Intelligent teaching resource optimization management system

Abstract

The invention discloses an intelligent teaching resource optimization management system, relates to the technical field of teaching resources, and aims to solve the problem that traditional teaching resource management often lacks a scientific evaluation mechanism. Newly uploaded teaching resources are only simply stored and classified, the content quality of the newly uploaded teaching resources is not deeply classified, knowledge points in the resources may have the problems of errors, outdated time or unclear explanation, but the system cannot automatically recognize and prompt, so that low-quality teaching resources never exist, and the teaching resources cannot be automatically identified and prompted. Through collaborative operation of user management, resource management, an evaluation mechanism and an auditing module, an efficient and scientific closed-loop system is formed, the quality of teaching resources can be remarkably improved, cooperation among teachers is promoted, high-quality and high-applicability teaching resources are provided for students, higher-quality development of education and teaching activities is promoted, and the teaching efficiency is improved. Therefore, the quality and reasonable allocation of resources are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching resources, and in particular to a smart teaching resource optimization management system. Background Art

[0002] With the widespread application of information technology in the field of education, the degree of digitalization of teaching resources has been continuously improved. Educational institutions, schools and teachers have accumulated a large number of teaching resources, including electronic teaching plans, courseware, online course materials, etc. However, these resources vary in quality, applicability and accuracy. On the one hand, teachers need to spend a lot of time screening and modifying appropriate teaching resources during lesson preparation and teaching; on the other hand, students find it difficult to obtain high-quality content that meets their own learning needs when faced with massive resources.

[0003] Traditional teaching resource management often lacks a scientific evaluation mechanism. Newly uploaded teaching resources are simply stored and classified without in-depth analysis of their content quality. Knowledge points in the resources may be wrong, outdated, or unclear, but the system cannot automatically identify and prompt them, which has led to the existence of low-quality teaching resources.

[0004] In view of the above problems, a smart teaching resource optimization management system is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a smart teaching resource optimization management system to solve the problem of low resource quality in the background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: a smart teaching resource optimization management system, comprising:

[0007] User management module: students, teachers, and evaluators register through the user management module, fill in information, and log in to the system using their registered account. The system categorizes students, teachers, and evaluators;

[0008] Resource management module: Teachers upload teaching resources through the resource management module. The resources will be stored in the system and classified according to their subjects and grades. After the resources are successfully uploaded, other teachers can annotate the newly uploaded resources on the teacher side. The annotation content is stored in the corresponding teaching resource document. The uploader of the teaching resource can modify the annotation content and submit the teaching resource for the second time after the modification. The teacher side can still annotate after the second submission;

[0009] Evaluation module: When the number of annotations on teaching resources reaches the preset threshold, the evaluation mechanism is activated. The evaluation mechanism includes content coincidence check, comparing the original text and the modified text, and checking the coincidence of the annotation content and the modified information. The coincidence calculation formula is:

[0010] ,determine the evaluation status of teaching resources according to the overlap results;

[0011] The evaluation status includes: modification fully valid, modification partially valid, modification invalid;

[0012] Coincidence For the modification to be fully effective;

[0013] It is effective for the modified part;

[0014] Coincidence The modification is invalid;

[0015] Review module: For the parts marked as invalid modifications, the uploader of the teaching resources gives corresponding explanations. If the explanation is acceptable, the next process will be entered, otherwise the teaching resources will be returned;

[0016] Crowdsourcing evaluation mode: When the evaluation status is that the modification is fully effective or partially effective, the system automatically enters the crowdsourcing evaluation mode. The system randomly assigns teaching resources to evaluators, who are composed of subject teachers, teaching experts and outstanding students. The evaluators conduct evaluations based on content quality, teaching applicability and clarity of expression within the specified time. The evaluation results are divided into pass or fail. If the proportion of fail is greater than the proportion of pass, the teaching resources are returned. If the proportion of fail is less than the proportion of pass, the teaching resources are open to the public, and students can use them after the public release.

[0017] Preferably, the system extracts the original teaching resource text, the text containing the annotation content, and the modified teaching resource text from the database, compares the content involved in the annotation and the modified information through natural language processing technology and text matching algorithm, uses a similarity calculation method based on word vectors, converts the text into a vector representation, and then calculates the similarity between the vectors.

[0018] Preferably, in the resource management module, resource classification adopts a content-based classification algorithm, and teaching resource documents ; This is the first teaching resource document. This is the second teaching resource document. is the total number of teaching resource documents in the system, the vocabulary set , The first function word, The second function word, is the total number of words in the vocabulary set;

[0019] Constructing the document-term matrix ,in Words to express In the documentation The weight in

[0020] vocabulary In the documentation The word frequency in For vocabulary In the documentation The number of times it appears in .

[0021] Preferably, the inverse document frequency is calculated: ,in is the total number of documents, Contains vocabulary The number of documents; weight calculation, ,in is the word frequency, is the inverse document frequency, through Cluster analysis is performed to classify resources by subject and grade.

[0022] Preferably, in the resource management module, the storage of teaching resources adopts a distributed file system, and each teaching resource file is divided into multiple data blocks and stored on different storage nodes. The size of the teaching resource file is , the data block size is , the number of storage nodes is , then the number of data blocks , Indicates rounding up. The system will round up according to the preset storage strategy. The data blocks are evenly distributed in At the same time, the system creates an index table for each teaching resource, which records the resource's subject, grade, file name, and storage node location information.

[0023] Preferably, the evaluators are composed of 40% subject teachers, 40% education experts and 20% outstanding students, and each teaching resource is evaluated by 3 evaluators; the evaluators score the teaching resources on a scale of 1-10 within a specified time according to the standards of content quality, teaching applicability and clarity of expression, where the weight of content quality is 40%, the weight of teaching applicability is 40%, and the weight of clarity of expression is 20%. The average score is calculated based on the scores of the evaluators, and teaching resources with a score below 6 are marked as needing to be revised.

[0024] Preferably, in the evaluation calculation, The number of subject teachers is , the number of education experts is , the number of outstanding students is ,and , the number of subject teachers to be selected , number of education experts , the number of outstanding students The selection process is achieved by marking the personnel in the evaluation personnel database by type and then randomly selecting them according to the above number.

[0025] Preferably, the multiple dimensions for evaluating the quality of teaching resources include content quality, teaching applicability and clarity of expression, and weights are set for each of them, where the weight of content quality is , teaching suitability weight , clarity of expression weight ,and , collect the scores of subject teachers, teaching experts and outstanding students on each dimension through the crowdsourcing evaluation model, with the score range of 1-10 points. According to the collected scoring data, calculate the average score of teaching suitability , average content quality score , average score of clarity of expression , using the formula , average score of computing resources ,in Used to determine whether the resource needs to be modified.

[0026] Preferably, the evaluation of content quality is based on the accuracy, comprehensiveness and novelty of knowledge points, where the accuracy of knowledge points accounts for 10% of the content quality weight. Proportion, comprehensiveness of knowledge points Proportion, the novelty of knowledge points accounts for Ratio, where , ,and When calculating the content quality score, the knowledge points are scored separately in these three aspects and the total score is calculated in proportion.

[0027] Preferably, the system sets the adjusted score threshold , used to compare with the average score of resources For comparison, When the system automatically marks the teaching resource as needing to be revised, it will send a notification to the resource uploader containing the resource's average score, scores in each dimension, and revision suggestions. The revision suggestions are generated based on the parts with lower scores in each dimension. When the resource is evaluated, it maintains the current state or enters the next process, and the evaluation results are recorded for subsequent analysis.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. The present invention provides a smart teaching resource optimization management system, which forms an efficient and scientific closed-loop system through the coordinated operation of user management, resource management, evaluation mechanism and audit modules. It can significantly improve the quality of teaching resources, promote collaboration among teachers, provide students with high-quality and highly applicable teaching resources, and promote the better development of educational and teaching activities to ensure the quality and reasonable allocation of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flow chart of the present invention;

[0031] Figure 2 This is a diagram for determining the degree of overlap of the contents of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings.

[0034] Combination Figure 1-Figure 2 , a smart teaching resource optimization management system of the present invention comprises:

[0035] User management module: Students, teachers, and evaluators access the user management module and fill in detailed information on the registration interface, such as name, age, contact information, identity (corresponding to students, teachers, and evaluators), and subject. The system checks the format of the input information to ensure that the name length is limited to a certain range and the email format must comply with the specifications. After successful registration, the user logs in to the system using the account and the password set by the user. The system identifies the user's identity based on the account the user logs in to, and loads specific function interfaces for users of different identities, including the resource upload and management related function entrances that teachers can see after logging in, and the list of available teaching resources that students can see after logging in;

[0036] Resource management module: Teachers upload teaching resources through the resource management module. The resources will be stored in the system and classified according to their subjects and grades. The system extracts the original teaching resource text, the text containing the annotation content, and the modified teaching resource text from the database. Through natural language processing technology and text matching algorithm, the content involved in the annotation and the modified information are compared. The similarity calculation method based on word vectors is used to convert the text into vector representation, and then the similarity between vectors is calculated. In the resource management module, resource classification adopts a content-based classification algorithm. Teaching resource documents ; This is the first teaching resource document. This is the second teaching resource document. is the total number of teaching resource documents in the system, the vocabulary set , The first function word, The second function word, is the total number of words in the vocabulary set;

[0037] Constructing the document-term matrix ,in Words to express In the documentation The weight in

[0038] vocabulary In the documentation The word frequency in For vocabulary In the documentation The number of occurrences in , inverse document frequency calculation: ,in is the total number of documents, Contains vocabulary The number of documents; weight calculation, ,in is the word frequency, is the inverse document frequency, through Cluster analysis is performed to classify resources by subject and grade. In the resource management module, the storage of teaching resources adopts a distributed file system, and each teaching resource file is divided into multiple data blocks and stored on different storage nodes. The size of the teaching resource file is , the data block size is , the number of storage nodes is , then the number of data blocks , Indicates rounding up. The system will round up according to the preset storage strategy. The data blocks are evenly distributed in At the same time, the system creates an index table for each teaching resource, which records the resource's subject, grade, file name, and storage node location information.

[0039] After the resource is successfully uploaded, other teachers can annotate the newly uploaded resource on the teacher side. The annotation content is stored in the corresponding teaching resource document. The uploader of the teaching resource can modify the annotation content and submit the teaching resource for the second time after the modification. The teacher side can still annotate after the second submission.

[0040] Other teachers can browse the newly uploaded resource list on the teacher side and click to enter the resource page. They can use annotation tools to make annotations, including highlighting text and adding text box comments. The annotation content will be associated with the resource in real time, stored in a special annotation database, and bound to the specific location information of the resource document (such as document page number, paragraph number). After receiving the annotation notification from other teachers, the teaching resource uploader can check the annotation content, modify the resource locally, and upload it again through the resource management module after the modification is completed. After the second upload, other teachers can continue to annotate, forming a cycle of continuous improvement;

[0041] Evaluation module: When the number of annotations on a teaching resource reaches 10, that is, the preset threshold is reached, the evaluation mechanism is automatically started. The evaluation mechanism includes content coincidence check, comparing the original text and the modified text, and checking the coincidence of the annotation content and the modified information. The coincidence calculation formula is:

[0042] ,determine the evaluation status of teaching resources according to the overlap results;

[0043] The evaluation status includes: modification fully valid, modification partially valid, modification invalid;

[0044] Coincidence For the modification to be fully effective;

[0045] It is effective for the modified part;

[0046] Coincidence The modification is invalid;

[0047] When the evaluation module starts the content overlap check, the system first connects to the database to obtain the original teaching resource text, the annotated content text and the modified teaching resource text. The content overlap check in the evaluation module runs automatically without manual intervention by the user. The system processes and calculates the text in the background according to predetermined procedures and algorithms, which improves the accuracy of the content overlap check. The method based on word vectors and cosine similarity can compare texts at the semantic level, not just based on literal matching, avoiding the limitations of simple string matching.

[0048] Review module: For the parts marked as invalid modifications, the uploader of the teaching resources gives corresponding explanations. If the explanation is acceptable, the next process will be entered, otherwise the teaching resources will be returned;

[0049] When the modification is evaluated as invalid, the system automatically sends a notification to the uploader of the teaching resources. The notification lists in detail the parts marked as invalid modification, the annotation content, and matters that need to be explained. After receiving the notification, the uploader enters a detailed explanation in the system interface within the specified time, such as 72 hours, including the modification ideas and understanding of the annotations, and views the uploader's explanation and related resource information in the system interface in the crowdsourcing evaluation module today.

[0050] Crowdsourcing evaluation mode: When the evaluation status is "Fully effective modification" or "Partially effective modification", the system automatically enters the crowdsourcing evaluation mode. The system randomly assigns teaching resources to evaluators, who are composed of subject teachers, teaching experts and outstanding students. The evaluators conduct evaluations based on content quality, teaching applicability and clarity of expression within a specified time. The evaluation results are divided into pass or fail. If the percentage of fail is greater than the percentage of pass, the teaching resources are returned. If the percentage of fail is less than the percentage of pass, the teaching resources are open to the public, and students can use them after the publicization.

[0051] The evaluators are composed of 40% subject teachers, 40% education experts and 20% outstanding students. Each teaching resource is evaluated by 3 evaluators. The evaluators score the teaching resources on a scale of 1-10 within the specified time according to the standards of content quality, teaching applicability and clarity of expression, of which the weight of content quality is 40%, the weight of teaching applicability is 40%, and the weight of clarity of expression is 20%. The average score is calculated based on the scores of the evaluators. Teaching resources with scores below 6 points are marked as needing to be revised. The evaluation calculation is in progress. The number of subject teachers is , the number of education experts is , the number of outstanding students is ,and , the number of subject teachers to be selected , number of education experts , the number of outstanding students The selection process is achieved by marking the personnel in the evaluation personnel database by type and randomly selecting them according to the above number. The multiple dimensions of evaluating the quality of teaching resources include content quality, teaching applicability and expression clarity, and weights are set for them respectively, among which the content quality weight is , teaching suitability weight , clarity of expression weight ,and , collect the scores of subject teachers, teaching experts and outstanding students on each dimension through the crowdsourcing evaluation model, with the score range of 1-10 points. According to the collected scoring data, calculate the average score of teaching suitability , average content quality score , average score of clarity of expression , using the formula , average score of computing resources ,in Used to determine whether resources need to be modified again;

[0052] The evaluation of content quality is based on the accuracy, comprehensiveness and novelty of knowledge points, among which the accuracy of knowledge points accounts for the weight of content quality. Proportion, comprehensiveness of knowledge points Proportion, the novelty of knowledge points accounts for Ratio, where , ,and When calculating the content quality score, the knowledge points are scored separately in these three aspects and the total score is calculated in proportion.

[0053] System-set adjustable score thresholds , used to compare with the average score of resources For comparison, When the system automatically marks the teaching resource as needing to be revised, it will send a notification to the resource uploader containing the resource's average score, scores in each dimension, and revision suggestions. The revision suggestions are generated based on the parts with lower scores in each dimension. When the resource is evaluated, it maintains the current state or enters the next process, and the evaluation results are recorded for subsequent analysis.

[0054] In use:

[0055] Students: After logging into the system, you can search in the resource browsing interface to find available teaching resources, click to download or view and use them online.

[0056] Teachers: Log in to the system regularly, upload new teaching resources or check the annotations of the resources you have uploaded, make modifications and submit again. You can also annotate the resources newly uploaded by other teachers. If you receive a notification that a resource has been returned or requires explanation, handle it in a timely manner.

[0057] Evaluators: According to the tasks assigned by the system, complete the evaluation of teaching resources within the specified time and fill in the scoring and evaluation content carefully.

[0058] For students: they can obtain high-quality teaching resources that have been strictly evaluated and optimized, improve learning effects and efficiency, and reduce learning confusion caused by resource quality issues. For teachers: they can promote communication and collaboration among teachers, and continuously improve the quality of their own teaching resources through annotation and modification processes. At the same time, they can obtain new teaching ideas and methods from the feedback of other teachers and evaluators. For the optimization management system: they can scientifically manage and optimize teaching resources, improve the overall quality of education, ensure the applicability and effectiveness of teaching resources, and make reasonable allocation and utilization of resources.

[0059] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0060] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart teaching resource optimization management system, characterized in that: include: User management module: students, teachers, and evaluators register through the user management module, fill in information, and log in to the system using their registered account. The system categorizes students, teachers, and evaluators; Resource management module: Teachers upload teaching resources through the resource management module. The resources will be stored in the system and classified according to their subjects and grades. After the resources are successfully uploaded, other teachers can annotate the newly uploaded resources on the teacher side. The annotation content is stored in the corresponding teaching resource document. The uploader of the teaching resource can modify the annotation content and submit the teaching resource for the second time after the modification. The teacher side can still annotate after the second submission; Evaluation module: When the number of annotations on teaching resources reaches the preset threshold, the evaluation mechanism is activated. The evaluation mechanism includes content coincidence check, comparing the original text and the modified text, and checking the coincidence of the annotation content and the modified information. The coincidence calculation formula is: ,determine the evaluation status of teaching resources according to the overlap results; The evaluation status includes: modification fully valid, modification partially valid, modification invalid; Coincidence For the modification to be fully effective; It is effective for the modified part; Coincidence The modification is invalid; Review module: For the parts marked as invalid modifications, the uploader of the teaching resources gives corresponding explanations. If the explanation is acceptable, the next process will be entered, otherwise the teaching resources will be returned; Crowdsourcing evaluation mode: When the evaluation status is that the modification is fully effective or partially effective, the system automatically enters the crowdsourcing evaluation mode. The system randomly assigns teaching resources to evaluators, who are composed of subject teachers, teaching experts and outstanding students. The evaluators conduct evaluations based on content quality, teaching applicability and clarity of expression within the specified time. The evaluation results are divided into pass or fail. If the proportion of fail is greater than the proportion of pass, the teaching resources are returned. If the proportion of fail is less than the proportion of pass, the teaching resources are open to the public, and students can use them after the public release.

2. The intelligent teaching resource optimization management system according to claim 1, characterized in that: The system extracts the original teaching resource text, the text containing the annotation content, and the modified teaching resource text from the database. Through natural language processing technology and text matching algorithm, it compares the content involved in the annotation and the modified information, and uses the word vector-based similarity calculation method to convert the text into a vector representation, and then calculates the similarity between the vectors.

3. The intelligent teaching resource optimization management system according to claim 1, characterized in that: In the resource management module, resource classification adopts a content-based classification algorithm, and teaching resource documents ; It is the first teaching resource document. This is the second teaching resource document. is the total number of teaching resource documents in the system, the vocabulary set , The first function word, The second function word, is the total number of words in the vocabulary set; Constructing the document-term matrix ,in Words to express In the documentation The weight in vocabulary In the documentation The word frequency in For vocabulary In the documentation The number of times it appears in .

4. The intelligent teaching resource optimization management system according to claim 3 is characterized by: Inverse document frequency calculation: ,in is the total number of documents, Contains vocabulary The number of documents; weight calculation, ,in is the word frequency, is the inverse document frequency, through Cluster analysis is performed to classify resources by subject and grade.

5. The intelligent teaching resource optimization management system according to claim 1, characterized in that: In the resource management module, the storage of teaching resources adopts a distributed file system, and each teaching resource file is divided into multiple data blocks and stored on different storage nodes. The size of the teaching resource file is , the data block size is , the number of storage nodes is , then the number of data blocks , Indicates rounding up. The system will round up according to the preset storage strategy. The data blocks are evenly distributed in At the same time, the system creates an index table for each teaching resource, which records the resource's subject, grade, file name, and storage node location information.

6. The intelligent teaching resource optimization management system according to claim 1, characterized in that: The evaluators are composed of 40% subject teachers, 40% education experts and 20% outstanding students. Each teaching resource is evaluated by 3 evaluators. The evaluators score the teaching resources on a scale of 1-10 within the specified time according to the standards of content quality, teaching applicability and clarity of expression, where the weight of content quality is 40%, the weight of teaching applicability is 40%, and the weight of clarity of expression is 20%. The average score is calculated based on the scores of the evaluators, and teaching resources with a score below 6 are marked as needing to be revised.

7. The intelligent teaching resource optimization management system according to claim 6, characterized in that: During evaluation calculation, The number of subject teachers is , the number of education experts is , the number of outstanding students is ,and , the number of subject teachers to be selected , number of education experts , the number of outstanding students The selection process is achieved by marking the personnel in the evaluation personnel database by type and then randomly selecting them according to the above number.

8. The intelligent teaching resource optimization management system according to claim 1, characterized in that: The multiple dimensions of evaluating the quality of teaching resources include content quality, teaching applicability and clarity of expression, and weights are set for each of them, among which the weight of content quality is , teaching suitability weight , clarity of expression weight ,and , collect the scores of subject teachers, teaching experts and outstanding students for each dimension through the crowdsourcing evaluation model, with the score range of 1-10 points. According to the collected scoring data, calculate the average score of teaching suitability , average content quality score , average score of clarity of expression , using the formula , average score of computing resources ,in Used to determine whether the resource needs to be modified.

9. The intelligent teaching resource optimization management system according to claim 1, characterized in that: The evaluation of content quality is based on the accuracy, comprehensiveness and novelty of knowledge points, among which the accuracy of knowledge points accounts for the weight of content quality. Proportion, comprehensiveness of knowledge points Proportion, the novelty of knowledge points accounts for Ratio, where , ,and When calculating the content quality score, the knowledge points are scored separately in these three aspects and the total score is calculated in proportion.

10. The intelligent teaching resource optimization management system according to claim 1, characterized in that: Score thresholds adjusted by system settings , used to compare with the average score of resources For comparison, When the system automatically marks the teaching resource as needing to be revised, it will send a notification to the resource uploader containing the resource's average score, scores in each dimension, and revision suggestions. The revision suggestions are generated based on the parts with lower scores in each dimension. When the resource is evaluated, it maintains the current state or enters the next process, and the evaluation results are recorded for subsequent analysis.

Images