in line with actual needs. Brief Description of the Drawings

[0080] The present invention will be further described below with reference to the accompanying drawings.

[0081] Figure 1It is a system block diagram of a training subject management system based on knowledge classification according to the present invention.

[0082] Figure 2 It is a schematic flowchart of a training subject management method based on knowledge classification according to the present invention. Specific embodiments

[0083] 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0084] Embodiment 1

[0085] Please refer to Figure 1 and Figure 2 As shown, the present invention is a training subject management method based on knowledge classification, including:

[0086] The first step, knowledge classification:

[0087] Classify the knowledge content in the text related to all training subjects, and classify it into basic knowledge, advanced knowledge, and applied knowledge;

[0088] The classification method is as follows:

[0089] Step F1, basic knowledge classification:

[0090] Step F1.1, extract the knowledge content corresponding to the basic concepts, basic theories, and basic operation specifications from all the knowledge content in the text related to all training subjects;

[0091] For example: in language training subjects, letters, phonetic symbols, basic vocabulary, simple grammar rules, etc. belong to the category of basic knowledge;

[0092] Step F1.2, establish a basic knowledge keyword library, and use a text matching algorithm to compare the extracted knowledge content with the keyword library:

[0093] Among them, the text matching algorithm is an existing technology, so it will not be elaborated here;

[0094] If the keyword library contains the extracted relevant knowledge content, the extracted relevant knowledge content is determined as basic knowledge;

[0095] Step F1.3, form all the basic knowledge into a basic knowledge set;

[0096] In this embodiment, manual review and confirmation are also carried out on the basic knowledge set by professionals. The method is as follows: professionals judge each piece of knowledge content in the basic knowledge set one by one according to the essential attributes of the relevant knowledge content and its fundamental status in the training system, and finally determine the basic knowledge set;

[0097] Step F2, advanced knowledge classification:

[0098] Step F2.1, select a piece of knowledge content. Through natural language processing technology, extract the key concepts and relationship statements in this knowledge content. Then, take the key concepts as nodes and the relationship statements as the edges between the nodes to construct a knowledge graph;

[0099] Among them, natural language processing technology is an existing technology, so it will not be elaborated here;

[0100] In this embodiment, the extraction method of key concepts in the knowledge content is as follows: perform word segmentation on the knowledge content, and then count the frequency of each word obtained by word segmentation; then, define the nouns and noun phrases with a frequency higher than the preset frequency threshold as key concepts;

[0101] Step F2.2, mark this knowledge content as E∈{e j}, j = 1, 2,... v, where v represents the number of key concepts in the knowledge content;

[0102] At the same time, mark the basic knowledge set as B∈{b i}, i = 1, 2,... n, where n represents the number of all basic knowledge in the basic knowledge set, and b i represents the i-th piece of basic knowledge in the basic knowledge set;

[0103] Step F2.3, count the number of times that the key concepts in the knowledge content and each piece of basic knowledge appear together in each statement in the relevant text, and mark it as N(e j , b i );

[0104] At the same time, count the total number of times that the key concepts in the knowledge content appear in each statement in the relevant text, and mark it as N(b i )

[0105] Step F2.4, through: Calculate the correlation degree R(e j , b i ) between the key concepts in the knowledge content and the basic knowledge;

[0106] Step F2.5, the correlation degree R(e j , b i) Compare with the preset correlation threshold RY:

[0107] When R(e j , b i ) ≥ RY, then determine the key concept in the extracted knowledge content as advanced knowledge;

[0108] When R(e j , b i ) < RY, then do not determine the key concept in the extracted knowledge content as advanced knowledge;

[0109] Step F2.6. Subsequently, form all advanced knowledge into an advanced knowledge set;

[0110] In this embodiment, the basic knowledge set is also manually reviewed and confirmed by professionals. The method is as follows: Professionals judge each piece of knowledge content in the basic knowledge set one by one according to the difficulty level of the relevant knowledge content and its role in the training and advancement process, and finally determine the basic knowledge set;

[0111] Step F3. Apply knowledge classification:

[0112] Step F3.1. Collect actual application cases related to the training subject and store them in a pre-established case database;

[0113] Step F3.2. Use the semantic analysis matching method to match each piece of knowledge content with the actual application cases in the case database. The matching method is as follows:

[0114] Use the semantic analysis tool in natural language processing technology to perform semantic encoding on the knowledge content and the actual application cases respectively, and convert the text into semantic vectors that can be understood by the computer;

[0115] Calculate the similarity between the semantic vector of the knowledge content and the semantic vector of the actual application case through the cosine similarity formula;

[0116] When its similarity exceeds the preset similarity threshold, it is determined that the knowledge content appears in the actual application case;

[0117] Among them, the cosine similarity formula is

[0118] In the formula, Sim(P t , A g ) is the similarity between the semantic vector of the knowledge content and the semantic vector of the actual application case, P t is the semantic vector of the knowledge content, t = 1, 2,... r, r represents the number of knowledge contents in the relevant text, A g is the semantic vector of the actual application case, g = 1, 2,... c, c represents the number of actual application cases in the case database;

[0119] Step F3.3: Count the number of occurrences of each knowledge content in each actual application case in the case database, and mark it as K(P t , A g );

[0120] Step F3.4: Calculate the application frequency F(Pt) of the t-th knowledge content through ;

[0121] Step F3.5: Compare the application frequency F(P t ) of each knowledge content with the preset application frequency threshold FY:

[0122] When F(P t ) ≥ FY, determine the extracted knowledge content as applied knowledge;

[0123] When F(P t ) < FY, do not determine the extracted knowledge content as applied knowledge;

[0124] Step F3.6: Combine all applied knowledge into an applied knowledge set;

[0125] In this embodiment, professional personnel are also used to manually review and confirm the corresponding applied knowledge set. The method is as follows: Professional personnel make judgments on the knowledge content in the applied knowledge set one by one according to the relevant knowledge content, and finally determine the applied knowledge set;

[0126] Second step: Knowledge assessment:

[0127] Evaluate the knowledge level of the trainer based on basic knowledge, advanced knowledge, and applied knowledge, and determine the knowledge level grades of the trainer in basic knowledge, advanced knowledge, and applied knowledge respectively;

[0128] The knowledge level assessment method is as follows:

[0129] Step G1: Basic knowledge level assessment:

[0130] Step G1.1: Design a test question bank covering each basic knowledge based on the determined basic knowledge set; Randomly select a specified number of test questions from the test question bank to form a test paper, and let the trainer complete the answer within a specified time;

[0131] Step G1.2: Score the trainer's test answer sheet according to the standard answers corresponding to the test questions, obtain the score of the trainer, and mark it as DF1. At the same time, extract the total score of the test paper and mark it as ZF1;

[0132] Step G1.3: Calculate the basic knowledge level score SP1 through: ;

[0133] Step G1.4: Classify the basic knowledge level of the trainer into different levels according to the pre-set rating rules;

[0134] The rating rules are as follows:

[0135] If SP1 ≥ 80, it is determined that the basic knowledge level of the trainer is excellent;

[0136] If 60 ≤ SP1 < 80, it is determined that the basic knowledge level of the trainer is good;

[0137] If 40 ≤ SP1 < 60, it is determined that the basic knowledge level of the trainer is medium;

[0138] If SP1 < 40, it is determined that the basic knowledge level of the trainer is poor;

[0139] Step G2: Advanced knowledge level assessment:

[0140] Step G2.1: Design a test question bank covering each advanced knowledge according to the determined advanced knowledge set; randomly select a specified number of test questions from the test question bank to form a test paper, and let the trainer complete the answer within the specified time;

[0141] Step G2.2: Score the trainer's test paper according to the corresponding standard answers of the test questions, obtain the score of the trainer, mark it as DF2, and at the same time extract the total score of the test paper and mark it as ZF2;

[0142] Step G2.3: Pass: Calculate the advanced knowledge level score SP2;

[0143] Step G2.4: Classify the advanced knowledge level of the trainer into different levels according to the pre-set rating rules;

[0144] The rating rules are as follows:

[0145] If SP2 ≥ 80, it is determined that the advanced knowledge level of the trainer is excellent;

[0146] If 60 ≤ SP2 < 80, it is determined that the advanced knowledge level of the trainer is good;

[0147] If 40 ≤ SP2 < 60, it is determined that the advanced knowledge level of the trainer is medium;

[0148] If SP2 < 40, it is determined that the advanced knowledge level of the trainer is poor;

[0149] Step G3: Applied knowledge level assessment:

[0150] Step G3.1: Design a test question bank covering all application knowledge based on the determined set of application knowledge; randomly select a specified number of test questions from the test question bank to form a test paper, and let the trainer complete the answering within a specified time limit;

[0151] Step G3.2: Score the trainer's test paper according to the corresponding standard answers of the test questions, obtain the trainer's score, mark it as DF3, and at the same time extract the total score of the test paper, and mark it as ZF3;

[0152] Step G3.3: Calculate the application knowledge level score SP3 through: Calculate the application knowledge level score SP3;

[0153] Step G3.4: According to the pre-set rating rules, divide the trainer's application knowledge level into different levels;

[0154] The rating rules are as follows:

[0155] If SP3 ≥ 80, it is determined that the trainer's application knowledge level is excellent;

[0156] If 60 ≤ SP3 < 80, it is determined that the trainer's application knowledge level is good;

[0157] If 40 ≤ SP3 < 60, it is determined that the trainer's application knowledge level is medium;

[0158] If SP3 < 40, it is determined that the trainer's application knowledge level is poor;

[0159] Step 3: Matching management:

[0160] Based on the knowledge level grades of the trainer in basic knowledge, advanced knowledge, and application knowledge respectively, and combined with the pre-set knowledge content recommendation rules, perform matching recommendations for the knowledge content corresponding to the trainer and the training subjects;

[0161] In this embodiment, the knowledge classification unit classifies the text knowledge related to the training subjects in detail, including extracting basic concepts, etc. to determine basic knowledge, using knowledge graphs and correlation calculations to determine advanced knowledge, and determining application knowledge based on actual application cases and application frequencies, and verifying and confirming by professionals to ensure accurate classification. The knowledge assessment unit designs test question banks for the three types of knowledge respectively to evaluate the trainer's knowledge level and divide different levels, providing a basis for subsequent matching management. The matching management unit then performs matching recommendations for the trainer and the knowledge content based on the evaluation results and rules. The overall process helps to manage the training subjects more scientifically and reasonably and improve the training effect.

[0162] Embodiment 2

[0163] Please refer to Figure 1 and Figure 2As shown in the figure, as the second embodiment of the present invention, in the specific implementation of the present application, compared with the first embodiment, the technical solution of this embodiment is only different from that of the first embodiment in that a knowledge content recommendation rule is proposed in this embodiment;

[0164] The knowledge content recommendation rule is as follows:

[0165] Step P1, based on the knowledge level of basic knowledge:

[0166] When the basic knowledge level of the trainee is excellent, the knowledge content corresponding to the advanced knowledge level and the applied knowledge level is recommended to the trainee;

[0167] Among them, the ratio of the knowledge content corresponding to the advanced knowledge level and the applied knowledge level is 1:4;

[0168] Its function is to further improve the knowledge level and application ability of the trainee;

[0169] When the basic knowledge level of the trainee is good, the knowledge content corresponding to the basic knowledge level and the advanced knowledge level is recommended to the trainee;

[0170] Among them, the ratio of the knowledge content corresponding to the basic knowledge level and the advanced knowledge level is 3:7;

[0171] Its function is to consolidate the basic knowledge of the trainee and appropriately expand the advanced knowledge;

[0172] When the basic knowledge level of the trainee is medium, the knowledge content corresponding to the basic knowledge level and the advanced knowledge level is recommended to the trainee;

[0173] Among them, the ratio of the knowledge content corresponding to the basic knowledge level and the advanced knowledge level is 4:1;

[0174] Its function is to help the trainee gradually improve the knowledge level;

[0175] When the basic knowledge level of the trainee is poor, the knowledge content of the basic knowledge level is recommended to the trainee;

[0176] Its function is to ensure that the trainee has a solid foundation;

[0177] Step P2, based on the knowledge level of advanced knowledge:

[0178] When the advanced knowledge level of the trainee is excellent, the knowledge content corresponding to the advanced knowledge level and the applied knowledge level is recommended to the trainee;

[0179] Among them, the ratio of the knowledge content corresponding to the advanced knowledge level and the applied knowledge level is 4:1;

[0180] Its function is to give full play to the potential of the trainee;

[0181] When the trainer's advanced knowledge level is good, the knowledge content corresponding to the advanced knowledge level and the applied knowledge level is recommended to the trainer;

[0182] Among them, the ratio of the knowledge content corresponding to the advanced knowledge level and the applied knowledge level is 1:1;

[0183] When the trainer's advanced knowledge level is medium, the knowledge content corresponding to the basic knowledge level and the advanced knowledge level is recommended to the trainer;

[0184] Among them, the ratio of the knowledge content corresponding to the basic knowledge level and the advanced knowledge level is 2:3;

[0185] Its function is to help the trainer strengthen the understanding and application of advanced knowledge;

[0186] When the trainer's advanced knowledge level is poor, the knowledge content corresponding to the basic knowledge level and the advanced knowledge level is recommended to the trainer;

[0187] Among them, the ratio of the knowledge content corresponding to the basic knowledge level and the advanced knowledge level is 4:1;

[0188] Step P3, based on the knowledge level grade of applied knowledge:

[0189] When the trainer's advanced knowledge level is excellent, it is recommended that the trainer participate in large-scale practical application projects;

[0190] Its function is to enable the trainer to continuously improve their application ability and innovation ability in practice;

[0191] When the trainer's advanced knowledge level is good, it is recommended that the trainer participate in small-scale practical application projects, and at the same time, the knowledge content corresponding to the applied knowledge level is recommended to the trainer;

[0192] Its function is to enable the trainer to further improve their application skills in practice;

[0193] When the trainer's advanced knowledge level is medium, the knowledge content corresponding to the applied knowledge level is recommended to the trainer, and it is recommended that the trainer participate in the practical courses corresponding to the application projects;

[0194] Its function is to cultivate the trainer's application awareness and ability;

[0195] When the trainer's advanced knowledge level is poor, the knowledge content corresponding to the basic knowledge level, the advanced knowledge level and the applied knowledge level is recommended to the trainer;

[0196] Among them, the ratio of the knowledge content corresponding to the basic knowledge level, the advanced knowledge level and the applied knowledge level is 5:3:2.

[0197] This embodiment proposes a comprehensive and highly targeted knowledge content recommendation rule. According to the different proficiency levels of the trainer in basic knowledge, advanced knowledge, and applied knowledge, corresponding recommendation plans are given respectively. For example, those with excellent basic knowledge are focused on the recommendation of advanced and applied knowledge, and the recommendation ratios of knowledge content at different levels are clarified. A personalized recommendation strategy is formulated for trainers at different proficiency levels, which can better meet the learning needs of trainers and help improve their knowledge system and capabilities.

[0198] Embodiment III

[0199] Please refer to Figure 1 and Figure 2 As shown in [relevant figures], as Embodiment III of the present invention, in the specific implementation of this application, compared with Embodiment I and Embodiment II, the technical solution of this embodiment lies in the combined implementation of the solutions of the above-mentioned Embodiment I and Embodiment II.

[0200] This embodiment combines and implements the solutions of Embodiment I and Embodiment II, which not only has the advantage of scientifically managing training subjects through knowledge classification and evaluation in Embodiment I, but also has the strength of the personalized knowledge content recommendation rule in Embodiment II. By integrating the advantages of both, it can manage training subjects more comprehensively and effectively, provide knowledge content recommendations that are more in line with the actual level and needs of trainers, further improve the quality and efficiency of training management, and promote the overall improvement of the knowledge level and application ability of trainers.

[0201] A training subject management system based on knowledge classification, which is implemented through a training subject management method based on knowledge classification. The system includes:

[0202] A knowledge classification unit for classifying the knowledge content in the text related to all training subjects and classifying it into basic knowledge, advanced knowledge, and applied knowledge;

[0203] A knowledge evaluation unit for evaluating the knowledge level of trainers based on basic knowledge, advanced knowledge, and applied knowledge and determining the knowledge level grades of trainers in basic knowledge, advanced knowledge, and applied knowledge respectively;

[0204] A matching management unit for making matching recommendations on the corresponding knowledge content of trainers and training subjects based on the knowledge level grades of trainers in basic knowledge, advanced knowledge, and applied knowledge respectively.

[0205] It should be stated that all the data collected in this application are collected with the consent and authorization of the users, and the uses of the data are legal and compliant, and the use and processing of the data comply with the relevant laws, regulations, and standards of the relevant regions.

[0206] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0207] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application who can't easily think of changes or substitutions should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

Claims

1. A training subject management method based on knowledge classification, characterized in that: The following steps are involved: Knowledge classification: Classify the knowledge content in the texts related to all training subjects into basic knowledge, advanced knowledge and applied knowledge; Knowledge assessment: Evaluate the trainees' knowledge level based on basic knowledge, advanced knowledge and applied knowledge, and determine the trainees' knowledge level in basic knowledge, advanced knowledge and applied knowledge respectively; Matching management: Based on the trainees' knowledge levels in basic knowledge, advanced knowledge and applied knowledge, and combined with pre-set knowledge content recommendation rules, the corresponding knowledge content of the training subjects will be matched and recommended to the trainees.

2. A training subject management method based on knowledge classification according to claim 1, characterized in that: The classification and processing of basic knowledge are as follows: Step F1.1: Extract the knowledge contents corresponding to the basic concepts, basic theories and basic operation specifications from all the knowledge contents related to all the training subjects; Step F1.2: Establish a basic knowledge keyword library and use the text matching algorithm to compare the extracted knowledge content with the keyword library: If the keyword library contains the extracted relevant knowledge content, the extracted relevant knowledge content is determined to be basic knowledge; Step F1.3: Group all basic knowledge into a basic knowledge set.

3. A training subject management method based on knowledge classification according to claim 2, characterized in that: The classification and processing of advanced knowledge are as follows: Step F2.1, select a piece of knowledge content, extract the key concepts and relational statements in the knowledge content through natural language processing technology, and then use the key concepts as nodes and the relational statements as edges between nodes to construct a knowledge graph; Step F2.2: Mark the knowledge content as E∈{e j }, j = 1, 2, ... v, v represents the number of key concepts in the knowledge content; At the same time, the basic knowledge set is marked as B∈{b i }, i = 1, 2, ... n, n represents the number of all basic knowledge in the basic knowledge set, b i Represents the i-th basic knowledge in the basic knowledge set; Step F2.3: Count the number of times the key concepts and basic knowledge in the knowledge content appear together in each sentence in the relevant text, and mark it as N (e j , b i ); At the same time, the total number of times the key concepts in the knowledge content appear in each sentence in the relevant text is counted and marked as N (b i ) Step F2.4, by: Calculate the correlation R(e) between key concepts and basic knowledge in the knowledge content j , b i ); Step F2.5: The correlation between key concepts and basic knowledge in the knowledge content R(e j , b i ) is compared with the preset correlation threshold RY: When R(e j , b i )≥RY, the key concepts in the extracted knowledge content are judged as advanced knowledge; otherwise, they are not advanced knowledge; Step F2.6, then organize all the advanced knowledge into an advanced knowledge set.

4. A training subject management method based on knowledge classification according to claim 3, characterized in that: The classification and processing of application knowledge are as follows: Step F3.1, collect practical application cases related to the training subject and store them in a pre-established case database; Step F3.2, using semantic analysis matching method to match each knowledge content with the actual application cases in the case database; Step F3.3: Count the number of times each knowledge content appears in each practical application case in the case database, and mark it as K(P t , A g ); Step F3.4: Pass Calculate the application frequency F(Pt) of the tth knowledge content; Step F3.5: Apply the application frequency of each knowledge content F(P t ) is compared with the preset application frequency threshold FY: When F(P t )≥FY, then the extracted knowledge content is judged as applied knowledge, otherwise it is not applied knowledge; Step F3.6: Group all application knowledge into an application knowledge set.

5. A training subject management method based on knowledge classification according to claim 4, characterized in that: The matching method in step F3.2 is as follows: Use semantic analysis tools in natural language processing technology to semantically encode knowledge content and practical application cases, and convert text into semantic vectors that can be understood by computers; The similarity between the knowledge content semantic vector and the actual application case semantic vector is calculated using the cosine similarity formula; When the similarity exceeds the preset similarity threshold, the knowledge content is deemed to appear in the actual application case.

6. A training subject management method based on knowledge classification according to claim 4, characterized in that: Knowledge level is assessed as follows: Select basic knowledge for knowledge level assessment; Step G1.1, based on the determined basic knowledge set, design a set of test question banks covering various basic knowledge; A specified number of test questions are randomly selected from the test question bank to form a test paper, and the trainees are required to complete the answers within the specified time; Step G1.2, score the trainee's test paper according to the standard answers corresponding to the test questions, obtain the trainee's score, and mark it as DF1, and extract the total score of the test paper and mark it as ZF1; Step G1.3, by: Calculate the basic knowledge level score SP1; Step G1.4: Divide the basic knowledge level of the trainees into different levels according to the pre-set rating rules.

7. A training subject management method based on knowledge classification according to claim 6, characterized in that: The rating rules are as follows: SP1≥80 indicates that the basic knowledge level is excellent; SP2≥80 indicates that the trainee's advanced knowledge level is excellent; SP3≥80 indicates that the trainee's applied knowledge level is excellent; 60≤SP1<80, indicating that the basic knowledge level of the trainee is good; 60≤SP2<80, indicating that the trainee’s advanced knowledge level is good; 60≤SP3<80, indicating that the trainee’s applied knowledge level is good; 40≤SP1<60, indicating that the basic knowledge level of the trainee is medium; 40≤SP2<60, indicating that the trainee’s advanced knowledge level is medium; 40≤SP3<60, indicating that the trainee’s applied knowledge level is moderate; SP1<40, indicating that the basic knowledge level of the trainee is poor; SP2<40, indicating that the trainee’s advanced knowledge level is poor; SP3<40, indicating that the trainee's applied knowledge level is poor.

8. The method for managing training subjects based on knowledge classification according to claim 6, characterized in that: in, The knowledge level of Advanced Knowledge and Applied Knowledge is assessed in the same way as the knowledge level of Basic Knowledge.

9. The method for managing training subjects based on knowledge classification according to claim 5, characterized in that: in, The formula for cosine similarity is: Where, Sim(P t , A g ) is the similarity between the knowledge content semantic vector and the actual application case semantic vector, P t is the semantic vector of the knowledge content, t = 1, 2, ... r, r represents the amount of knowledge content in the relevant text, A g is the semantic vector of the actual application case, g = 1, 2, ... c, c represents the number of actual application cases in the case database.

10. A training subject management system based on knowledge classification, the system is implemented by a training subject management method based on knowledge classification according to any one of claims 1 to 9, characterized in that: The system includes: Knowledge classification unit, which is used to classify the knowledge content in the texts related to all training subjects into basic knowledge, advanced knowledge and applied knowledge; The knowledge assessment unit is used to assess the knowledge level of the trainees based on basic knowledge, advanced knowledge and applied knowledge, and determine the knowledge level of the trainees in basic knowledge, advanced knowledge and applied knowledge respectively; The matching management unit is used to recommend matching of trainees with corresponding knowledge content of training subjects according to the trainees' knowledge levels in basic knowledge, advanced knowledge and applied knowledge.

Images