Geophysics teaching assisting method and system based on mapping knowledge domain

Abstract

The invention discloses a knowledge graph-based geophysics teaching assistance method and system. The method comprises the steps of obtaining associated graph information of gravitational exploration professional knowledge and basic physical knowledge; constructing a learning track map of the student according to the associated map information; analyzing answer data of the students based on the learning track atlas, and generating a knowledge blind spot diagnosis report; generating a progressive explanation path from basic physics to professional knowledge according to the knowledge blind spot diagnosis report; generating supplementary learning content based on the progressive interpretation path; and tracking and analyzing the test performance of the student after supplementary learning, and evaluating the question answering effect. Therefore, according to the geophysics teaching auxiliary method based on the knowledge graph, the physical basic knowledge defects of students can be made up in a targeted mode, the learning effect is improved, and the interest of the students in the geophysics major is enhanced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of educational technology, and in particular to a geophysical teaching auxiliary method and system based on knowledge graph. Background Art

[0002] In the teaching process of geophysics, the fields covered are broad and complex, including but not limited to gravity exploration, geomagnetism, geoelectricity, seismic method, well logging method, etc. These different geophysical methods have their own characteristics, requiring students to have a solid foundation in physics and an in-depth understanding of the professional field. However, in the actual teaching process, especially for freshmen with weak physics foundation, they often face many challenges.

[0003] First, when students first come into contact with geophysics courses, they need to master basic physics knowledge and the professional terms and principles of various geophysical methods. Due to the lack of necessary physics foundation, students often find it difficult to understand basic concepts such as gravitational potential field, geomagnetic field, electromagnetic field, etc. As the course progresses, students' confusion deepens when more complex calculation methods and data processing techniques are involved.

[0004] Secondly, different geophysical methods have their own unique operational requirements and data analysis steps in practice. For example, gravity exploration requires the correct use of gravimeters for field measurements, while the geomagnetic law relies on the measurement and analysis of the geomagnetic field. These practical operations require students to not only understand theoretical knowledge but also have practical operation capabilities. However, due to students' insufficient understanding of basic concepts, it is difficult for them to accurately judge the rationality of measurement results in practice, and it is also difficult to discover and correct errors in the measurement process.

[0005] More importantly, due to the fear of exposing their weak physics foundation, many students often choose to memorize silently rather than ask questions, which leads to the accumulation and expansion of wrong cognition. In this case, even if teachers find the problem, it is difficult to accurately locate the specific knowledge blind spots of each student, let alone make up for their shortcomings in basic physics knowledge.

[0006] Existing teaching assistance systems usually have many deficiencies. First, these systems often use unified teaching content and progress, which makes it difficult to adapt to the individual differences of different students. For students with weak physics foundation, this one-size-fits-all teaching method may cause them to fail to keep up with the course progress; while for students with a good foundation, they may feel that the content is repetitive and redundant. Secondly, these systems often lack the ability to deeply analyze students' knowledge structure and cannot accurately identify students' knowledge blind spots. This results in the system being unable to provide students with targeted learning suggestions and supplementary materials, and it is difficult to improve students' learning efficiency.

[0007] In addition, existing systems often use fixed knowledge points to explain questions and provide supplementary learning, lacking the dynamic construction of the relationship between basic physics knowledge and professional knowledge. This static way of presenting knowledge makes it difficult for students to build a complete knowledge system, nor does it allow students to understand the inherent connection between different knowledge points. This not only affects students' in-depth understanding of knowledge, but may also cause them to be unable to flexibly apply what they have learned when faced with complex problems.

[0008] Finally, existing systems lack the ability to continuously track and analyze students’ learning process. They can usually only provide simple test results, but cannot comprehensively analyze students’ learning trajectories, nor can they dynamically adjust teaching strategies based on students’ learning performance. This lack of personalized and adaptable teaching method is difficult to meet the special needs of geophysics teaching.

[0009] In summary, these problems combine to lead to poor teaching results, low student motivation, and weak knowledge. This is particularly serious in a major with strong theoretical and practical requirements such as geophysics. Students may barely follow along in class, but cannot flexibly apply what they have learned in practical applications, which not only affects their learning outcomes, but may also have a negative impact on their future career development. Summary of the invention

[0010] The embodiment of the present invention provides a geophysics teaching auxiliary method and system based on knowledge graph, which can specifically make up for the students' basic physical knowledge deficiencies, improve learning effects, and enhance students' interest in geophysics.

[0011] To achieve the above objectives, in a first aspect, the present invention provides a geophysical teaching auxiliary method based on a knowledge graph, comprising:

[0012] Obtaining the correlation map information of gravity exploration expertise and basic physics knowledge;

[0013] Constructing a learning trajectory map of the student according to the association map information;

[0014] Analyze students' answer data based on the learning trajectory graph to generate a knowledge blind spot diagnosis report;

[0015] generating a progressive interpretation path from basic physics to professional knowledge according to the knowledge blind spot diagnosis report;

[0016] generating supplementary learning content based on the progressive interpretation path;

[0017] Track and analyze students’ test performance after supplementary learning and evaluate the effectiveness of question-answering.

[0018] In one embodiment of the present invention, generating a progressive interpretation path from basic physics to professional knowledge according to the knowledge blind spot diagnosis report includes:

[0019] Obtaining missing information of knowledge points in the knowledge blind spot diagnosis report;

[0020] Extracting corresponding basic physics knowledge points and professional knowledge points from the associated graph information according to the knowledge point missing information;

[0021] Calculating the correlation strength between the basic physics knowledge points and the professional knowledge points to obtain correlation strength data;

[0022] Sorting the basic physics knowledge points and professional knowledge points according to the association strength data to generate a knowledge point sequence;

[0023] The progressive interpretation path is generated based on the knowledge point sequence.

[0024] In one embodiment of the present invention, the calculating the correlation strength between the basic physics knowledge points and the professional knowledge points to obtain the correlation strength data includes:

[0025] Obtaining similarity coefficients, usage frequency correlation coefficients and dependency coefficients of the basic physics knowledge points and the professional knowledge points;

[0026] Obtaining preset weight coefficients, wherein the weight coefficients include a similarity weight coefficient, a usage frequency weight coefficient, and a dependency weight coefficient;

[0027] The association strength data between the basic physics knowledge points and the professional knowledge points are calculated according to the similarity coefficient, the usage frequency association coefficient, the dependency coefficient and the corresponding weight coefficient.

[0028] In one embodiment of the present invention, the calculating of the association strength data between the basic physics knowledge points and the professional knowledge points according to the similarity coefficient, the usage frequency association coefficient, the dependency coefficient and the corresponding weight coefficient comprises:

[0029] Acquiring historical data of the similarity coefficient, the usage frequency correlation coefficient, and the dependency coefficient;

[0030] Performing standardization processing on the historical data to obtain a standardization coefficient;

[0031] Calculate adjustment parameters of each weight coefficient according to the normalization coefficient;

[0032] updating the weight coefficient based on the adjustment parameter;

[0033] The updated weight coefficient is weightedly calculated with the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient to obtain the correlation strength data.

[0034] In one embodiment of the present invention, the updated weight coefficient is weightedly calculated with the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient to obtain the correlation strength data, which includes:

[0035] Obtaining a preset association strength threshold;

[0036] Perform weighted calculation on the updated weight coefficient and the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient to obtain initial correlation strength data;

[0037] comparing the initial association strength data with the association strength threshold;

[0038] When the initial association strength data is greater than the association strength threshold, retaining the initial association strength data;

[0039] When the initial association strength data is less than or equal to the association strength threshold, setting the initial association strength data to zero;

[0040] The retained initial association strength data and the initial association strength data set to zero are used as the final association strength data.

[0041] In one embodiment of the present invention, comparing the initial association strength data with the association strength threshold comprises:

[0042] Obtaining a numerical range of the initial correlation strength data;

[0043] Dividing the initial correlation strength data into a plurality of intervals according to the numerical range;

[0044] Calculate the data distribution density within each of the intervals;

[0045] Determining a data cluster center based on the data distribution density;

[0046] Using the data cluster center as a reference benchmark, normalizing the initial association strength data to obtain normalized data;

[0047] The normalized data is numerically compared to the association strength threshold.

[0048] In one embodiment of the present invention, the geophysical teaching auxiliary method based on knowledge graph further includes:

[0049] Obtaining the knowledge deficiency type in the knowledge blind spot diagnosis report;

[0050] Selecting corresponding learning content from a preset supplementary learning resource library according to the type of knowledge deficiency;

[0051] Sorting the knowledge dependency relationship of the learning content based on the association graph information;

[0052] Generate a learning content sequence according to the sorting result;

[0053] A corresponding exercise question group is set based on the learning content sequence.

[0054] In a second aspect, the present invention provides a geophysical teaching auxiliary system based on a knowledge graph, comprising: a first acquisition module, a construction module, a first generation module, a second generation module, a third generation module and an evaluation module. The first acquisition module is used to obtain the associated graph information of gravity exploration professional knowledge and basic physics knowledge. The construction module is used to construct a student's learning trajectory graph based on the associated graph information. The first generation module is used to analyze the student's answer data based on the learning trajectory graph and generate a knowledge blind spot diagnosis report. The second generation module is used to generate a progressive interpretation path from basic physics to professional knowledge based on the knowledge blind spot diagnosis report. The third generation module is used to generate supplementary learning content based on the progressive interpretation path. And the evaluation module is used to track and analyze the test performance of students after supplementary learning and evaluate the effect of answering questions.

[0055] In a third aspect, the present invention provides an electronic device, comprising:

[0056] at least one processor; and

[0057] a memory communicatively coupled to the at least one processor;

[0058] Among them, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the geophysical teaching assistance method based on knowledge graph as described above.

[0059] In a fourth aspect, the present invention provides a computer-readable storage medium, comprising a computer program and instructions, which, when the computer program or the instructions are executed on a computer, enables the computer to execute the geophysical teaching assistance method based on the knowledge graph as described above.

[0060] Compared with the prior art, the knowledge graph-based geophysics teaching assistance method and system according to the present invention can effectively improve students' learning effects and enhance their interest in the geophysics major by accurately identifying students' knowledge blind spots, dynamically associating basic physics knowledge with professional knowledge, and generating personalized progressive learning paths and supplementary learning content. At the same time, it can also continuously track students' learning performance, evaluate the effectiveness of answering questions, and dynamically adjust teaching strategies based on feedback, thereby realizing personalized and adaptive teaching and significantly improving the overall teaching quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flow chart of a geophysical teaching auxiliary method based on knowledge graph in the first embodiment of the present invention;

[0062] Figure 2 It is a structural schematic diagram of a geophysical teaching auxiliary system based on knowledge graph in the second embodiment of the present invention;

[0063] Figure 3 It is a structural schematic diagram of an electronic device in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0064] The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention, rather than to limit the embodiments of the present invention. It is also necessary to explain that, for ease of description, only parts related to the embodiments of the present invention are shown in the accompanying drawings, rather than all structures.

[0065] In the teaching process of geophysics, due to the large number of geophysics branches, including but not limited to gravity exploration, geomagnetic method, geoelectric method, seismic method, well logging method, etc., the physical knowledge points involved are numerous and complex, so the present invention only takes gravity exploration as an example, but other branches can also adopt the method and system of the present invention. When teaching the principle of gravity exploration course for freshmen with weak physical foundation, many technical challenges are often faced. Specifically, students need to master the basic knowledge of gravity and professional terms at the same time, but due to the lack of necessary physics foundation, they encounter difficulties in understanding the basic concepts of gravity potential field. As the course deepens, students' confusion deepens when it comes to gravity anomaly calculation and data processing methods. In the practical link, when these students try to use gravimeters for field measurements, due to insufficient understanding of basic concepts, they cannot accurately judge the rationality of the measurement results, and it is difficult to find and correct errors in the measurement process. In this case, even if the teacher finds the problem, it is difficult to accurately locate the specific knowledge blind spots of each student, and it is even more impossible to make up for their shortcomings in basic physical knowledge in a targeted manner.

[0066] In a typical geophysics teaching scenario, such as a gravity exploration practice course, students need to use a CG-5 gravimeter for field measurements. The measurement process includes three main steps: instrument setup, data acquisition, and preliminary processing. Among them, the instrument setup stage involves parameter settings such as horizontal adjustment, temperature compensation, and tidal correction of the gravimeter. The data acquisition stage requires students to understand the basic principles of gravity measurement, operate the instrument correctly, and record data. The preliminary processing stage requires students to correct the raw data and perform simple anomaly calculations.

[0067] However, due to students' insufficient understanding of basic physical concepts, the following problems often occur in practice: First, during the instrument setting stage, students cannot accurately understand the physical meaning of temperature compensation and tidal correction, resulting in incorrect parameter settings. Secondly, during the data collection process, due to the lack of understanding of the spatial variation characteristics of the gravity field, students may ignore the importance of measuring point selection, resulting in the collected data being unable to accurately reflect the underground structure. Finally, during the data processing stage, it is difficult for students to correctly interpret the physical nature of the phenomenon, resulting in large deviations in the correction results. These problems directly affect the accuracy and reliability of the measurement results, making it difficult for the entire practical teaching process to achieve the expected results.

[0068] If these technical problems cannot be effectively solved, a series of serious consequences will occur. First, the erroneous cognition accumulated by students in gravity exploration practice will affect their understanding of the entire subject and form an erroneous knowledge structure. Secondly, due to the inability to accurately judge the rationality of the measurement results, students may make incorrect geological interpretations in future practical work, affecting the accuracy of exploration decisions. In addition, if this problem persists, it will reduce teaching efficiency and increase the workload of teachers. In the long run, this may lead to a decline in the quality of trained geophysical professionals and fail to meet the industry's demand for high-quality talents. Therefore, there is an urgent need for a teaching assistance system that can automatically identify students' knowledge blind spots, dynamically associate basic physical concepts with professional knowledge, and provide personalized progressive question-and-answer sessions to improve the effectiveness of gravity exploration teaching in geophysics majors.

[0069] In the teaching of geophysics majors, especially when teaching the course of gravity exploration principles to freshmen with weak physics foundation, there are often many challenges. Students need to master the basic knowledge of gravity and professional terminology at the same time, but due to the lack of necessary physics foundation, they have difficulty in understanding the basic concepts of gravity potential field. As the course progresses, students' confusion deepens when it comes to gravity anomaly calculations and data processing methods. In the practical stage, when these students try to use gravimeters for field measurements, due to insufficient understanding of basic concepts, they cannot accurately judge the rationality of the measurement results, and it is difficult to find and correct errors in the measurement process.

[0070] To solve these problems, the present invention first considers building a knowledge graph system to associate gravity exploration expertise with basic physics knowledge. This method can help students establish connections between knowledge, but only static knowledge graphs may not meet the needs of personalized teaching.

[0071] Therefore, the present invention further considers how to use this knowledge graph to analyze students' learning situation. One possible solution is to construct a student learning trajectory graph based on the knowledge graph. This dynamic graph can reflect the student's learning process, but it still lacks the ability to diagnose students' specific problems.

[0072] In order to accurately identify students' knowledge blind spots, the present invention proposes to analyze students' answer data based on the learning trajectory map and generate a knowledge blind spot diagnosis report. This method can accurately locate each student's specific knowledge blind spots, but how to effectively make up for these blind spots remains a challenge.

[0073] To address this problem, the present invention considers generating a progressive interpretation path from basic physics to professional knowledge based on the knowledge blind spot diagnosis report. This method can provide students with a personalized learning path, but how to ensure the pertinence and effectiveness of the learning content still needs further consideration.

[0074] In order to improve the pertinence of learning content, the present invention proposes to generate supplementary learning content based on a progressive explanation path. This method can provide students with tailored learning materials, but how to evaluate the effectiveness of this teaching method remains a problem.

[0075] Finally, in order to evaluate the teaching effect and continuously improve it, the present invention proposes tracking and analyzing the test performance of students after supplementary learning and evaluating the effect of answering questions. This method can form a closed-loop teaching auxiliary system and continuously optimize the teaching effect.

[0076] Embodiment 1

[0077] Figure 1 is a flow chart of a geophysical teaching auxiliary method based on knowledge graph in the first embodiment of the present invention, such as Figure 1 As shown, embodiment 1 provides a geophysical teaching auxiliary method based on knowledge graph, including:

[0078] Step S100, obtaining the correlation map information of gravity exploration professional knowledge and basic physics knowledge;

[0079] Specifically, the association graph information refers to the connection and dependency between gravity exploration expertise and basic physics knowledge, which can be expressed by indicators such as the association strength, usage frequency and dependency between knowledge points. Specifically, by analyzing the content of textbooks, expert knowledge and subject system, the association relationship between knowledge points is established. The association strength can be quantified by calculating the co-occurrence frequency of knowledge points, semantic similarity and other methods. Among them,

[0080] Step S200, constructing a student's learning trajectory map according to the associated map information;

[0081] Specifically, the learning trajectory map refers to a personalized knowledge network constructed on the basis of the association map based on the students' learning behavior and performance. It can be generated using data such as students' answer records, learning progress, and knowledge mastery. Specifically, by recording and analyzing students' learning behaviors, such as course learning progress, homework completion, and test scores, a personalized knowledge network is generated on the basis of the association map. The learning trajectory map reflects the students' actual learning path and knowledge mastery in the knowledge map.

[0082] Step S300, analyzing the student's answer data based on the learning trajectory graph to generate a knowledge blind spot diagnosis report;

[0083] Specifically, the knowledge blind spot diagnosis report refers to the analysis of students' answer data to identify students' understanding defects and misconceptions on specific knowledge points. It can be generated by error rate analysis, answer time statistics, and knowledge point correlation analysis. Specifically, by conducting in-depth analysis of students' answer data, including error rate statistics, answer time analysis, and knowledge point correlation analysis, students' understanding defects and misconceptions on specific knowledge points can be identified. The diagnostic report not only points out knowledge blind spots, but also provides possible reasons for the formation of blind spots and related basic knowledge gaps.

[0084] Step S400, generating a progressive interpretation path from basic physics to professional knowledge according to the knowledge blind spot diagnosis report;

[0085] Specifically, the progressive explanation path refers to the gradual transition and explanation process from basic physics knowledge to professional knowledge, which can be constructed by sorting the correlation strength of knowledge points and the progressive difficulty. Specifically, by analyzing the correlation between knowledge blind spots and basic physics knowledge, a knowledge chain from basic to professional is constructed. The generation of the explanation path takes into account the correlation strength between knowledge points, the progressive difficulty and the cognitive characteristics of students to ensure the coherence and effectiveness of the learning process.

[0086] Step S500, generating supplementary learning content based on the progressive interpretation path;

[0087] Specifically, supplementary learning content refers to targeted learning materials generated based on students' knowledge blind spots and progressive interpretation paths, which can be presented in the form of automatically generated text explanations, chart examples, and interactive exercises. Specifically, based on the interpretation path, targeted learning materials are automatically generated, including text explanations, chart examples, interactive exercises, etc. The generated content fully considers the students' knowledge base and learning style, ensuring the pertinence and effectiveness of supplementary learning.

[0088] Step S600, tracking and analyzing the test performance of students after supplementary learning, and evaluating the effect of answering questions;

[0089] Specifically, by setting targeted test questions, we can evaluate the students’ knowledge mastery after supplementary learning. The evaluation results are used to adjust the learning trajectory map and optimize the supplementary learning content, forming a closed-loop teaching assistance system.

[0090] Based on the above analysis, the present invention realizes accurate diagnosis of students' knowledge blind spots and generation of personalized learning paths by constructing association map information and learning trajectory maps. This method can not only dynamically associate basic physical concepts with professional knowledge, but also provide progressive explanations and targeted supplementary learning content, thereby effectively improving the effect of gravity exploration teaching in geophysics majors.

[0091] In a specific embodiment, the present invention can be applied in the gravity exploration course of geophysics major. Specifically, first, a correlation map containing basic knowledge of gravity (such as the law of universal gravitation, gravity field theory) and professional knowledge of gravity exploration (such as gravity anomaly, Bouguer correction) is constructed. For example, the correlation strength between the basic physical concept of "gravity field" and the professional concept of "gravity anomaly" may be set to 0.8 (full score is 1). Then, the system records the performance of students in the course learning process, including classroom test scores, homework completion status, and practical operation scores. For example, student A scored 70% in the test related to "gravity field", but only 50% in the homework related to "gravity anomaly". Based on these data, the system constructs a personalized learning trajectory map for student A. Then, the system analyzes the answer data of student A and finds that he has difficulty in understanding the concept of "gravity anomaly". The knowledge blind spot diagnosis report generated by the system points out that student A's basic understanding of "gravity field" is insufficient, which makes it difficult to accurately grasp the physical essence of "gravity anomaly". Based on this diagnosis, the system generates a progressive interpretation path from "gravity field" to "gravity anomaly". This path may include the following steps: (1) the definition and characteristics of the gravity field; (2) the spatial variation of the gravity field; (3) the difference between the ideal gravity field and the actual gravity field; (4) the definition and physical meaning of the gravity anomaly. The system then generates targeted supplementary learning content, including a visualization diagram of the gravity field, an example of the calculation of gravity anomaly, and a series of interactive exercises from easy to difficult. For example, an interactive gravity field simulator is provided to allow students to observe the changes in the gravity field by adjusting parameters, thereby deepening their understanding of the concept of gravity anomaly. Finally, the system evaluates the learning effect of student A through a targeted test. The test questions may include identifying the characteristics of gravity anomalies under different geological structures, calculating the gravity anomaly values ​​under given conditions, etc. Based on the test results, the system will further adjust the learning trajectory map of student A and optimize future supplementary learning content. In this way, the technical solution of the present invention can provide personalized learning support for each student and effectively improve the effect of gravity exploration teaching in geophysics majors.

[0092] In this embodiment, step S400 includes:

[0093] Step S401, obtaining knowledge point missing information in the knowledge blind spot diagnosis report;

[0094] Specifically, the missing information of these knowledge points includes, for example, students' understanding deviation or insufficient grasp of certain basic physical concepts or professional knowledge points. For example, students may not have a clear understanding of the basic concept of gravity field, or have difficulties in calculating gravity anomaly.

[0095] Step S402, extracting corresponding basic physics knowledge points and professional knowledge points from the associated graph information according to the knowledge point missing information;

[0096] Specifically, the association map information is a knowledge network that includes gravity exploration expertise and basic physics knowledge, which contains the association relationship between various knowledge points. For example, if students have difficulty understanding the calculation of gravity anomalies, the system will extract the related basic physics knowledge points (such as the law of gravity, the concept of potential energy) and professional knowledge points (such as Bouguer anomaly, terrain correction, etc.).

[0097] Step S403, calculating the correlation strength between the basic physics knowledge points and the professional knowledge points to obtain correlation strength data;

[0098] Specifically, the calculation of association strength can be based on multiple factors, such as the similarity between knowledge points, the degree of association of usage frequency, and the dependency between knowledge points, etc. For example, the law of gravity and the calculation of gravity anomaly may have a high association strength because the former is the theoretical basis of the latter.

[0099] Step S404, sorting the basic physics knowledge points and professional knowledge points according to the association strength data to generate a knowledge point sequence;

[0100] Specifically, based on the calculated correlation strength data, the basic physics knowledge points and professional knowledge points are sorted to generate a knowledge point sequence. This sequence reflects the progressive relationship of knowledge from basic to professional. For example, the sequence may start from the basic law of gravity, gradually transition to the concept of gravity potential field, then the definition of gravity anomaly, and finally to the complex gravity anomaly calculation method.

[0101] Step S405, generating the progressive interpretation path based on the knowledge point sequence;

[0102] Specifically, this path will serve as a personalized learning guide for students, guiding them to gradually transition from the basic knowledge they have mastered to more complex professional knowledge. For example, the path may first review the law of gravity, then explain the concept of gravitational potential field, then introduce the definition and significance of gravity anomaly, and finally explain in detail the calculation method and application of gravity anomaly.

[0103] Based on the above analysis, the present invention accurately locates students' knowledge missing points by analyzing the knowledge blind spot diagnosis report, and uses the association map information to establish the connection between basic physics knowledge and professional knowledge. By calculating the association strength between knowledge points, the closeness of the relationship between knowledge points can be determined, thereby generating a progressive learning path from basic to professional. This method can provide students with personalized learning guidance and help them gradually build a complete knowledge system.

[0104] In a specific embodiment, the present invention first uses natural language processing technology to analyze the knowledge blind spot diagnosis report, extract keywords and concepts, and determine the students' knowledge missing points. Then, the graph database is used to store and query the associated graph information to quickly locate and extract relevant knowledge points. The calculation of the association strength can use a machine learning algorithm, such as PageRank or TextRank, to consider the multidimensional relationship between knowledge points. The knowledge point sorting can use a topological sorting algorithm to ensure the logic and coherence of the learning path. Finally, the template generation technology can be used to automatically generate a personalized progressive interpretation path based on the sorted knowledge point sequence. This method has significant advantages over traditional fixed teaching content and progress. It can accurately identify each student's knowledge blind spots, provide personalized learning paths, and help students establish a coherent understanding from basic physics to professional knowledge. This not only improves learning efficiency, but also enhances students' learning interest and confidence. In addition, by dynamically constructing knowledge associations, the method can adapt to the learning needs and progress of different students and achieve true teaching in accordance with their aptitude. Compared with the prior art, the method of the present invention has obvious advantages in the following aspects: First, it uses knowledge graph technology to capture the complex relationship between knowledge points more comprehensively and accurately, rather than just a simple linear relationship. Secondly, by calculating the strength of association between knowledge points, the learning path can be determined more accurately, avoiding knowledge jumps or duplications that may occur in traditional methods. Furthermore, this method is dynamic and adaptive, and can adjust the learning path in real time according to the actual situation of the students, rather than adopting a preset fixed path. Finally, this method helps students establish a more systematic and in-depth understanding by closely combining basic physics knowledge with professional knowledge, solving the problem of disconnection between basic knowledge and professional knowledge in traditional teaching.

[0105] In this embodiment, step S403 includes:

[0106] Step S4031, obtaining the similarity coefficient, usage frequency correlation coefficient and dependency coefficient of the basic physics knowledge point and the professional knowledge point;

[0107] Specifically, the similarity coefficient reflects the degree of similarity between two knowledge points in terms of concepts and content. For example, the two knowledge points of "gravity field" and "electric field" have certain similarities in physics concepts. They both belong to the category of field and may have a higher similarity coefficient. The frequency of use correlation coefficient indicates the frequency of two knowledge points appearing at the same time or citing each other during the teaching and learning process. For example, when explaining "gravity anomaly", it is often necessary to refer to the concept of "gravitational acceleration", and the frequency of use correlation coefficient between these two knowledge points may be high. The dependency coefficient reflects the degree of dependence of one knowledge point on another knowledge point. For example, the understanding and calculation of "Bouguer anomaly" heavily relies on the concept of "free air anomaly", so the dependency coefficient between these two knowledge points may be very high.

[0108] Step S4032, obtaining preset weight coefficients, wherein the weight coefficients include a similarity weight coefficient, a usage frequency weight coefficient, and a dependency weight coefficient;

[0109] Specifically, by introducing weight coefficients, the present invention can flexibly adjust the importance of various factors according to different teaching scenarios and goals. For example, in the teaching stage that emphasizes concept understanding, the similarity weight coefficient can be appropriately increased; while in the stage that focuses on practical application, the proportion of the frequency of use weight coefficient can be increased.

[0110] Step S4033, calculating the association strength data between the basic physics knowledge points and the professional knowledge points according to the similarity coefficient, the usage frequency association coefficient, the dependency coefficient and the corresponding weight coefficient;

[0111] Specifically, in order to calculate the association strength data, the present invention adopts a weighted summation method. The specific formula can be expressed as:

[0112] Association strength = α*similarity coefficient + β*frequency of use association coefficient + γ*dependence coefficient

[0113] Among them, α, β, and γ are the similarity weight coefficient, the usage frequency weight coefficient, and the dependency weight coefficient, respectively, and α+β+γ=1.

[0114] The advantage of this calculation method is that it can comprehensively consider multiple influencing factors and adapt to different teaching needs by adjusting the weights. For example, when α = 0.3, β = 0.3, and γ = 0.4, it means that when calculating the association strength, the influence of dependency is slightly greater than the influence of similarity and frequency of use.

[0115] Furthermore, the present invention can also dynamically adjust these weight coefficients according to the actual teaching effect. For example, by analyzing the learning performance and feedback of students, it can be found that in the learning of certain knowledge points, the similarity factor has a greater impact on students' understanding, so the value of α can be increased accordingly. This dynamic adjustment mechanism enables the calculation of association strength to be continuously optimized and better meet the learning needs of students.

[0116] Based on the above analysis, the present invention achieves accurate calculation of the association strength between basic physics knowledge points and professional knowledge points by introducing coefficients of multiple dimensions and corresponding weights. This method takes into account the similarity, usage frequency and dependency between knowledge points, making the calculation of association strength more comprehensive and accurate.

[0117] In a specific embodiment, the present invention can set an initial weight configuration, such as α=0.4, β=0.3, γ=0.3. Then, through the machine learning algorithm, the student's learning data and test results are analyzed to automatically adjust these weight coefficients. For example, if it is found that the student performs well in understanding similar concepts, but has difficulties in applying frequently used knowledge points, the system may gradually adjust the weights to α=0.35, β=0.4, γ=0.25 to strengthen the influence of the frequency of use factor. Therefore, the present invention not only provides a method for accurately calculating the association strength of knowledge points, but also realizes a mechanism for dynamically optimizing calculation parameters according to actual teaching effects. Compared with the traditional calculation method of fixed weights or single factors, this method can more accurately reflect the actual degree of association between knowledge points, thereby laying the foundation for building a more reasonable learning path and providing more targeted teaching content. Compared with the prior art, the method of the present invention has the following advantages: it takes into account the association factors of multiple dimensions instead of relying solely on a single indicator, which makes the calculation of association strength more comprehensive and accurate. By introducing adjustable weight coefficients, the method has higher flexibility and adaptability, and can be adjusted according to different teaching needs and student characteristics. This method supports dynamic optimization and can continuously improve the calculation parameters according to the actual teaching effect, which is a feature that traditional fixed algorithms do not have. This precise correlation strength calculation method provides a more reliable data basis for subsequent learning path planning and personalized teaching, which helps to improve the effect of the entire teaching assistance system.

[0118] In this embodiment, step S4033 includes:

[0119] Step S40331, obtaining historical data of the similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient;

[0120] Specifically, these historical data can come from students' learning records, answering situations, and teachers' teaching feedback. For example, the frequency of students' inquiries about related basic physics concepts when learning a certain knowledge point in the past period of time can be counted as historical data of the usage frequency correlation coefficient.

[0121] Step S40332, normalizing the historical data to obtain a normalization coefficient;

[0122] Specifically, the standardization process can adopt a variety of methods, such as minimum-maximum normalization or Z-score normalization. The purpose of this step is to eliminate the dimensional differences between different coefficients so that they can be compared and calculated on the same scale.

[0123] Step S40333, calculating adjustment parameters of each weight coefficient according to the normalization coefficient;

[0124] Specifically, a machine learning algorithm, such as a gradient descent method, can be used to optimize the adjustment parameters. The calculation of the adjustment parameters needs to consider the distribution characteristics, change trends, and correlation with the learning effect of the standardized coefficients.

[0125] Step S40334, updating the weight coefficient based on the adjustment parameter;

[0126] Specifically, the updating process may use methods such as linear interpolation or nonlinear function mapping to ensure that the updated weight coefficients still satisfy the constraint that the sum is 1.

[0127] Step S40335, performing weighted calculation on the updated weight coefficient and the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient to obtain the correlation strength data;

[0128] Specifically, this step can be implemented through matrix operations to improve computational efficiency.

[0129] Based on the above analysis, it can be seen that through this dynamic adjustment method, the present invention can more accurately capture the correlation between knowledge points, thereby generating a progressive interpretation path that better meets the actual needs of students. This not only helps to improve learning efficiency, but also can better adapt to the learning characteristics and progress of different students.

[0130] In a specific embodiment, an initial weight coefficient distribution can be set, such as similarity weight coefficient α = 0.4, frequency of use weight coefficient β = 0.3, and dependency weight coefficient γ = 0.3. Before calculating the association strength data each time, the system will calculate the standardization coefficient and adjustment parameter based on the learning data of the recent period (such as the past week). Assuming that the calculated adjustment parameters are Δα = 0.05, Δβ = -0.02, and Δγ = -0.03, the updated weight coefficients are α' = 0.45, β' = 0.28, and γ' = 0.27. This dynamic adjustment mechanism can adaptively adjust the weights of each factor according to the student's learning situation. For example, if it is found that students rely more on analogies of similar concepts when understanding certain knowledge points, the system will appropriately increase the similarity weight coefficient; conversely, if it is found that students are more likely to master related concepts by frequently using certain knowledge points, the system will increase the frequency of use weight coefficient. Compared with the prior art, the present invention can adjust the weight coefficient in real time according to the student's learning progress and individual differences, so that the generated progressive interpretation path is more personalized and effective. By introducing historical data and standardizing processing, the weight adjustment is made more objective and accurate, avoiding the deviation that may be caused by subjective settings. The use of methods such as matrix operations can quickly process large amounts of data and is suitable for real-time teaching assistance systems. Each weight adjustment has clear data support and calculation process, which makes it easier for teachers to understand and analyze students' learning characteristics.

[0131] In this embodiment, step S40335 includes:

[0132] Obtaining a preset association strength threshold;

[0133] Specifically, the acquisition of the association strength threshold can be achieved in a variety of ways. For example, a fixed threshold, such as 0.5 or 0.6, can be set based on historical data analysis; the threshold can also be dynamically adjusted based on the distribution of current data, such as taking the median or a specific percentile of the data. In addition, machine learning methods can also be used to automatically determine the optimal threshold by training the model.

[0134] Perform weighted calculation on the updated weight coefficient and the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient to obtain initial correlation strength data;

[0135] Specifically, linear weighting can be expressed as: initial association strength = w1*similarity coefficient + w2*usage frequency association coefficient + w3*dependence coefficient, where w1, w2, and w3 are the corresponding updated weight coefficients. Nonlinear weighting can be transformed using exponential functions or logarithmic functions to better capture the nonlinear relationship between coefficients.

[0136] comparing the initial association strength data with the association strength threshold;

[0137] Specifically, in the process of comparing the initial correlation strength data with the threshold, a tolerance range can be introduced, such as setting an error band of ±5%. This can avoid data misjudgment caused by minor errors and improve the stability of the algorithm. For data close to the threshold, fuzzy logic processing can be used to assign a value between 0 and the original value instead of simply binarizing it.

[0138] When the initial association strength data is greater than the association strength threshold, retaining the initial association strength data;

[0139] When the initial association strength data is less than or equal to the association strength threshold, setting the initial association strength data to zero;

[0140] Specifically, the operation of setting the initial correlation strength data to zero is actually a data noise reduction process. This processing method can effectively remove weak correlations or false correlations that may be caused by noise, thereby improving the accuracy of subsequent analysis. However, in some cases, completely setting the data to zero may lose some potentially useful information. Therefore, you can consider setting a very small non-zero value (such as 0.01) instead of zero to retain weak but potentially meaningful correlations.

[0141] taking the retained initial association strength data and the initial association strength data set to zero as the final association strength data;

[0142] Specifically, in the process of generating the final association strength data, a data normalization step can be introduced. For example, the maximum and minimum normalization or Z-score normalization can be used to map the data to [0,1] or a distribution with a mean of 0 and a standard deviation of 1. This makes the association strengths between different knowledge points comparable, which is convenient for subsequent analysis and application.

[0143] Based on the above analysis, it can be seen that the technical solution of the present invention effectively improves the calculation accuracy of the association strength data by introducing the association strength threshold and data processing strategy. Specifically, the preset association strength threshold provides an objective standard for data screening and reduces the error caused by subjective judgment. The process of weighted calculation of the initial association strength data comprehensively considers multiple factors such as similarity, frequency of use and dependence, thereby improving the comprehensiveness and accuracy of the data. By comparing with the threshold and performing data screening, weak correlation and noise data are effectively removed, thereby improving data quality. Special processing (such as setting it to zero) is performed on data below the threshold to further reduce the impact of noise. The association strength data set finally generated not only retains significant correlation information, but also minimizes the interference of irrelevant data, thereby significantly improving the calculation accuracy.

[0144] In a specific embodiment, the present invention can be applied in a geophysical teaching system as follows: First, the system presets the association strength threshold value to be 0.6. Then, for the two knowledge points of "gravity anomaly" and "free air correction", their similarity coefficient is calculated to be 0.7, the usage frequency association coefficient is 0.8, and the dependency coefficient is 0.9. Assuming that the updated weight coefficients are 0.3, 0.3, and 0.4, respectively, the initial association strength data is calculated as: 0.3*0.7+0.3*0.8+0.4*0.9=0.81. Since 0.81 is greater than the preset threshold value of 0.6, this initial association strength data is retained. In contrast, for the two knowledge points of "gravity anomaly" and "seismic wave", if the calculated initial association strength data is 0.45, since it is less than the threshold value of 0.6, the system will set it to zero. Finally, the system will combine all the retained and set to zero association strength data to form an accurate association strength data set for subsequent knowledge graph construction and learning path generation.

[0145] In this embodiment, the comparing the initial association strength data with the association strength threshold comprises: obtaining a numerical range of the initial association strength data; dividing the initial association strength data into a plurality of intervals according to the numerical range; calculating the data distribution density in each of the intervals; determining a data cluster center based on the data distribution density; using the data cluster center as a reference benchmark, normalizing the initial association strength data to obtain normalized data; and numerically comparing the normalized data with the association strength threshold;

[0146] Specifically, in practical applications, appropriate algorithms and parameters can be flexibly selected according to specific data characteristics and application requirements. For example, when the data distribution shows obvious multi-peak characteristics, the Gaussian mixture model can be considered to determine the cluster center. When there are outliers in the data, the median and interquartile range can be used instead of the mean and standard deviation for normalization. The association strength data processed by this method can better reflect the relative degree of association between knowledge points, and help generate a more reasonable and effective progressive interpretation path. At the same time, this method also improves the system's adaptability to different data distribution characteristics, and enhances the robustness and versatility of the teaching auxiliary system.

[0147] In a specific embodiment, assume that the initial correlation strength data obtained by the system ranges from 0 to 1. First, the system divides this range into 10 intervals, namely [0, 0.1), [0.1, 0.2), …, [0.9, 1]. Then, the system calculates the number of data points in each interval and divides it by the total amount of data to obtain the data distribution density of each interval. Next, the system uses the K-means algorithm to cluster these density data with the midpoint of the interval as the initial cluster center, and finally determines 3 cluster centers, which are located at 0.2, 0.5 and 0.8 respectively. The system uses these three cluster centers as reference points to perform piecewise linear normalization on the initial correlation strength data. Specifically, for data falling in the interval [0,0.2), the normalization formula is y=x / 0.2; for data falling in the interval [0.2,0.5), the normalization formula is y=1+(x-0.2) / 0.3; for data falling in the interval [0.5,0.8), the normalization formula is y=2+(x-0.5) / 0.3; for data falling in the interval [0.8,1], the normalization formula is y=3+(x-0.8) / 0.2. Finally, the system compares the normalized data with a preset association strength threshold (e.g., 2.5). Association strengths greater than the threshold are considered significant, and the corresponding knowledge point pairs will be given priority in the progressive interpretation path. This method can better adapt to different data distribution characteristics than simple linear normalization or fixed threshold comparison. For example, when most of the association strength data are concentrated in low-value areas, this method can more finely distinguish the differences in low-value areas; when the data presents obvious hierarchical characteristics, this method can more accurately reflect the boundaries between different levels. This helps the system generate a more reasonable and targeted progressive explanation path, thereby improving the teaching assistance effect.

[0148] In this embodiment, the geophysical teaching auxiliary method based on knowledge graph also includes:

[0149] Obtaining the knowledge deficiency type in the knowledge blind spot diagnosis report;

[0150] Specifically, the types of knowledge deficiency may include, for example, unclear basic physical concepts, misunderstanding of professional terms, insufficient mastery of calculation methods, etc.

[0151] Selecting corresponding learning content from a preset supplementary learning resource library according to the type of knowledge deficiency;

[0152] Specifically, according to these types, the system selects corresponding learning content from a pre-established supplementary learning resource library. This resource library may contain various forms of learning materials, such as text explanations, diagrams, video explanations, etc.

[0153] Sorting the knowledge dependency relationship of the learning content based on the association graph information;

[0154] Specifically, this step ensures that the order of presentation of learning content conforms to the logical relationship between knowledge points. For example, before learning the calculation method of gravity anomaly, students need to master the basic concept of gravity potential field. Based on these dependencies, the system arranges the learning content from basic to advanced.

[0155] Generate a learning content sequence according to the sorting result;

[0156] Specifically, after the sorting is completed, the system generates a learning content sequence. This sequence may include multiple knowledge modules, each module targeting a specific knowledge point or skill. For example, for a student who has difficulty using a gravimeter, the learning sequence may include the following: gravity measurement principle, gravimeter structure introduction, operation steps explanation, common error analysis, etc.

[0157] Setting a corresponding exercise group based on the learning content sequence;

[0158] Specifically, these exercises are closely related to the learning content and are designed to help students consolidate their knowledge and test their learning effects. Exercises may include multiple-choice questions, fill-in-the-blank questions, practical questions, etc. to comprehensively assess students' understanding.

[0159] Based on the above analysis, this method can not only provide personalized supplementary learning content, but also ensure the logic and coherence of the learning content, which helps students better understand and master relevant knowledge.

[0160] In a specific embodiment, the present invention can dynamically adjust the sequence of learning content according to the student's learning progress and performance. For example, if a student performs well in the practice of a certain knowledge point, the system may reduce the relevant supplementary content and increase more difficult content. On the contrary, if the student encounters difficulties in a certain link, the system may provide more explanations and exercises. In addition, the system can also combine multimedia technology to provide students with a more intuitive and interactive learning experience. For example, when explaining how to use a gravimeter, a 3D model and a virtual operation interface can be provided to allow students to practice operations in a virtual environment. This approach can not only enhance students' understanding, but also increase their interest in learning.

[0161] By implementing this method, the present invention can effectively solve the problem that it is difficult to provide personalized supplementary learning content for each student's knowledge blind spots in traditional teaching. It not only improves learning efficiency, but also helps students build a more systematic and complete knowledge system. Compared with the prior art, the method of the present invention is more flexible and intelligent, and can dynamically adjust the learning content and sequence according to the actual needs of students, thereby realizing truly personalized teaching.

[0162] In some of the above embodiments, during the implementation of the present invention, there is still a problem of how to efficiently sort the learning content to ensure that students can learn in a reasonable order. In this regard, the present invention further proposes a method for sorting the knowledge dependency relationship of the learning content based on the association graph information. The method first obtains the association strength values ​​between the knowledge points in the association graph information, and these association strength values ​​reflect the closeness of the connection between different knowledge points. Then, a knowledge point dependency matrix is ​​constructed based on these association strength values, and the matrix can clearly show the dependency relationship between the knowledge points. Next, the learning content is topologically sorted based on this knowledge point dependency matrix to determine a reasonable learning order. In the process of topological sorting, a loop may be encountered, which indicates that there are knowledge points with circular dependencies. When a loop is detected in the topological sorting, the system will obtain the mastery evaluation value of each knowledge point in the loop. These evaluation values ​​can be calculated based on factors such as the student's historical learning data and test scores. According to these mastery evaluation values, the system can determine the priority of the knowledge points in the loop and disconnect the dependency relationship of the lowest priority knowledge point in the loop, thereby breaking the circular dependency. Finally, the system will re-execute the topological sorting to obtain the final sorting result of the learning content.

[0163] The core of this method is to use the association graph information and knowledge point dependency to dynamically generate the content order that is most suitable for students to learn. By constructing a knowledge point dependency matrix, the complex relationship between knowledge points can be fully captured. The application of topological sorting ensures that the presentation order of learning content is logical, and students can learn step by step, avoiding the difficulty of understanding caused by the confusion of knowledge point order.

[0164] When dealing with loop problems, it is critical to consider the mastery assessment value. This allows the system to decide how to break the circular dependency based on the student's actual situation, rather than simply making a random choice. For example, if there is a knowledge point in the loop that the student has already mastered well, the system may choose to break the dependency of this knowledge point because the student's need to review this knowledge point is relatively low.

[0165] Specifically, the acquisition of association strength values ​​can be achieved by analyzing textbook content, expert evaluation, or historical teaching data. The knowledge point dependency matrix can be represented in the form of an adjacency matrix, where the values ​​of the matrix elements represent the association strength between the knowledge points. Topological sorting can be implemented using depth-first search (DFS) or the Kahn algorithm. When loops are detected, the Floyd-Warshall algorithm or the Johnson algorithm can be used to identify all loops.

[0166] The calculation of the mastery assessment value can take into account several factors, such as:

[0167] 1. The student's score rate in relevant tests;

[0168] 2. The accuracy of students completing relevant exercises;

[0169] 3. The time invested by students in learning this knowledge point;

[0170] 4. Students’ self-assessment results on this knowledge point;

[0171] These factors can be combined to obtain a mastery assessment value by weighted average. For example: mastery assessment value = 0.4*test score rate + 0.3*practice accuracy rate + 0.2*time investment score + 0.1*self-assessment score. Among them, the weights of each item can be adjusted according to actual teaching experience.

[0172] In a specific embodiment, the present invention can be applied in the gravity exploration course in geophysics teaching. Assume that the following knowledge points need to be sorted: A. Basic concepts of gravity field; B. Principles of gravity measuring instruments; C. Gravity anomaly calculation method; D. Gravity data processing technology; E. Practical application of gravity exploration.

[0173] First, by analyzing the relationship between these knowledge points, a knowledge point dependency matrix is ​​constructed:

[0174] ABCDE

[0175] A 0 1 1 0 0

[0176] B 0 0 1 1 0

[0177] C 0 0 0 1 1

[0178] D 0 0 0 0 1

[0179] E 0 0 0 0 0

[0180] Among them, 1 means there is a dependency, and 0 means there is no dependency.

[0181] After performing topological sorting, the resulting learning order is: A→B→C→D→E.

[0182] This order ensures that students learn the basic concepts first, then gradually delve into instrument principles, calculation methods, data processing, and finally learn practical applications. If a loop is found in the actual situation, such as a circular dependency between C and D, the system will obtain the student's mastery evaluation values ​​for C and D. Assuming that the student's mastery of C is 0.7 and the mastery of D is 0.4, the system will choose to disconnect D's dependency on C because the student has a higher degree of mastery of C and is more suitable as a prerequisite.

[0183] Through this method, the present invention can generate a personalized learning content sequence for each student, ensuring the consistency and efficiency of the learning process. Compared with the traditional fixed learning sequence, this dynamic sorting method is more adaptable to the individual differences and knowledge structure of students, thereby improving the learning effect.

[0184] Based on the above analysis, it can be seen that the present invention can dynamically adjust the learning order according to the students' actual mastery of the knowledge, rather than adopting a fixed learning path; taking into account the knowledge mastery of each student, it provides a truly personalized learning sequence; comprehensively considers the complex relationship between knowledge points through associative graph information, rather than just simple linear dependencies; can handle the problem of circular dependencies between knowledge points to ensure the rationality of the learning order; and this method is not only applicable to geophysics teaching, but can also be extended to the teaching of other subjects, providing new ideas and tools for improving teaching effectiveness and learning efficiency.

[0185] In some of the above embodiments, the present invention still faces the problem of how to accurately quantify the strength of association between knowledge points and the degree of students' mastery of knowledge points during implementation. In this regard, the present invention further proposes a geophysics teaching auxiliary method based on knowledge graph, which involves the calculation of the strength of association between knowledge points and the degree of students' knowledge mastery.

[0186] The method proposed in the present invention first obtains the similarity coefficient S(i,j), the usage frequency correlation coefficient F(i,j) and the dependency coefficient D(i,j) between knowledge points i and j. These coefficients reflect the degree of association between different knowledge points. Then, the correlation strength R(i,j) between knowledge points i and j is calculated according to the formula R(i,j)=α*S(i,j)+β*F(i,j)+γ*D(i,j). Among them, α, β, γ are weight coefficients, and α+β+γ=1. This calculation method comprehensively considers multiple correlation factors between knowledge points and can more accurately reflect the actual relationship between knowledge points. Next, the course test score rate C(k,t), practical operation score T(k,t) and error rate change trend E(k,t) of students for knowledge point k at time t are obtained. These data reflect the students' mastery of knowledge points in different aspects. Then, the student's mastery of knowledge point k at time t is calculated according to the formula P(k,t)=λ*C(k,t)+μ*T(k,t)+ν*E(k,t)*exp(-δt). Among them, λ, μ, ν are weight coefficients, and λ+μ+ν=1, δ is the time decay coefficient, and t is the time variable. This calculation method not only takes into account the student's performance in theory and practice, but also introduces the time decay factor, which can more accurately reflect the student's actual mastery of the knowledge point.

[0187] The present invention achieves accurate quantification of the strength of knowledge point association and students' knowledge mastery by introducing multiple parameters and weight coefficients. Specifically, the calculation of the strength of knowledge point association takes into account three aspects: similarity, frequency of use, and dependence. By adjusting the weight coefficients α, β, and γ, it can flexibly adapt to different teaching scenarios and knowledge characteristics. For example, for some professional knowledge points in gravity exploration, they may be more dependent on basic physical knowledge. In this case, the weight γ of the dependence coefficient can be appropriately increased.

[0188] The calculation of students' knowledge mastery combines three dimensions: course testing, practical operation, and error rate changes, and introduces a time decay factor. This design can comprehensively evaluate students' learning effects. For example, by adjusting the weight coefficients λ, μ, and ν, the importance of theoretical mastery or practical ability can be emphasized according to the characteristics of different knowledge points. The introduction of the time decay factor exp(-δt) reflects the possible forgetting of students' knowledge over time, making the mastery evaluation more in line with the actual learning rules.

[0189] Furthermore, the method of the present invention can be used in combination with the aforementioned knowledge graph and learning trajectory graph. For example, the connection weights between knowledge points in the association graph can be optimized based on the calculated knowledge point association strength R(i,j). At the same time, the student's knowledge mastery P(k,t) can be used to dynamically update the learning trajectory graph to reflect the real-time changes in the student's learning progress.

[0190] In a specific embodiment, assume that in the gravity exploration course, there are two key knowledge points: gravity potential field theory (i) and gravity anomaly calculation method (j). The system first calculates the correlation strength R(i,j) of these two knowledge points. Assume that the similarity coefficient S(i,j) = 0.7, the usage frequency correlation coefficient F(i,j) = 0.8, the dependency coefficient D(i,j) = 0.9, the weight coefficient α = 0.3, β = 0.3, γ = 0.4. Then R(i,j) = 0.3*0.7+0.3*0.8+0.4*0.9 = 0.81. This result shows that there is a strong correlation between the two knowledge points.

[0191] For student A's mastery of gravity anomaly calculation method (k) at t = 30 days, P(k,30), assuming that his course test score rate C(k,30) = 0.8, practical operation score T(k,30) = 0.7, error rate change trend E(k,30) = -0.1 (negative value means the error rate is decreasing), weight coefficient λ = 0.4, μ = 0.4, ν = 0.2, time decay coefficient δ = 0.01. Then P(k,30) = 0.4*0.8 + 0.4*0.7 + 0.2*(-0.1)*exp(-0.01*30) ≈ 0.58. This result shows that student A's mastery of this knowledge point is at a medium level.

[0192] In this way, teachers can accurately understand the degree of correlation between different knowledge points and each student's mastery of each knowledge point. This helps teachers optimize the organization and sequence of teaching content and provide more targeted guidance to students. For example, if it is found that a student has a low mastery of gravity anomaly calculation methods, and this knowledge point is highly related to gravity potential field theory, the teacher can suggest that the student review gravity potential field theory first, and then learn gravity anomaly calculation methods.

[0193] Embodiment 2

[0194] Figure 2 is a schematic diagram of the structure of a geophysical teaching auxiliary system based on knowledge graph in the second embodiment of the present invention, such as Figure 2 As shown, embodiment 2 provides a geophysical teaching auxiliary system based on knowledge graph, including: a first acquisition module 201, a construction module 202, a first generation module 203, a second generation module 204, a third generation module 205 and an evaluation module 206. The first acquisition module 201 is used to obtain the associated graph information of gravity exploration professional knowledge and basic physics knowledge. The construction module 202 is used to construct the student's learning trajectory graph based on the associated graph information. The first generation module 203 is used to analyze the student's answer data based on the learning trajectory graph and generate a knowledge blind spot diagnosis report. The second generation module 204 is used to generate a progressive interpretation path from basic physics to professional knowledge based on the knowledge blind spot diagnosis report. The third generation module 205 is used to generate supplementary learning content based on the progressive interpretation path. And the evaluation module 206 is used to track and analyze the test performance of students after supplementary learning and evaluate the effect of answering questions.

[0195] In this embodiment, the second generation module 204 includes: a first acquisition unit, an extraction unit, a obtaining unit, a first generation unit and a second generation unit. The first acquisition unit is used to obtain the knowledge point missing information in the knowledge blind spot diagnosis report. The extraction unit is used to extract the corresponding basic physics knowledge points and professional knowledge points from the association map information according to the knowledge point missing information. The obtaining unit is used to calculate the association strength between the basic physics knowledge points and the professional knowledge points to obtain association strength data. The first generation unit is used to sort the basic physics knowledge points and professional knowledge points according to the association strength data to generate a knowledge point sequence. The second generation unit is used to generate the progressive interpretation path based on the knowledge point sequence.

[0196] In this embodiment, the obtaining unit includes: a first obtaining subunit, a second obtaining subunit and a calculating subunit. The first obtaining subunit is used to obtain the similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient of the basic physics knowledge point and the professional knowledge point. The second obtaining subunit is used to obtain a preset weight coefficient, and the weight coefficient includes a similarity weight coefficient, a usage frequency weight coefficient and a dependency weight coefficient. The calculating subunit is used to calculate the association strength data between the basic physics knowledge point and the professional knowledge point according to the similarity coefficient, the usage frequency correlation coefficient, the dependency coefficient and the corresponding weight coefficient.

[0197] In this embodiment, the calculation subunit includes: an acquisition subunit, a first acquisition subunit, a calculation subunit, an update subunit and a second acquisition subunit. The acquisition subunit is used to acquire the historical data of the similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient. The first acquisition subunit is used to perform standardization on the historical data to obtain a standardized coefficient. The calculation subunit is used to calculate the adjustment parameters of each weight coefficient based on the standardized coefficient. The update subunit is used to update the weight coefficient based on the adjustment parameter. The second acquisition subunit is used to perform weighted calculation on the updated weight coefficient with the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient respectively to obtain the association strength data.

[0198] In this embodiment, the second obtaining sub-unit includes: an obtaining sub-unit, an obtaining sub-unit, a comparing sub-unit, a retaining sub-unit, a first setting sub-unit and a second setting sub-unit. The obtaining sub-unit is used to obtain a preset association strength threshold. The obtaining sub-unit is used to perform weighted calculation on the updated weight coefficient and the corresponding similarity coefficient, the usage frequency association coefficient and the dependency coefficient to obtain initial association strength data. The comparing sub-unit is used to compare the initial association strength data with the association strength threshold. The retaining sub-unit is used to retain the initial association strength data when the initial association strength data is greater than the association strength threshold. The first setting sub-unit is used to set the initial association strength data to zero when the initial association strength data is less than or equal to the association strength threshold. The second setting sub-unit is used to use the retained initial association strength data and the initial association strength data set to zero as the final association strength data.

[0199] In this embodiment, the comparison of the initial association strength data with the association strength threshold includes: obtaining the numerical range of the initial association strength data; dividing the initial association strength data into multiple intervals according to the numerical range; calculating the data distribution density in each of the intervals; determining the data cluster center based on the data distribution density; using the data cluster center as a reference benchmark to normalize the initial association strength data to obtain normalized data; and numerically comparing the normalized data with the association strength threshold.

[0200] In this embodiment, the geophysical teaching auxiliary system based on knowledge graph also includes: a second acquisition module, a screening module, a sorting module, a fourth generation module and a setting module. The second acquisition module is used to obtain the knowledge missing type in the knowledge blind spot diagnosis report. The screening module is used to filter the corresponding learning content from the preset supplementary learning resource library according to the knowledge missing type. The sorting module is used to sort the knowledge dependency relationship of the learning content based on the associated graph information. The fourth generation module is used to generate a learning content sequence according to the sorting result. The setting module is used to set a corresponding exercise group based on the learning content sequence.

[0201] The various variations and specific examples of the geophysical teaching assistance method based on knowledge graph provided in Example 1 are also applicable to the geophysical teaching assistance system based on knowledge graph provided in this example. Through the above detailed description of a geophysical teaching assistance method based on knowledge graph, those skilled in the art can clearly know the implementation method of a geophysical teaching assistance system based on knowledge graph in this example, so for the sake of brevity of the specification, it will not be described in detail here.

[0202] Embodiment 3

[0203] Figure 3 is a schematic diagram of the structure of an electronic device in Embodiment 3 of the present invention, such as Figure 3 As shown, the third embodiment further provides an electronic device 300 , which may include: a processor 301 and a memory 302 .

[0204] The memory 302 is used to store programs; the memory 302 may include volatile memory (English: volatile memory), such as random-access memory (English: random-access memory, abbreviated: RAM), such as static random-access memory (English: static random-access memory, abbreviated: SRAM), double data rate synchronous dynamic random access memory (English: Double Data Rate Synchronous Dynamic Random Access Memory, abbreviated: DDR SDRAM), etc.; the memory may also include non-volatile memory (English: non-volatile memory), such as flash memory (English: flash memory). The memory 302 is used to store computer programs (such as applications, functional modules, etc. that implement the above method), computer instructions, etc., and the above computer programs, computer instructions, etc. can be partitioned and stored in one or more memories 302. And the above computer programs, computer instructions, data, etc. can be called by the processor 301.

[0205] The above-mentioned computer programs, computer instructions, etc. may be stored in partitions in one or more memories 302 . And the above-mentioned computer programs, computer instructions, etc. may be called by the processor 301 .

[0206] The processor 301 is used to execute the computer program stored in the memory 302 to implement each step of the method involved in the above embodiment.

[0207] For details, please refer to the relevant description in the previous method embodiment.

[0208] The processor 301 and the memory 302 may be independent structures or integrated structures. When the processor 301 and the memory 302 are independent structures, the memory 302 and the processor 301 may be coupled and connected via a bus 303 .

[0209] The electronic device of this embodiment can execute the technical solution in the above method, and its specific implementation process and technical principle are the same, which will not be repeated here.

[0210] Embodiment 4

[0211] Embodiment 4 also provides a computer-readable storage medium, including a computer program and instructions. When the computer program or instructions are executed on a computer, the computer executes the geophysical teaching auxiliary method based on the knowledge graph of any embodiment of the present invention.

[0212] Computer-readable storage media include: USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks, and other media that can store program codes.

[0213] This embodiment also provides a computer program product, which includes: a computer program, which is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0214] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the disclosure of the present invention can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0215] In summary, the geophysical teaching auxiliary method and system based on knowledge graph of the present invention has the following beneficial effects:

[0216] 1. By analyzing students' learning trajectory maps and answer data, the system can accurately identify students' understanding deficiencies and misconceptions on specific knowledge points and generate detailed knowledge blind spot diagnosis reports, which helps teachers quickly locate students' learning difficulties and provide targeted teaching support;

[0217] 2. Based on the knowledge blind spot diagnosis report, the system generates a progressive explanation path from basic physics to professional knowledge. This personalized learning path can help students gradually make up for knowledge deficiencies and establish a complete knowledge system, thereby improving learning effects and learning interests;

[0218] 3. Using knowledge graph technology, the system can dynamically associate basic physics knowledge with professional knowledge to form a knowledge network, which not only helps students understand the inherent connection between knowledge points, but also enhances the systematicness and coherence of knowledge, and helps to cultivate students' comprehensive analysis ability;

[0219] 4. Based on the progressive explanation path, the system generates targeted supplementary learning content, including text explanations, chart examples and interactive exercises, which not only meet the actual needs of students, but also consolidate and expand students' knowledge system and improve learning efficiency;

[0220] 5. By tracking and analyzing students' test performance after supplementary learning, evaluating the effectiveness of question-answering, and dynamically adjusting the learning path and supplementary learning content based on the evaluation results, this closed-loop feedback mechanism helps to continuously optimize teaching results and ensure that students can continue to make progress;

[0221] 6. This method fully considers the individual differences of students and can provide personalized learning support according to the actual situation of each student, which helps to meet the learning needs of different students and improve the overall teaching effect;

[0222] 7. By providing personalized learning paths and targeted supplementary learning content, the system can stimulate students' interest and enthusiasm in learning; at the same time, by continuously tracking and evaluating students' learning performance, the system can provide timely feedback and encouragement to further enhance students' learning motivation;

[0223] 8. It not only improves students' learning outcomes, but also provides teachers with valuable teaching feedback; by analyzing students' learning data and performance, teachers can better understand students' learning needs and teaching difficulties, thereby continuously improving teaching methods and strategies and improving their own professional level.

[0224] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A geophysical teaching auxiliary method based on knowledge graph, characterized in that: include: Obtaining the correlation map information of gravity exploration expertise and basic physics knowledge; Constructing a learning trajectory map of the student according to the association map information; Analyze students' answer data based on the learning trajectory graph to generate a knowledge blind spot diagnosis report; generating a progressive interpretation path from basic physics to professional knowledge according to the knowledge blind spot diagnosis report; generating supplementary learning content based on the progressive interpretation path; Track and analyze students’ test performance after supplementary learning and evaluate the effectiveness of question-answering.

2. The geophysical teaching auxiliary method based on knowledge graph according to claim 1, characterized in that: The stepwise explanation path from basic physics to professional knowledge generated according to the knowledge blind spot diagnosis report includes: Obtaining missing information of knowledge points in the knowledge blind spot diagnosis report; Extracting corresponding basic physics knowledge points and professional knowledge points from the associated graph information according to the knowledge point missing information; Calculating the correlation strength between the basic physics knowledge points and the professional knowledge points to obtain correlation strength data; Sorting the basic physics knowledge points and professional knowledge points according to the association strength data to generate a knowledge point sequence; The progressive interpretation path is generated based on the knowledge point sequence.

3. The geophysical teaching auxiliary method based on knowledge graph according to claim 2, characterized in that: The calculating the correlation strength between the basic physics knowledge points and the professional knowledge points to obtain the correlation strength data includes: Obtaining similarity coefficients, usage frequency correlation coefficients and dependency coefficients of the basic physics knowledge points and the professional knowledge points; Obtaining preset weight coefficients, wherein the weight coefficients include a similarity weight coefficient, a usage frequency weight coefficient, and a dependency weight coefficient; The association strength data between the basic physics knowledge points and the professional knowledge points are calculated according to the similarity coefficient, the usage frequency association coefficient, the dependency coefficient and the corresponding weight coefficient.

4. The geophysical teaching auxiliary method based on knowledge graph according to claim 3 is characterized in that: The calculating the association strength data between the basic physics knowledge points and the professional knowledge points according to the similarity coefficient, the usage frequency association coefficient, the dependency coefficient and the corresponding weight coefficient comprises: Acquiring historical data of the similarity coefficient, the usage frequency correlation coefficient, and the dependency coefficient; Performing standardization processing on the historical data to obtain a standardization coefficient; Calculate adjustment parameters of each weight coefficient according to the normalization coefficient; updating the weight coefficient based on the adjustment parameter; The updated weight coefficient is weightedly calculated with the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient to obtain the correlation strength data.

5. The geophysical teaching auxiliary method based on knowledge graph according to claim 4 is characterized in that: The updated weight coefficient is respectively weighted calculated with the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient to obtain the correlation strength data, which includes: Obtaining a preset association strength threshold; Perform weighted calculation on the updated weight coefficient and the corresponding similarity coefficient, the usage frequency correlation coefficient and the dependency coefficient to obtain initial correlation strength data; comparing the initial association strength data with the association strength threshold; When the initial association strength data is greater than the association strength threshold, retaining the initial association strength data; When the initial association strength data is less than or equal to the association strength threshold, setting the initial association strength data to zero; The retained initial association strength data and the initial association strength data set to zero are used as the final association strength data.

6. The geophysical teaching auxiliary method based on knowledge graph according to claim 5, characterized in that: The comparing the initial association strength data with the association strength threshold comprises: Obtaining a numerical range of the initial correlation strength data; Dividing the initial correlation strength data into a plurality of intervals according to the numerical range; Calculate the data distribution density within each of the intervals; Determining a data cluster center based on the data distribution density; Using the data cluster center as a reference benchmark, normalizing the initial association strength data to obtain normalized data; The normalized data is numerically compared to the association strength threshold.

7. The geophysical teaching auxiliary method based on knowledge graph according to claim 1, characterized in that: Also includes: Obtaining the knowledge deficiency type in the knowledge blind spot diagnosis report; Selecting corresponding learning content from a preset supplementary learning resource library according to the type of knowledge deficiency; Sorting the knowledge dependency relationship of the learning content based on the association graph information; Generate a learning content sequence according to the sorting result; A corresponding exercise question group is set based on the learning content sequence.

8. A geophysical teaching auxiliary system based on knowledge graph, characterized in that: include: The first acquisition module is used to obtain the associated atlas information of gravity exploration expertise and basic physics knowledge; A construction module, used to construct a learning trajectory map of the student according to the associated map information; A first generating module is used to analyze the students' answer data based on the learning trajectory graph to generate a knowledge blind spot diagnosis report; A second generating module is used to generate a progressive interpretation path from basic physics to professional knowledge according to the knowledge blind spot diagnosis report; A third generation module, configured to generate supplementary learning content based on the progressive interpretation path; as well as The evaluation module is used to track and analyze students’ test performance after supplementary learning and evaluate the effectiveness of question answering.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively coupled to the at least one processor; In which, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the geophysical teaching auxiliary method based on knowledge graph described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: It includes a computer program and instructions. When the computer program or the instructions are run on a computer, the computer executes the geophysical teaching auxiliary method based on the knowledge graph as described in any one of claims 1 to 7.

Images