Interactive learning resource management method and system for basic education, computer equipment and medium

Abstract

The invention provides an interactive learning resource management method and system for basic education, computer equipment and a medium, and belongs to the technical field of user learning resource management, and the method comprises the following steps: S1, constructing an initial learning resource knowledge graph of each subject, and testing a user to obtain an initial learning resource knowledge graph of each subject; optimizing the initial learning resource knowledge graph and making a learning plan according to the test result and the forgetting curve; s2, assisting the user in executing the learning plan through AR equipment, and monitoring the learning progress and the learning state of the user; and S3, managing the learning resource knowledge graph through the block chain, and recording the learning plan and the learning progress of the user. By adopting the interactive learning resource management method and system for basic education, the computer equipment and the medium, the use experience and learning enthusiasm of the user can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of user learning resource management, and in particular to an interactive learning resource management method, system, computer equipment and medium for basic education. Background Art

[0002] The field of basic education has always been the focus and difficulty of global education development. With the continuous advancement of information technology, interactive learning resource management methods have gradually become an important direction of education reform. Early learning resource management mainly relied on paper textbooks and teachers' classroom teaching. Although it can meet educational needs to a certain extent, it has significant deficiencies in personalized teaching and resource management. With the development of Internet technology, digital learning resource management systems have emerged. These systems have improved the accessibility and utilization of resources by digitizing learning resources and sharing them online. The rise of knowledge graph technology has brought new opportunities to the field of education. Knowledge graphs can help users build a systematic knowledge system by structured representation of knowledge points and their relationships. However, existing knowledge graph technologies are insufficient in dynamic updates and personalized recommendations, and lack personalization and incentives for users' learning content, and cannot make full use of users' learning data for adaptive adjustments. Summary of the invention

[0003] The purpose of the present invention is to provide an interactive learning resource management method, system, computer device and medium for basic education, which can effectively improve the user experience and learning enthusiasm.

[0004] To achieve the above object, the present invention provides an interactive learning resource management method for basic education, comprising the following steps:

[0005] S1. Build the initial learning resource knowledge graph for each subject, test users, optimize the initial learning resource knowledge graph based on the test results and forgetting curve, and formulate a learning plan;

[0006] S2. Assist users to execute their learning plans through AR devices and monitor their learning progress and status;

[0007] S3. Manage the knowledge graph of learning resources through blockchain and record user learning plans and learning progress.

[0008] Preferably, in step S1, the initial learning resource knowledge graph of each subject is constructed and the user is tested. The specific operations are as follows:

[0009] Collect user information to determine the user's education stage, collect corresponding learning resources according to the user's education stage, and classify the collected learning resources by subject;

[0010] Use NLP technology to segment the classified learning resources, use NER technology to identify knowledge points in the learning resources, and use semantic dependency analysis tools to analyze the semantic relationships of knowledge points. Define knowledge points as knowledge nodes, and define semantic relationships of knowledge points as primitive edges to construct an initial learning resource knowledge graph. Construct a separate initial learning resource knowledge graph for each subject.

[0011] Generate test papers based on the initial learning resource knowledge graph of each subject, and use the test papers to test users on knowledge points of each subject to obtain test results of knowledge points of each subject;

[0012] Among them, the test paper contains all the knowledge nodes in the initial learning resource knowledge graph and the proportion is the same; the test results of each subject knowledge point include the test score, test time and test accuracy of each subject.

[0013] Preferably, in step S1, the initial learning resource knowledge graph is optimized according to the test results and the forgetting curve, and the specific operations are:

[0014] Calculate the user's mastery of knowledge nodes based on the user's test results in each subject:

[0015]

[0016] Among them, M i is the mastery degree of the i-th knowledge node; n i is the number of learning resources in the i-th knowledge node; S ik is the test score of the kth learning resource in the i-th knowledge node;

[0017] Combined with the Ebbinghaus forgetting curve, the user's memory retention rate of knowledge nodes is calculated:

[0018]

[0019] Among them, P i is the user's memory retention rate for the i-th knowledge node; t i is the test time of the user at the i-th knowledge node; τ is the forgetting constant;

[0020] Calculate the user's memory retention rate of all knowledge nodes in the knowledge graph, use the memory retention rate as the weight of the knowledge node in the knowledge graph, and use the average of the weights of two knowledge nodes as the optimized edge of the knowledge node in the knowledge graph to adjust the knowledge node relationship, and add the semantic relationship of the knowledge point in the original edge to the optimized edge of the knowledge node as the remark information;

[0021] The initial learning resource knowledge graph of each subject is optimized to obtain the user-optimized learning resource knowledge graph of each subject, and the user-optimized learning resource knowledge graph of each subject is moved into the three-dimensional space, and the spatial axes of the three-dimensional space are defined as the horizontal axis x, the vertical axis y, and the vertical axis z. The user-optimized learning resource knowledge graph is fixed on the plane formed by the horizontal axis x and the vertical axis y, and the memory retention rate is used as the coordinate of the vertical axis z. According to the memory retention rate, the knowledge nodes in the user-optimized learning resource knowledge graph are represented three-dimensionally, and the knowledge nodes in the user-optimized learning resource knowledge graph are simultaneously colored according to the memory retention rate using a coloring algorithm, and the higher the memory retention rate, the darker the coloring;

[0022] Among them, the user optimized learning resource knowledge graph is represented as a two-dimensional plane.

[0023] Preferably, in step S1, the specific operation of formulating a learning plan is:

[0024] Calculate the user's learning efficiency based on the user's test scores, test time, and test accuracy in each subject:

[0025]

[0026] Among them, E i is the user learning efficiency of the i-th knowledge node; C ik is the test accuracy of the kth learning resource in the i-th knowledge node; t ik is the test time of the kth learning resource in the i-th knowledge node;

[0027] Calculate the rate of change of user learning efficiency:

[0028]

[0029] Among them, R i,i+1 The learning efficiency change rate from the user learning the i-th knowledge node to the i+1-th knowledge node; E i+1 is the learning efficiency of the i+1th knowledge node;

[0030] Sort the user's learning knowledge nodes according to the test time, calculate the learning efficiency change rate in turn, and use the third-order exponential smoothing model to smooth the learning efficiency change rate:

[0031]

[0032] in, is the third-order smoothing value at time t; is the second-order smoothing value at time t-1; is the first-order smoothing value at time t-2; Z t-3 is the learning efficiency change rate at time t-3; α 1, α 2 and α 3 All are smoothing coefficients;

[0033] Set the initial value of the smoothing coefficient, use the training set to train the third-order exponential smoothing model, and optimize the model parameters based on the gradient descent optimization algorithm and mean square error to find the optimal smoothing coefficient;

[0034] Calculate the third-order smoothed value of the learning efficiency change rate of all knowledge nodes to form a curve graph, observe the highest point of the curve graph as the split point, and count the number of knowledge nodes before the split point as the daily learning amount of a single subject;

[0035] Calculate the weight of a single subject based on user learning efficiency and memory retention rate:

[0036]

[0037] Among them, K v is the single subject weight of the vth subject; m is the number of knowledge nodes of the vth subject; R vi，vi+1 is the learning efficiency change rate from the i-th knowledge node to the i+1-th knowledge node of the v-th subject; P vi is the memory retention rate of the ith knowledge node in the vth subject; q is the total number of subjects;

[0038] The daily learning amount of a single subject is weighted and summed according to the weight of the single subject to obtain the user's daily comprehensive learning amount:

[0039]

[0040] Among them, L is the user’s daily comprehensive learning amount; L v is the daily learning amount of the vth subject;

[0041] The memory retention rate of the knowledge nodes in the optimized learning resource knowledge graph of each subject is averaged, and the learning demand weight W of each subject is obtained. i :

[0042]

[0043] Among them, ε is the smoothing value;

[0044] Add up the learning demand weights of all subjects and calculate the proportion of each subject's learning demand weight. Multiply the user's daily comprehensive learning volume by the proportion of each subject's learning demand weight to get the daily learning volume of each subject.

[0045] After obtaining the daily learning volume of each subject, select the knowledge nodes with medium and lowest memory retention rates from the optimized learning resource knowledge graph of each subject, keep the ratio of 1:1 and fill them into the daily learning volume to form a daily learning plan for each subject;

[0046] The single-day study plans of all subjects are integrated to form the user's daily comprehensive study plan, and the order and schedule of the single-day study plan for each subject are adjusted according to the user's preferences.

[0047] Preferably, in step S2, the AR device is used to assist the user in executing the learning plan and monitor the user's learning progress and learning status. The specific operations are:

[0048] After formulating a daily comprehensive learning plan for users, AR devices are used to assist users in executing and adjusting the learning plan. AR devices monitor users' learning progress in real time, and reward and encourage users when they complete their daily learning plan for a subject, forming a single-subject check-in record, and generating a daily learning report after users complete their daily comprehensive learning plan;

[0049] The system collects user physiological data in real time while the user is learning, and judges the user's learning status based on the pre-trained convolutional neural network model. When an abnormal learning status is detected, the user is reminded to suspend the learning plan for a rest, and the rest time is set at half an hour. After the rest time, the user is reminded to continue the learning plan. If the user's learning status is normal within one hour of continued learning, the system continues to assist the user to complete the daily comprehensive learning plan. If the user's learning status is still abnormal within one hour of continued learning, the system recommends that the user suspend the learning plan, and the daily comprehensive learning plan is automatically extended to the next day.

[0050] Preferably, in step S3, the learning resource knowledge graph is managed through the blockchain, and the specific operations are: uploading the user's optimized learning resource knowledge graph to the blockchain for management, and when the AR device assists the user in executing the daily comprehensive learning plan, the user's learning knowledge node information is uploaded to the blockchain in real time, and the blockchain highlights the corresponding knowledge nodes. After the user completes the daily comprehensive learning plan, the knowledge node coloring is updated according to the user's memory retention rate of the knowledge nodes. The blockchain tests the user after completing the daily comprehensive learning plan, and formulates the next daily comprehensive learning plan based on the test results.

[0051] Preferably, in step S3, recording the user's learning plan and learning progress means that the blockchain records the user's learning progress in real time after receiving the user's learning knowledge node information uploaded by the AR device, and generates a learning progress table according to the timestamp. After generating the daily comprehensive learning plan, the blockchain generates a classification according to the user information and stores the daily comprehensive learning plan.

[0052] The present invention also provides an interactive learning resource management system for basic education, including a testing module, an optimization module, a planning module, an auxiliary monitoring module and a management and storage module;

[0053] Among them, the test module is used to determine the user's education stage to generate the initial learning resource knowledge graph for each subject, and to test the user to obtain the test results;

[0054] An optimization module is used to optimize the initial learning resource knowledge graph according to the test results and the forgetting curve to obtain an optimized learning resource knowledge graph for each subject;

[0055] The planning module is used to formulate the user's daily comprehensive learning plan based on the optimized learning resource knowledge graph;

[0056] The auxiliary monitoring module is used to assist users in executing daily comprehensive learning plans, monitor the user's learning progress and learning status in real time, and remind users to study according to the learning status;

[0057] The management storage module is used to manage the user's daily comprehensive learning plan and record the user's learning progress and learning plan.

[0058] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned interactive learning resource management method for basic education when executing the computer program.

[0059] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned interactive learning resource management method for basic education.

[0060] Therefore, the present invention adopts the above-mentioned interactive learning resource management method, system, computer equipment and medium for basic education, and the beneficial technical effects are as follows: the present invention tests users by constructing initial learning resource knowledge graphs for various subjects, obtains optimized learning resource knowledge graphs based on the test results, and formulates daily comprehensive learning plans for users, thereby obtaining knowledge graphs and learning plans that are more in line with the user's personality, and monitors the user's learning progress and learning status in real time, gives rewards and reminders, and effectively improves the user's usage experience and learning enthusiasm. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A flowchart of the interactive learning resource management method for basic education;

[0062] Figure 2 A flowchart for the development and implementation of user learning plans;

[0063] Figure 3 This is a schematic diagram of the structure of an interactive learning resource management system for basic education. DETAILED DESCRIPTION

[0064] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0065] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0066] Embodiment 1

[0067] refer to Figure 1 and Figure 2 This embodiment provides an interactive learning resource management method for basic education, comprising the following steps:

[0068] S1. Build the initial learning resource knowledge graph for each subject, test users, optimize the initial learning resource knowledge graph based on the test results and forgetting curve, and formulate a learning plan;

[0069] Specifically, the initial learning resource knowledge graph of each subject is constructed, and testing of users means collecting user information to determine the user's education stage, collecting corresponding learning resources according to the user's education stage, and classifying the collected learning resources according to the subject;

[0070] Use NLP technology to segment the classified learning resources, use NER technology to identify knowledge points in the learning resources, and use semantic dependency analysis tools to analyze the semantic relationships of knowledge points. Define knowledge points as knowledge nodes, and define semantic relationships of knowledge points as primitive edges to construct an initial learning resource knowledge graph. Construct a separate initial learning resource knowledge graph for each subject.

[0071] A test paper is generated based on the initial learning resource knowledge graph of each subject. The test paper contains all knowledge nodes in the initial learning resource knowledge graph with the same proportion. The test paper is used to test the users' knowledge points in each subject to obtain the test results of each subject. The test results of each subject knowledge point include the test score, test time and test accuracy of each subject.

[0072] By accurately collecting and classifying learning resources, we can ensure the relevance and applicability of learning content and improve learning efficiency. By using NLP technology to segment learning resources, we can accurately identify words or phrases in sentences and improve the accuracy of knowledge point recognition. Using NER technology to identify knowledge points can ensure the accuracy and comprehensiveness of knowledge point extraction. Through semantic dependency analysis, we can construct a semantic relationship network between knowledge points to form a more intuitive and systematic knowledge graph. By constructing the initial learning resource knowledge graph, we can systematically display the knowledge points of each subject and their relationships, which is convenient for users to grasp the knowledge structure as a whole. Generating test papers based on the knowledge graph can comprehensively cover knowledge points and objectively evaluate the user's knowledge mastery. Testing is an important means to evaluate the user's knowledge mastery, and the test results provide a basis for the formulation of personalized learning plans.

[0073] Optimize the initial learning resource knowledge graph based on the test results and the forgetting curve. The specific operations are as follows:

[0074] Calculate the user's mastery of knowledge nodes based on the user's test results in each subject:

[0075]

[0076] Among them, M i is the mastery degree of the i-th knowledge node; n i is the number of learning resources in the i-th knowledge node; S ik is the test score of the kth learning resource in the i-th knowledge node;

[0077] Combined with the Ebbinghaus forgetting curve, the user's memory retention rate of knowledge nodes is calculated:

[0078]

[0079] Among them, P i is the user's memory retention rate for the i-th knowledge node; t i is the test time of the user at the i-th knowledge node; τ is the forgetting constant;

[0080] Calculate the user's memory retention rate of all knowledge nodes in the knowledge graph, use the memory retention rate as the weight of the knowledge node in the knowledge graph, and use the average of the weights of two knowledge nodes as the optimized edge of the knowledge node in the knowledge graph to adjust the knowledge node relationship, and add the semantic relationship of the knowledge point in the original edge to the optimized edge of the knowledge node as the remark information;

[0081] The initial learning resource knowledge graph of each subject is optimized to obtain the user-optimized learning resource knowledge graph of each subject, and the user-optimized learning resource knowledge graph of each subject is moved into the three-dimensional space, and the spatial axes of the three-dimensional space are defined as the horizontal axis x, the vertical axis y, and the vertical axis z. The user-optimized learning resource knowledge graph is fixed on the plane formed by the horizontal axis x and the vertical axis y, and the memory retention rate is used as the coordinate of the vertical axis z. According to the memory retention rate, the knowledge nodes in the user-optimized learning resource knowledge graph are represented three-dimensionally, and the knowledge nodes in the user-optimized learning resource knowledge graph are simultaneously colored according to the memory retention rate using a coloring algorithm, and the higher the memory retention rate, the darker the coloring;

[0082] Among them, the user optimized learning resource knowledge graph is represented as a two-dimensional plane.

[0083] The specific steps for making a study plan are:

[0084] Calculate the user's learning efficiency based on the user's test scores, test time, and test accuracy in each subject:

[0085]

[0086] Among them, E i is the user learning efficiency of the i-th knowledge node; C ik is the test accuracy of the kth learning resource in the i-th knowledge node; t ik is the test time of the kth learning resource in the i-th knowledge node;

[0087] Calculate the rate of change of user learning efficiency:

[0088]

[0089] Among them, R i,i+1 The learning efficiency change rate from the user learning the i-th knowledge node to the i+1-th knowledge node; E i+1 is the learning efficiency of the i+1th knowledge node;

[0090] Sort the user's learning knowledge nodes according to the test time, calculate the learning efficiency change rate in turn, and use the third-order exponential smoothing model to smooth the learning efficiency change rate:

[0091]

[0092] in, is the third-order smoothing value at time t; is the second-order smoothing value at time t-1; is the first-order smoothing value at time t-2; Z t-3 is the learning efficiency change rate at time t-3; α 1 , α 2 and α 3 All are smoothing coefficients;

[0093] Set the initial value of the smoothing coefficient, use the training set to train the third-order exponential smoothing model, and optimize the model parameters based on the gradient descent optimization algorithm and mean square error to find the optimal smoothing coefficient;

[0094] Calculate the third-order smoothed value of the learning efficiency change rate of all knowledge nodes to form a curve graph, observe the highest point of the curve graph as the split point, and count the number of knowledge nodes before the split point as the daily learning amount of a single subject;

[0095] Calculate the weight of a single subject based on user learning efficiency and memory retention rate:

[0096]

[0097] Among them, K v is the single subject weight of the vth subject; m is the number of knowledge nodes of the vth subject; R vi，vi+1is the learning efficiency change rate from the i-th knowledge node to the i+1-th knowledge node of the v-th subject; P vi is the memory retention rate of the ith knowledge node in the vth subject; q is the total number of subjects;

[0098] The daily learning amount of a single subject is weighted and summed according to the weight of the single subject to obtain the user's daily comprehensive learning amount:

[0099]

[0100] Among them, L is the user’s daily comprehensive learning amount; L v is the daily learning amount of the vth subject;

[0101] The memory retention rate of the knowledge nodes in the optimized learning resource knowledge graph of each subject is averaged, and the learning demand weight W of each subject is obtained. i :

[0102]

[0103] Among them, ε is the smoothing value;

[0104] Add up the learning demand weights of all subjects and calculate the proportion of each subject's learning demand weight. Multiply the user's daily comprehensive learning volume by the proportion of each subject's learning demand weight to get the daily learning volume of each subject.

[0105] After obtaining the daily learning volume of each subject, select the knowledge nodes with medium and lowest memory retention rates from the optimized learning resource knowledge graph of each subject, keep the ratio of 1:1 and fill them into the daily learning volume to form a daily learning plan for each subject;

[0106] The single-day study plans of all subjects are integrated to form the user's daily comprehensive study plan, and the order and schedule of the single-day study plan for each subject are adjusted according to the user's preferences.

[0107] By comprehensively testing the accuracy and test time, the user's learning efficiency at different knowledge nodes can be accurately evaluated. This method not only takes into account the user's learning speed, but also the learning accuracy, and provides a comprehensive evaluation of learning effects. By calculating the learning efficiency change rate, the user's learning progress can be dynamically evaluated and the key nodes in the learning process can be identified. The third-order exponential smoothing model can more accurately capture the trend of changes in learning efficiency and reduce the impact of data fluctuations through three levels of smoothing. The single-subject weight of each subject is calculated by the user's learning efficiency change rate and memory retention rate to ensure the scientificity and rationality of the learning plan. The user's daily comprehensive learning volume is calculated by weighted summation to ensure the comprehensiveness and balance of the learning plan. By calculating the comprehensive memory retention rate, the overall learning effect and memory status of each subject can be evaluated, and the learning demand weight of each subject can be determined. By selecting knowledge nodes with medium and lowest memory retention rates, the rationality and effectiveness of the learning plan can be ensured. By integrating the single-day learning plans of various subjects, a comprehensive and personalized daily comprehensive learning plan is formed. The subject order and time arrangement are adjusted according to user preferences to improve the user's learning enthusiasm and participation.

[0108] S2. Assist users to execute their learning plans through AR devices and monitor their learning progress and status;

[0109] The specific operations are:

[0110] After formulating a daily comprehensive learning plan for users, AR devices are used to assist users in executing and adjusting the learning plan. AR devices monitor users' learning progress in real time, and reward and encourage users when they complete their daily learning plan for a subject, forming a single-subject check-in record, and generating a daily learning report after users complete their daily comprehensive learning plan;

[0111] The system collects user physiological data in real time while the user is learning, and judges the user's learning status based on the pre-trained convolutional neural network model. When an abnormal learning status is detected, the user is reminded to suspend the learning plan for a rest, and the rest time is set at half an hour. After the rest time, the user is reminded to continue the learning plan. If the user's learning status is normal within one hour of continued learning, the system continues to assist the user to complete the daily comprehensive learning plan. If the user's learning status is still abnormal within one hour of continued learning, the system recommends that the user suspend the learning plan, and the daily comprehensive learning plan is automatically extended to the next day.

[0112] Through AR devices, users can learn in an immersive environment, which enhances the fun and interactivity of learning. At the same time, AR devices can monitor the user's learning progress in real time to ensure that the execution and adjustment of the learning plan are more accurate and timely. By monitoring the user's learning progress in real time, AR devices can give timely rewards and encouragement when the user completes the learning task, enhancing the user's sense of accomplishment and learning motivation. For example, after the user completes the learning task of mathematics, the system can give points rewards and generate check-in records to help users develop good learning habits. The single-day learning report generated after the daily comprehensive learning plan is completed can summarize the user's learning situation, provide feedback and improvement suggestions, and further In order to improve the learning effect, by collecting the user's physiological data in real time and analyzing it based on the pre-trained convolutional neural network model, the user's learning status can be accurately judged. By monitoring the user's learning status in real time and reminding the user to rest in time when an abnormal situation is detected, learning fatigue can be effectively prevented and learning effect can be improved. For example, when the user shows fatigue signals during the learning process, the system will remind the user to rest for half an hour and continue learning after the rest. This mechanism not only ensures the sustainability of learning, but also improves the user's learning experience and efficiency. By monitoring the user's status in the process of continued learning in real time, the system can dynamically adjust the learning plan to ensure the reasonable allocation and execution of learning tasks.

[0113] S3. Manage the knowledge graph of learning resources through blockchain and record user learning plans and learning progress.

[0114] The learning resource knowledge graph is managed through blockchain. The specific operations are as follows: the user's optimized learning resource knowledge graph is uploaded to the blockchain for management. When the AR device assists the user in executing the daily comprehensive learning plan, the user's learning knowledge node information is uploaded to the blockchain in real time. The blockchain highlights the corresponding knowledge nodes, and simultaneously updates the knowledge node coloring according to the user's memory retention rate of the knowledge nodes after the user completes the daily comprehensive learning plan. The blockchain tests the user after completing the daily comprehensive learning plan and formulates the next daily comprehensive learning plan based on the test results.

[0115] Blockchain technology can ensure the integrity and security of uploaded learning resource knowledge graph data and prevent data from being maliciously tampered with. Through decentralized distributed ledgers, all nodes jointly maintain data, ensuring data transparency and credibility. By uploading users' learning knowledge node information in real time, timely tracking and management of learning progress can be ensured. Blockchain can record users' learning status at each knowledge node in real time, facilitating subsequent adjustment and optimization of learning plans. Highlighting knowledge nodes can intuitively reflect users' learning progress and help users adjust their learning plans in a timely manner. Through visual effects such as color changes, users can see at a glance which knowledge points have been learned and which need further consolidation. By updating the coloring of knowledge nodes, the user's mastery of each knowledge point and memory retention rate can be dynamically reflected. Users can intuitively understand their memory status of each knowledge point through the depth of color, which helps with timely review and consolidation. By dynamically formulating the next daily comprehensive learning plan based on test results, continuous optimization and personalization of learning plans can be ensured.

[0116] Recording user learning plans and learning progress means that after receiving the user learning knowledge node information uploaded by the AR device, the blockchain records the user's learning progress in real time and generates a learning progress table based on the timestamp. After generating a daily comprehensive learning plan, the blockchain generates a classification based on the user information and stores the daily comprehensive learning plan.

[0117] Blockchain technology can ensure the integrity and security of learning progress data. Through decentralized distributed ledgers, all nodes jointly maintain data, ensuring the transparency and credibility of the data. By generating a learning progress chart through a timestamp, timely tracking and management of learning progress can be ensured. Blockchain can record the user's learning status at each knowledge node in real time and generate a learning progress chart with a timestamp to facilitate subsequent adjustment and optimization of the learning plan. By generating and storing daily comprehensive learning plans through blockchain technology, the personalization and security of the learning plan can be ensured. The system can generate a suitable learning plan for each user based on the user's basic information, learning preferences and historical learning data, and classify and manage it to ensure the scientificity and applicability of the plan.

[0118] Embodiment 2

[0119] like Figure 3 As shown, it is a structural diagram of an interactive learning resource management system for basic education of the present invention, including a testing module, an optimization module, a planning module, an auxiliary monitoring module and a management storage module;

[0120] Among them, the test module is used to determine the user's education stage to generate the initial learning resource knowledge graph for each subject, and to test the user to obtain the test results;

[0121] An optimization module is used to optimize the initial learning resource knowledge graph according to the test results and the forgetting curve to obtain an optimized learning resource knowledge graph for each subject;

[0122] The planning module is used to formulate the user's daily comprehensive learning plan based on the optimized learning resource knowledge graph;

[0123] The auxiliary monitoring module is used to assist users in executing daily comprehensive learning plans, monitor the user's learning progress and learning status in real time, and remind users to study according to the learning status;

[0124] The management storage module is used to manage the user's daily comprehensive learning plan and record the user's learning progress and learning plan.

[0125] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0126] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0127] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0128] It should be understood that each part of the present invention can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system.

[0129] Therefore, the present invention adopts the above-mentioned interactive learning resource management method, system, computer device and medium for basic education, which can effectively improve the user's usage experience and learning enthusiasm.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. An interactive learning resource management method for basic education, characterized in that: The following steps are involved: S1. Build the initial learning resource knowledge graph for each subject, test users, optimize the initial learning resource knowledge graph based on the test results and forgetting curve, and formulate a learning plan; S2. Assist users to execute their learning plans through AR devices and monitor their learning progress and status; S3. Manage the knowledge graph of learning resources through blockchain and record user learning plans and learning progress.

2. The interactive learning resource management method for basic education according to claim 1, characterized in that: In step S1, the initial learning resource knowledge graph of each subject is constructed and the user is tested. The specific operations are as follows: Collect user information to determine the user's education stage, collect corresponding learning resources according to the user's education stage, and classify the collected learning resources by subject; Use NLP technology to segment the classified learning resources, use NER technology to identify knowledge points in the learning resources, and use semantic dependency analysis tools to analyze the semantic relationships of knowledge points. Define knowledge points as knowledge nodes, and define semantic relationships of knowledge points as primitive edges to construct an initial learning resource knowledge graph. Construct a separate initial learning resource knowledge graph for each subject. Generate test papers based on the initial learning resource knowledge graph of each subject, and use the test papers to test users on knowledge points of each subject to obtain test results of knowledge points of each subject; Among them, the test paper contains all the knowledge nodes in the initial learning resource knowledge graph and the proportion is the same; the test results of each subject knowledge point include the test score, test time and test accuracy of each subject.

3. The interactive learning resource management method for basic education according to claim 2, characterized in that: In step S1, the initial learning resource knowledge graph is optimized according to the test results and the forgetting curve. The specific operations are as follows: Calculate the user's mastery of knowledge nodes based on the user's test results in each subject: Among them, M i is the mastery degree of the i-th knowledge node; n i is the number of learning resources in the i-th knowledge node; S ik is the test score of the kth learning resource in the i-th knowledge node; Combined with the Ebbinghaus forgetting curve, the user's memory retention rate of knowledge nodes is calculated: Among them, P i is the user's memory retention rate for the i-th knowledge node; t i is the test time of the user at the i-th knowledge node; τ is the forgetting constant; Calculate the user's memory retention rate of all knowledge nodes in the knowledge graph, use the memory retention rate as the weight of the knowledge node in the knowledge graph, and use the average of the weights of two knowledge nodes as the optimized edge of the knowledge node in the knowledge graph to adjust the knowledge node relationship, and add the semantic relationship of the knowledge point in the original edge to the optimized edge of the knowledge node as the remark information; The initial learning resource knowledge graph of each subject is optimized to obtain the user-optimized learning resource knowledge graph of each subject, and the user-optimized learning resource knowledge graph of each subject is moved into the three-dimensional space, and the spatial axes of the three-dimensional space are defined as the horizontal axis x, the vertical axis y and the vertical axis z, respectively. The user-optimized learning resource knowledge graph is fixed on the plane formed by the horizontal axis x and the vertical axis y, and the memory retention rate is used as the coordinate of the vertical axis z. According to the memory retention rate, the knowledge nodes in the user-optimized learning resource knowledge graph are represented three-dimensionally, and the knowledge nodes in the user-optimized learning resource knowledge graph are simultaneously colored according to the memory retention rate using a coloring algorithm, and the higher the memory retention rate, the darker the coloring; Among them, the user optimized learning resource knowledge graph is represented as a two-dimensional plane.

4. The interactive learning resource management method for basic education according to claim 3, characterized in that: In step S1, the specific operations of formulating a learning plan are: Calculate the user's learning efficiency based on the user's test scores, test time, and test accuracy in each subject: Among them, E i is the user learning efficiency of the i-th knowledge node; C ik is the test accuracy of the kth learning resource in the i-th knowledge node; t ik is the test time of the kth learning resource in the i-th knowledge node; Calculate the rate of change of user learning efficiency: Among them, R i,i+1 The learning efficiency change rate from the user learning the i-th knowledge node to the i+1-th knowledge node; E i+1 is the learning efficiency of the i+1th knowledge node; Sort the user's learning knowledge nodes according to the test time, calculate the learning efficiency change rate in turn, and use the third-order exponential smoothing model to smooth the learning efficiency change rate: in, is the third-order smoothing value at time t; is the second-order smoothing value at time t-1; is the first-order smoothing value at time t-2; Z t-3 is the learning efficiency change rate at time t-3; α1, α2 and α3 are all smoothing coefficients; Set the initial value of the smoothing coefficient, use the training set to train the third-order exponential smoothing model, and optimize the model parameters based on the gradient descent optimization algorithm and mean square error to find the optimal smoothing coefficient; Calculate the third-order smoothed value of the learning efficiency change rate of all knowledge nodes to form a curve graph, observe the highest point of the curve graph as the split point, and count the number of knowledge nodes before the split point as the daily learning amount of a single subject; Calculate the weight of a single subject based on user learning efficiency and memory retention rate: Among them, K v is the single subject weight of the vth subject; m is the number of knowledge nodes of the vth subject; R vi，vi+1 is the learning efficiency change rate from the i-th knowledge node to the i+1-th knowledge node of the v-th subject; P vi is the memory retention rate of the ith knowledge node in the vth subject; q is the total number of subjects; The daily learning amount of a single subject is weighted and summed according to the weight of the single subject to obtain the user's daily comprehensive learning amount: Among them, L is the user’s daily comprehensive learning amount; L v is the daily learning amount of the vth subject; The memory retention rate of the knowledge nodes in the optimized learning resource knowledge graph of each subject is averaged, and the learning demand weight W of each subject is obtained. i : Among them, ε is the smoothing value; Add up the learning demand weights of all subjects and calculate the proportion of each subject's learning demand weight. Multiply the user's daily comprehensive learning volume by the proportion of each subject's learning demand weight to get the daily learning volume of each subject. After obtaining the daily learning volume of each subject, select the knowledge nodes with medium and lowest memory retention rates from the optimized learning resource knowledge graph of each subject, keep the ratio of 1:1 and fill them into the daily learning volume to form a daily learning plan for each subject; The single-day study plans of all subjects are integrated to form the user's daily comprehensive study plan, and the order and schedule of the single-day study plan for each subject are adjusted according to the user's preferences.

5. The interactive learning resource management method for basic education according to claim 4, characterized in that: In step S2, the AR device is used to assist the user in executing the learning plan and monitor the user's learning progress and learning status. The specific operations are: After formulating a daily comprehensive learning plan for users, AR devices are used to assist users in executing and adjusting the learning plan. AR devices monitor users' learning progress in real time, and reward and encourage users when they complete their daily learning plan for a subject, forming a single-subject check-in record, and generating a daily learning report after users complete their daily comprehensive learning plan; The system collects user physiological data in real time while the user is learning, and judges the user's learning status based on the pre-trained convolutional neural network model. When an abnormal learning status is detected, the user is reminded to suspend the learning plan for a rest, and the rest time is set at half an hour. After the rest time, the user is reminded to continue the learning plan. If the user's learning status is normal within one hour of continued learning, the system continues to assist the user to complete the daily comprehensive learning plan. If the user's learning status is still abnormal within one hour of continued learning, the system recommends that the user suspend the learning plan, and the daily comprehensive learning plan is automatically extended to the next day.

6. The interactive learning resource management method for basic education according to claim 5, characterized in that: In step S3, the learning resource knowledge graph is managed through the blockchain. The specific operations are: uploading the user's optimized learning resource knowledge graph to the blockchain for management; when the AR device assists the user in executing the daily comprehensive learning plan, the user's learning knowledge node information is uploaded to the blockchain in real time; the blockchain highlights the corresponding knowledge nodes, and simultaneously updates the knowledge node coloring according to the user's memory retention rate of the knowledge nodes after the user completes the daily comprehensive learning plan; the blockchain tests the user after completing the daily comprehensive learning plan, and formulates the next daily comprehensive learning plan based on the test results.

7. The interactive learning resource management method for basic education according to claim 6, characterized in that: In step S3, recording the user's learning plan and learning progress means that the blockchain records the user's learning progress in real time after receiving the user's learning knowledge node information uploaded by the AR device, and generates a learning progress table according to the timestamp. After generating the daily comprehensive learning plan, the blockchain generates a classification according to the user information and stores the daily comprehensive learning plan.

8. A system for implementing the interactive learning resource management method for basic education as claimed in any one of claims 1 to 7, characterized in that: It includes testing module, optimization module, planning module, auxiliary monitoring module and management storage module; Among them, the test module is used to determine the user's education stage to generate the initial learning resource knowledge graph for each subject, and to test the user to obtain the test results; An optimization module is used to optimize the initial learning resource knowledge graph according to the test results and the forgetting curve to obtain an optimized learning resource knowledge graph for each subject; The planning module is used to formulate the user's daily comprehensive learning plan based on the optimized learning resource knowledge graph; The auxiliary monitoring module is used to assist users in executing daily comprehensive learning plans, monitor the user's learning progress and learning status in real time, and remind users to study according to the learning status; The management storage module is used to manage the user's daily comprehensive learning plan and record the user's learning progress and learning plan.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that when the processor executes the computer program, the steps of the interactive learning resource management method for basic education described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the interactive learning resource management method for basic education described in any one of claims 1 to 7 are implemented.

Images