Digital school course integrated management method and system

Through multi-dimensional analysis and integrated evaluation, the insufficient evaluation caused by single-dimensional analysis in digital school curriculum management is solved, and a more scientific and comprehensive curriculum quality evaluation is achieved, providing effective support for optimized management.

CN118982446AInactive Publication Date: 2024-11-19GUANGZHOU DISTANCE EDUCATION CENT CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411473422.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-22
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing digital school curriculum management method conducts curriculum quality analysis based on a single learning dimension, resulting in insufficient accuracy and comprehensiveness of the evaluation and the inability to achieve targeted optimization management.

Method used

Through an integrated management method and system of digital school curriculum, we collect course information to be recorded, equipment feature information, history course schedule information and historical learning information, and conduct multi-dimensional analysis, including recording progress quality requirements, learning quality requirements, and subscription quality requirements. Integrated evaluation with equipment quality requirements, and generate course quality labeling information.

Benefits of technology

It improves the scientificity, accuracy and comprehensiveness of course quality evaluation, and provides effective support for the targeted optimization management of digital courses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982446A_ABST
    Figure CN118982446A_ABST
Patent Text Reader

Abstract

The invention provides a digital school course integrated management method and system, and relates to the technical field of digital course management, and the method comprises the steps: obtaining the content of a completed digital course, carrying out the quality recognition, and obtaining the course quality information, and based on the progress quality requirement information, the learning quality requirement information, the subscription quality requirement information and the equipment quality requirement information, performing integrated evaluation on the course quality information to obtain course quality labeling information, labeling the digital course content and feeding back the digital course content to the user. Through the course management method, the technical problems that the accuracy and comprehensiveness of course quality evaluation are insufficient and the course cannot be accurately and specifically optimized and managed due to the fact that course quality analysis is generally carried out based on a single learning dimension in an existing digital school course management method can be solved, multiple important aspects of course quality can be comprehensively covered, and the course management efficiency is improved. The scientificity, accuracy and comprehensiveness of course quality evaluation are improved, and effective support is provided for targeted optimization management of subsequent courses.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of digital course management, and in particular to a digital school course integrated management method and system. Background Art

[0002] Digital schools, as an emerging model in the field of education, focus on using information technology to carry out educational and teaching activities through network platforms and digital resources. The development of digital schools has not only changed the traditional education model, but also provided more people with the opportunity to receive high-quality education. It is an important direction for the future development of education.

[0003] Relying on advanced network communication technology, cloud computing, big data, artificial intelligence and other modern information technologies, digital schools have built a flexible, efficient and convenient education and teaching environment. By establishing a resource library and an online platform, the extensive sharing and optimal configuration of educational resources can be achieved. Students and teachers can access rich teaching resources anytime and anywhere, including course videos, electronic teaching materials, interactive courseware, etc., which improves the utilization efficiency of educational resources. On the other hand, by using big data analysis and artificial intelligence technology, digital schools can provide personalized learning plans and teaching content according to students' learning habits, interests and mastery, and meet the needs of students' personalized development. For example, in the existing patent CN202211274468.0 "A digital school platform immersive digital learning method and system", through digital virtual immersive technology, practical virtual scene training and theoretical hobby scene simulation transplantation immersive training can achieve the technical goals of virtual digital immersive scene simulation of practical training and theoretical training, thereby improving the training quality and efficiency of digital schools.

[0004] At present, the existing digital school curriculum management methods usually conduct course quality analysis based on a single learning dimension, such as students' test scores or course completion rates. This method leads to insufficient accuracy and comprehensiveness in course quality evaluation, resulting in technical problems that make it impossible to accurately and targetedly optimize course management. Summary of the invention

[0005] The purpose of this application is to provide an integrated management method and system for digital school courses, so as to solve the technical problem that the existing digital school course management methods usually analyze course quality based on a single learning dimension, resulting in insufficient accuracy and comprehensiveness of course quality evaluation, and making it impossible to accurately carry out targeted optimization management of courses.

[0006] In view of the above problems, the present application provides a digital school curriculum integrated management method and system.

[0007] In a first aspect, the present application provides a digital school course integrated management method, which is implemented through a digital school course integrated management system, including: when a user is producing a digital course, collecting the course information to be recorded and the device feature information of the current device, and according to the course information to be recorded, indexing and obtaining the subscription feature information, historical class scheduling information and historical learning information of the course to which it belongs; according to the historical class scheduling information, performing a recording progress quality requirement analysis of the current course to be recorded, and obtaining progress quality requirement information; according to the historical class scheduling information combined with the historical learning information, performing a correlation analysis between the course recording quality and learning, and performing a learning quality requirement analysis, and obtaining learning quality requirement information; according to the subscription feature information, performing a subscription quality requirement analysis of the current digital course production, and obtaining subscription quality requirement information; according to the device feature information, performing a quality requirement analysis of the current digital course production, and obtaining device quality requirement information; obtaining the produced digital course content, performing quality identification, and obtaining course quality information, and based on the progress quality requirement information, learning quality requirement information, subscription quality requirement information and device quality requirement information, performing an integrated evaluation of the course quality information, obtaining course quality annotation information, annotating the digital course content and feeding it back to the user.

[0008] In the second aspect, the present application also provides a digital school course integrated management system for executing a digital school course integrated management method as described in the first aspect, including: an information collection module for collecting the course information to be recorded and the device feature information of the current device when the user is making a digital course, and obtaining the subscription feature information, historical class scheduling information and historical learning information of the course according to the course information to be recorded by indexing; a recording progress quality requirement analysis module for analyzing the recording progress quality requirements of the current course to be recorded according to the historical class scheduling information, and obtaining progress quality requirement information; a learning quality requirement analysis module for analyzing the course recording quality and learning quality according to the historical class scheduling information combined with the historical learning information. The module is used to analyze the correlation between the digital course content and the equipment quality information, and to analyze the learning quality requirements to obtain the learning quality requirements information; the module is used to analyze the subscription quality requirements of the current digital course production according to the subscription feature information, and to obtain the subscription quality requirements information; the module is used to analyze the quality requirements of the current digital course production according to the device feature information, and to obtain the equipment quality requirements information; the module is used to obtain the completed digital course content, perform quality identification, and obtain the course quality information; based on the progress quality requirements information, the learning quality requirements information, the subscription quality requirements information, and the equipment quality requirements information, the module is used to evaluate the course quality information in an integrated manner, obtain the course quality marking information, mark the digital course content, and feed back to the user.

[0009] In a third aspect, the present application also provides an electronic device comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable 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 steps of a digital school curriculum integrated management method described in any one of the above-mentioned first aspects.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages: When the user is making a digital course, the information of the course to be recorded is collected, and the device feature information of the current device is collected. According to the information of the course to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the course are indexed and obtained; according to the historical class scheduling information, the recording progress quality requirement analysis of the current course to be recorded is performed to obtain the progress quality requirement information; according to the historical class scheduling information combined with the historical learning information, the correlation analysis between the course recording quality and learning is performed, and the learning quality requirement analysis is performed to obtain the learning quality requirement information; according to the subscription feature information, the subscription quality requirement analysis of the current digital course production is performed to obtain the subscription quality requirement information; according to the device feature information, the quality requirement analysis of the current digital course production is performed to obtain the device quality requirement information; the produced digital course content is obtained, the quality identification is performed, and the course quality information is obtained; based on the progress quality requirement information, the learning quality requirement information, the subscription quality requirement information and the device quality requirement information, the course quality information is evaluated in an integrated manner to obtain the course quality marking information, the digital course content is marked and fed back to the user. That is to say, by conducting an integrated evaluation of course quality information based on progress quality requirement information, learning quality requirement information, subscription quality requirement information and device quality requirement information, course quality marking information is obtained; then the digital course content is marked according to the course quality marking information and fed back to users, which can comprehensively cover multiple important aspects of course quality, thereby improving the scientificity, accuracy and comprehensiveness of course quality evaluation, and providing effective support for the targeted optimization management of subsequent digital courses.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 A flowchart of an integrated management method for digital school courses is provided for this application; Figure 2 A flowchart of obtaining learning quality requirement information in a digital school curriculum integrated management method for this application; Figure 3 This is a structural diagram of an integrated digital school curriculum management system for this application.

[0014] Description of reference numerals: Information collection module 11, recording progress quality requirement analysis module 12, learning quality requirement analysis module 13, course quality analysis module 14, course quality evaluation module 15. DETAILED DESCRIPTION

[0015] This application provides a digital school course integrated management method and system to solve the technical problem that the existing digital school course management method usually analyzes course quality based on a single learning dimension, resulting in insufficient accuracy and comprehensiveness of course quality evaluation, and making it impossible to accurately optimize the course management. By analyzing the quality of digital courses from multiple dimensions, multiple important aspects of course quality can be fully covered, thereby improving the scientificity, accuracy and comprehensiveness of course quality evaluation, and providing effective support for the targeted optimization management of subsequent digital courses.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0017] For example, please refer to the attached Figure 1 The present application provides a digital school curriculum integrated management method, which is applied to a digital school curriculum integrated management system, and specifically includes the following steps: Step 1: When the user is making a digital course, the course information to be recorded is collected, and the device feature information of the current device is collected. According to the course information to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the course are indexed and obtained.

[0018] Specifically, when the user is producing a digital course, the information of the course to be recorded is collected, wherein the course to be recorded refers to the latest digital course to be recorded, produced and released, which can be set according to the actual situation. The information of the course to be recorded includes basic course information (including course name, course overview, target audience, scheduled course duration, teaching objectives, etc.) and course content structure (including chapter division, theme of each chapter, key knowledge points, scheduled teaching activities, etc.). And collect the device feature information of the current recording and production equipment, including hardware configuration, software configuration and network environment, etc. Then, according to the information of the course to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the course are obtained by indexing, wherein the subscription feature information includes the number of subscribers, etc.; the historical class scheduling information includes the release time and update frequency of the historical course, etc.; the historical learning information includes the course quality, student participation, learning evaluation, etc. By collecting the above information, we can better understand the historical performance of the course and the needs of potential learners, and provide reference data for subsequent course quality analysis.

[0019] Step 2: Based on the historical class scheduling information, analyze the recording progress quality requirements of the current course to be recorded to obtain progress quality requirement information.

[0020] Specifically, according to the historical class scheduling information, the recording progress quality requirements of the current course to be recorded are analyzed, that is, by calculating the time difference between the current recording time and the preset course release time, the progress quality requirements for the course are analyzed to obtain the progress quality requirement information; first, the time difference between the current recording time and the preset course release time is obtained; then, the time urgency is evaluated according to the time difference, that is, the progress quality requirements of the course are evaluated according to the length of the remaining time, wherein the time difference is proportional to the progress quality requirement information, that is, the smaller the time difference, the smaller the recording progress quality requirement, for example, if the remaining time is less, the progress quality requirement is relatively low, because the recording and production need to be completed within a limited time, and if the remaining time is more, the progress quality requirement can be relatively high, because the production team has more time to fine-tune the course content. Through the above analysis, it can be ensured that the course quality is maintained as much as possible within a limited time, and at the same time provide a reference basis for the subsequent integrated evaluation of course quality.

[0021] Step 3: Based on the historical class scheduling information and the historical learning information, conduct a correlation analysis between the course recording quality and learning, and conduct a learning quality requirement analysis to obtain learning quality requirement information.

[0022] Specifically, historical class scheduling information and historical learning information are collected, where historical class scheduling information includes course arrangements, recording quality standards, release time, etc., and historical learning information includes student participation, completion rate, test scores, learning evaluation, etc. Then, based on historical class scheduling information and historical learning information, the correlation analysis between course recording quality and learning is conducted. First, the correlation analysis indicators are determined, and key indicators of course quality (such as video clarity, content accuracy, teaching interaction, etc.) and key indicators of learning effectiveness (such as student satisfaction, knowledge mastery, course completion rate, etc.) are selected; then, statistical methods (such as Pearson correlation coefficient, Spearman rank correlation, etc.) are used to calculate the correlation between course quality indicators and learning effectiveness indicators; further, according to the size and sign of the correlation coefficient, the strength of the correlation between course quality and learning effectiveness is judged to obtain the correlation analysis results.

[0023] Then, according to the results of the correlation analysis between the course recording quality and learning, the learning quality requirements are analyzed. The correlation analysis results are proportional to the learning quality requirements, that is, the greater the correlation, the greater the learning quality requirements for digital courses, and the learning quality requirements information is obtained. By obtaining the learning quality requirements information, it can ensure that the positive correlation between the course recording quality and learning outcomes is fully utilized, and at the same time provide a reference for the subsequent integrated evaluation of course quality.

[0024] Step 4: Based on the subscription feature information, analyze the subscription quality requirements of the current digital course production to obtain subscription quality requirement information; based on the device feature information, analyze the quality requirements of the current digital course production to obtain device quality requirement information.

[0025] Specifically, the subscription quality requirements for the current digital course production are analyzed based on the subscription feature information, that is, the subscription quality requirements are analyzed based on features such as the number of subscribers. For example, the more subscribers there are, the greater the subscription quality requirements are, and the subscription quality requirement information is obtained. On the other hand, based on the device feature information, the quality requirements for the current digital course production are analyzed, such as analyzing the hardware and software configuration of the recording device, including processor speed, memory size, storage space, camera and microphone quality, etc. At the same time, the quality requirements for the current digital course production are set according to the device feature information, where the device features are proportional to the quality requirements, that is, the better the device features, the greater the quality requirements. By obtaining subscription quality requirement information and device quality requirement information, course quality evaluation can be performed from multiple dimensions, providing a reference for subsequent integrated course quality evaluation.

[0026] Step 5: Acquire the completed digital course content, perform quality identification, obtain course quality information, conduct an integrated evaluation of the course quality information based on the progress quality requirement information, learning quality requirement information, subscription quality requirement information, and device quality requirement information, obtain course quality marking information, mark the digital course content, and provide feedback to the user.

[0027] Specifically, first, the digital course content is obtained, and then the quality of the digital course content is identified to obtain the course quality information, that is, the image quality and coherence are identified based on the convolutional neural network, and the actual course quality information is obtained according to the image quality identification result analysis. Then, based on the progress quality requirement information, learning quality requirement information, subscription quality requirement information and equipment quality requirement information, the course quality information is evaluated in an integrated manner. For example, according to the evaluation criteria, relevant course quality data is collected; then, the course quality is scored according to the evaluation criteria of each dimension; then, the weighted average or other statistical methods are used, combined with the weights of each dimension, to calculate the comprehensive quality score of the course and obtain the course quality annotation information. Finally, the digital course content is annotated according to the course quality annotation information and fed back to the user. The above method can comprehensively cover multiple important aspects of course quality, thereby improving the scientificity, accuracy and comprehensiveness of course quality evaluation, and providing effective support for the targeted optimization management of subsequent digital courses.

[0028] The digital school course integrated management method is applied to a digital school course integrated management system, which can solve the technical problem that the existing digital school course management method usually analyzes course quality based on a single learning dimension, resulting in insufficient accuracy and comprehensiveness of course quality evaluation, and making it impossible to accurately carry out targeted optimization management of courses. By conducting an integrated evaluation of course quality information based on progress quality requirement information, learning quality requirement information, subscription quality requirement information, and device quality requirement information, course quality annotation information is obtained; then the digital course content is annotated according to the course quality annotation information and fed back to the user, which can comprehensively cover multiple important aspects of course quality, thereby improving the scientificity, accuracy, and comprehensiveness of course quality evaluation, and providing effective support for the targeted optimization management of subsequent digital courses.

[0029] Furthermore, step one of this application includes: When a user is making a digital course, the digital course's affiliated course, recording time information and course sequence information are collected as the course information to be recorded; the device performance information and device network information of the current device are collected as the device feature information; according to the course information to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the affiliated course are obtained by indexing, wherein the subscription feature information includes the number of subscribers, the historical class scheduling information includes the release time information and historical course quality information of multiple historical sequence courses of the affiliated course, and the historical learning information includes multiple learning evaluation information of the subscribing users on the multiple historical sequence courses.

[0030] Specifically, when the user is making a digital course, the digital course's affiliated course, recording time information, and course sequence information are collected as the course information to be recorded; on the other hand, the device performance information (hardware configuration, software environment, etc.) and device network information (network bandwidth, network stability, etc.) of the current device are collected as device feature information. Then, according to the course information to be recorded, the subscription feature information, historical class scheduling information, and historical learning information of the affiliated course are obtained by indexing, wherein the subscription feature information includes the number of subscribers, the historical class scheduling information includes the release time information and historical course quality information (including course content quality, teaching methods, learning outcomes, etc.) of multiple historical sequence courses of the affiliated course, and the historical learning information includes multiple learning evaluation information of the subscribing users on the multiple historical sequence courses.

[0031] Further, step 2 of this application includes: According to the historical class schedule information and the information of the courses to be recorded, the standard release time of the current digital course is obtained, and the remaining production time is calculated according to the current recording time information; according to the remaining production time, the preset quality requirement information is corrected and analyzed to obtain the progress quality requirement information.

[0032] Specifically, first, according to the historical class schedule information and the information of the courses to be recorded, the standard release time of the current digital course is obtained, and according to the current recording time information, the remaining production time is calculated, and the remaining production time is the time difference between the standard release time and the recording time information. Then, according to the remaining production time, the preset quality requirement information is corrected and analyzed. The preset quality requirement information can be set according to the actual scenario, where the smaller the remaining production time, the smaller the progress quality requirement. For example, if the remaining time is sufficient, the preset quality requirement can be kept unchanged or further improved; if the remaining time is tight, the preset quality requirement may need to be appropriately adjusted to ensure completion on time; the progress quality requirement information is obtained.

[0033] Further, as attached Figure 2 As shown, step three of this application includes: According to the historical class scheduling information and historical learning information, a correlation analysis between course recording quality and learning is performed to obtain a learning correlation coefficient; a set of sample learning correlation coefficients is collected, and according to the size of the sample learning correlation coefficients, annotations are set to obtain a set of sample learning quality requirement information; the set of sample learning correlation coefficients and the set of sample learning quality requirement information are used to train a learning quality requirement analyzer; the learning quality requirement analyzer is used to perform a learning quality requirement analysis on the learning correlation coefficients to obtain learning quality requirement information.

[0034] Specifically, according to the historical class scheduling information and historical learning information, the correlation analysis between course recording quality and learning is performed, such as using statistical methods (such as Pearson correlation coefficient, Spearman rank correlation, etc.) to calculate the correlation between recording quality indicators and learning effectiveness indicators to obtain learning correlation coefficients. Then, a set of sample learning correlation coefficients is collected, and the learning quality requirement information is annotated according to the size of the sample learning correlation coefficient, that is, according to the size of the sample learning correlation coefficient, a corresponding quality requirement level is set for each course. For example, if the learning correlation coefficient is high, it means that the recording quality has a significant impact on the learning effectiveness, and a higher learning quality requirement should be set; if the learning correlation coefficient is low, it may mean that the recording quality has a small impact on the learning effectiveness, and a lower learning quality requirement can be set; and a set of sample learning quality requirement information is obtained.

[0035] A learning quality requirement analyzer is constructed based on a BP neural network. The learning quality requirement analyzer is a neural network model that can be iteratively optimized in machine learning, including an input layer, multiple hidden layers and an output layer, wherein the input data of the input layer is a learning association coefficient, and the output data of the output layer is learning quality requirement information; further, the sample learning association coefficient set and the sample learning quality requirement information set are used as training data to perform supervised training on the learning quality requirement analyzer, and the prediction error is minimized by adjusting the model parameters (such as weights and biases), which is usually achieved through a back propagation algorithm. At the same time, a validation set is used to evaluate the performance of the model. According to the training and evaluation results of the model, the model architecture parameters such as the number of hidden layers and the number of neurons are adjusted to obtain a learning quality requirement analyzer that meets the preset convergence constraints.

[0036] Finally, the learning quality requirement analyzer is used to analyze the learning quality requirement of the learning association coefficient and output the learning quality requirement information. By constructing a learning quality requirement analyzer based on the BP neural network to analyze the learning quality requirement, the accuracy and efficiency of the output of the learning quality requirement information can be improved.

[0037] Furthermore, the present application also includes the following steps: Based on the multiple history course quality information in the history scheduling information, a history course quality information sequence is constructed; based on the multiple learning evaluation information in the history learning information, a history learning evaluation information sequence is constructed; based on grey correlation analysis, the history course quality information sequence is used as the main data sequence, and the history learning evaluation information sequence is used as the influencing data sequence, and correlation analysis and calculation are performed to obtain the learning correlation coefficient.

[0038] Specifically, first, the quality information of multiple history courses in the history class scheduling information is collected, and the collected quality information is cleaned, deduplicated and sorted to ensure the quality and consistency of the data; then the processed quality information is arranged in chronological order to construct a history course quality information sequence. Then, using the same method, according to the multiple learning evaluation information in the history learning information, the multiple learning evaluation information is arranged in chronological order to construct a history learning evaluation information sequence.

[0039] Then, based on the grey correlation analysis, the history course quality information sequence is used as the main data sequence, and the history learning evaluation information sequence is used as the influencing data sequence for correlation analysis. First, each data point in the history course quality information sequence and the history learning evaluation information sequence is standardized so that they can be compared on the same scale; then, for each data point in the history course quality information sequence, the absolute difference between it and the data point at the corresponding position in the history learning evaluation information sequence is calculated; then, according to the standardized data and the calculated absolute difference, the correlation coefficient is calculated using the grey correlation analysis method. When calculating the correlation coefficient, the difference of the time series, that is, the importance of data at different time points, needs to be considered; finally, the calculated correlation coefficient is accumulated to obtain the grey correlation degree between the main data sequence and the influencing data sequence, and finally the grey correlation degree is used as the learning correlation coefficient. Through the grey correlation analysis, we can deeply understand the relationship between the course quality information and the learning evaluation information, and provide a scientific basis for course production.

[0040] Further, step 4 of this application includes: Acquire a set of sample subscription feature information, and set annotations according to each sample subscription feature information to obtain a set of sample subscription quality requirement information; use the sample subscription feature information set and the sample subscription quality requirement information set to construct a subscription quality requirement classifier, classify the subscription feature information, and obtain subscription quality requirement information; collect a set of sample device feature information, and set annotations according to each sample device feature information to obtain a set of sample device quality requirement information; use the sample device feature information set and the sample device quality requirement information set to train a device quality requirement analyzer, perform input analysis on the device feature information, and obtain device quality requirement information.

[0041] Specifically, first, obtain a sample subscription feature information set, that is, a sample subscriber number set; then, based on each sample subscription feature information, mark the subscription quality requirement information, wherein the subscription quality requirement information is proportional to the number of subscribers, that is, the more subscribers there are, the larger the corresponding subscription quality requirement information. Then, construct a subscription quality requirement classifier based on the BP neural network, and its construction and training principles are the same as those of the above-mentioned learning quality requirement analyzer; then, use the sample subscription feature information set and the sample subscription quality requirement information set as training data to perform supervised training on the subscription quality requirement classifier to obtain a trained subscription quality requirement classifier. Further, classify the subscription feature information through the subscription quality requirement classifier to obtain subscription quality requirement information.

[0042] On the other hand, a set of sample equipment feature information is collected, and then the equipment quality requirement information is labeled according to each sample equipment feature information to obtain a set of sample equipment quality requirement information; the sample equipment feature information set and the sample equipment quality requirement information set are further used as training data to perform supervised training on an equipment quality requirement analyzer constructed based on a BP neural network, and the equipment feature information is input and analyzed by the equipment quality requirement analyzer to obtain equipment quality requirement information.

[0043] Further, step five of this application includes: Acquire the completed digital course content, perform quality identification on the digital course content, and obtain course quality information, wherein the course quality information is obtained by weighted calculation of image quality information and coherence quality information of quality identification and coherence quality identification; calculate and obtain comprehensive quality requirement information according to the progress quality requirement information, learning quality requirement information, subscription quality requirement information, and device quality requirement information; evaluate and calculate the course quality information according to the comprehensive quality requirement information to obtain course quality labeling information.

[0044] Specifically, the completed digital course content is obtained, and then a content recognition model is constructed based on a convolutional neural network. The image quality and image coherence of the digital course content are then identified through the content recognition model to obtain image quality information and coherence quality information. The image quality information and coherence quality information are further weighted and calculated, and the weighted calculation result is used as the course quality information, wherein the weight values ​​of the image quality information and the coherence quality information can be set according to the degree of influence, and the greater the degree of influence, the greater the weight.

[0045] On the other hand, weighted calculation is performed based on the progress quality requirement information, learning quality requirement information, subscription quality requirement information and device quality requirement information to obtain comprehensive quality requirement information; then, based on the comprehensive quality requirement information, the course quality information is evaluated and calculated, and course quality labeling information is obtained based on the evaluation results.

[0046] Furthermore, the present application also includes the following steps: Collect a set of sample digital course content, annotate the course image quality of the sample digital course content, and annotate the coherence quality of the sample digital course content to obtain a sample image quality information set and a sample coherence quality information set; use the sample digital course content set as input data, and use the sample image quality information set and the sample coherence quality information set as output supervision data, respectively, based on a convolutional neural network, train a course image quality recognition branch and a course coherence quality recognition branch to obtain a course quality identifier; use the course quality identifier to perform quality recognition on the digital course content, obtain image quality information and coherence quality information, and obtain course quality information through weighted calculation.

[0047] Specifically, first, a set of sample digital course content is collected, the course image quality of the sample digital course content is annotated, and the coherence quality of the sample digital course content is annotated to obtain a sample image quality information set and a sample coherence quality information set; that is, a large number of image samples of digital course content are collected, including different image quality and coherence levels; then the image samples are annotated, and the annotations include image quality (such as clarity, brightness, contrast, etc.) and image coherence (such as scene transition, action coherence, etc.).

[0048] Convolutional neural network is a deep learning model, which is mainly used to process data such as images, videos and sounds. It extracts local features of data through convolutional layer, and then performs classification or regression through fully connected layer to complete feature recognition. Then, based on convolutional neural network, a course image quality recognition branch and a course continuity quality recognition branch are constructed, and then the sample digital course content set is used as input data, the sample image quality information set is used as output supervision data of the course image quality recognition branch, and the sample continuity quality information set is used as output supervision data of the course continuity quality recognition branch. The course image quality recognition branch and the course continuity quality recognition branch are trained to obtain a course quality identifier. Finally, the course quality identifier is used to perform quality identification on the digital course content to obtain image quality information and continuity quality information, and then the image quality information and continuity quality information are weighted to obtain course quality information.

[0049] In summary, the digital school curriculum integrated management method provided by this application has the following technical effects: By conducting an integrated evaluation of course quality information based on progress quality requirement information, learning quality requirement information, subscription quality requirement information and device quality requirement information, course quality marking information can be obtained; then the digital course content is marked according to the course quality marking information and fed back to users, which can comprehensively cover multiple important aspects of course quality, thereby improving the scientificity, accuracy and comprehensiveness of course quality evaluation, and providing effective support for the targeted optimization management of subsequent digital courses.

[0050] Embodiment 2: Based on the digital school curriculum integrated management method in the above embodiment, the present application also provides a digital school curriculum integrated management system, see the attached Figure 3 ,include: The information collection module 11 is used to collect the information of the course to be recorded and the device feature information of the current device when the user is making a digital course. According to the information of the course to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the course to be recorded are obtained by indexing; the recording progress quality requirement analysis module 12 is used to analyze the recording progress quality requirements of the current course to be recorded according to the historical class scheduling information, and obtain the progress quality requirement information; the learning quality requirement analysis module 13 is used to analyze the correlation between the course recording quality and learning according to the historical class scheduling information combined with the historical learning information, and to analyze the learning quality requirements to obtain the learning quality requirement information ; A course quality analysis module 14 is used to perform a subscription quality requirement analysis on the current digital course production according to the subscription feature information to obtain subscription quality requirement information, and to perform a quality requirement analysis on the current digital course production according to the device feature information to obtain device quality requirement information; a course quality evaluation module 15 is used to obtain the completed digital course content, perform quality identification, obtain course quality information, perform an integrated evaluation on the course quality information based on the progress quality requirement information, learning quality requirement information, subscription quality requirement information and device quality requirement information, obtain course quality marking information, mark the digital course content and provide feedback to the user.

[0051] Furthermore, the digital school curriculum integrated management system is also used for: When a user is making a digital course, the digital course's affiliated course, recording time information and course sequence information are collected as the course information to be recorded; the device performance information and device network information of the current device are collected as the device feature information; according to the course information to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the affiliated course are obtained by indexing, wherein the subscription feature information includes the number of subscribers, the historical class scheduling information includes the release time information and historical course quality information of multiple historical sequence courses of the affiliated course, and the historical learning information includes multiple learning evaluation information of the subscribing users on the multiple historical sequence courses.

[0052] Furthermore, the digital school curriculum integrated management system is also used for: According to the historical class schedule information and the information of the courses to be recorded, the standard release time of the current digital course is obtained, and the remaining production time is calculated according to the current recording time information; according to the remaining production time, the preset quality requirement information is corrected and analyzed to obtain the progress quality requirement information.

[0053] Furthermore, the digital school curriculum integrated management system is also used for: According to the historical class scheduling information and historical learning information, a correlation analysis between course recording quality and learning is performed to obtain a learning correlation coefficient; a set of sample learning correlation coefficients is collected, and according to the size of the sample learning correlation coefficients, annotations are set to obtain a set of sample learning quality requirement information; the set of sample learning correlation coefficients and the set of sample learning quality requirement information are used to train a learning quality requirement analyzer; the learning quality requirement analyzer is used to perform a learning quality requirement analysis on the learning correlation coefficients to obtain learning quality requirement information.

[0054] Furthermore, the digital school curriculum integrated management system is also used for: Based on the multiple history course quality information in the history scheduling information, a history course quality information sequence is constructed; based on the multiple learning evaluation information in the history learning information, a history learning evaluation information sequence is constructed; based on grey correlation analysis, the history course quality information sequence is used as the main data sequence, and the history learning evaluation information sequence is used as the influencing data sequence, and correlation analysis and calculation are performed to obtain the learning correlation coefficient.

[0055] Furthermore, the digital school curriculum integrated management system is also used for: Acquire a set of sample subscription feature information, and set annotations according to each sample subscription feature information to obtain a set of sample subscription quality requirement information; use the sample subscription feature information set and the sample subscription quality requirement information set to construct a subscription quality requirement classifier, classify the subscription feature information, and obtain subscription quality requirement information; collect a set of sample device feature information, and set annotations according to each sample device feature information to obtain a set of sample device quality requirement information; use the sample device feature information set and the sample device quality requirement information set to train a device quality requirement analyzer, perform input analysis on the device feature information, and obtain device quality requirement information.

[0056] Furthermore, the digital school curriculum integrated management system is also used for: Acquire the completed digital course content, perform quality identification on the digital course content, and obtain course quality information, wherein the course quality information is obtained by weighted calculation of image quality information and coherence quality information of quality identification and coherence quality identification; calculate and obtain comprehensive quality requirement information according to the progress quality requirement information, learning quality requirement information, subscription quality requirement information, and device quality requirement information; evaluate and calculate the course quality information according to the comprehensive quality requirement information to obtain course quality labeling information.

[0057] Furthermore, the digital school curriculum integrated management system is also used for: Collect a set of sample digital course content, annotate the course image quality of the sample digital course content, and annotate the coherence quality of the sample digital course content to obtain a sample image quality information set and a sample coherence quality information set; use the sample digital course content set as input data, and use the sample image quality information set and the sample coherence quality information set as output supervision data, respectively, based on a convolutional neural network, train a course image quality recognition branch and a course coherence quality recognition branch to obtain a course quality identifier; use the course quality identifier to perform quality recognition on the digital course content, obtain image quality information and coherence quality information, and obtain course quality information through weighted calculation.

[0058] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The digital school curriculum integrated management method and specific examples in the aforementioned embodiment 1 are also applicable to the digital school curriculum integrated management system of this embodiment. Through the aforementioned detailed description of the digital school curriculum integrated management method, those skilled in the art can clearly understand the digital school curriculum integrated management system of this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0059] Embodiment three, based on the inventive concept of a digital school course integrated management method in the aforementioned embodiment, the present application also provides an electronic device, comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable 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 steps of the digital school course integrated management method described in any one of the aforementioned embodiments one.

[0060] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0061] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A digital school curriculum integrated management method, characterized in that: include: When the user is making a digital course, the course information to be recorded is collected, and the device feature information of the current device is collected. According to the course information to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the course are obtained by indexing; According to the historical course scheduling information, the recording progress quality requirement analysis of the current course to be recorded is performed to obtain progress quality requirement information; According to the historical class scheduling information and the historical learning information, a correlation analysis between the course recording quality and the learning is performed, and a learning quality requirement analysis is performed to obtain learning quality requirement information; According to the subscription characteristic information, a subscription quality requirement analysis of the current digital course production is performed to obtain subscription quality requirement information; according to the device characteristic information, a quality requirement analysis of the current digital course production is performed to obtain device quality requirement information; Acquire the completed digital course content, perform quality identification, obtain course quality information, perform an integrated evaluation of the course quality information based on the progress quality requirement information, learning quality requirement information, subscription quality requirement information and device quality requirement information, obtain course quality marking information, mark the digital course content and provide feedback to the user.

2. The digital school curriculum integrated management method according to claim 1, characterized in that: When a user is making a digital course, the course information to be recorded is collected, and the device feature information of the current device is collected. According to the course information to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the course are obtained by indexing, including: When the user is making a digital course, the course to which the digital course belongs, the recording time information and the course sequence information are collected as the course information to be recorded; Collect device performance information and device network information of the current device as device feature information; According to the information of the course to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the belonging course are obtained by indexing, wherein the subscription feature information includes the number of subscribers, the historical class scheduling information includes the release time information and historical course quality information of multiple historical sequence courses of the belonging course, and the historical learning information includes multiple learning evaluation information of the subscribed users on the multiple historical sequence courses.

3. The digital school curriculum integrated management method according to claim 1, characterized in that: According to the historical course scheduling information, the recording progress quality requirement analysis of the current course to be recorded is performed to obtain progress quality requirement information, including: According to the historical course scheduling information and the information of the courses to be recorded, the standard release time of the current digital course is obtained, and according to the current recording time information, the remaining production time is calculated; According to the remaining production time, the preset quality requirement information is corrected and analyzed to obtain the progress quality requirement information.

4. The digital school curriculum integrated management method according to claim 1, characterized in that: According to the historical course scheduling information combined with the historical learning information, the correlation analysis between the course recording quality and the learning is performed, and the learning quality requirement analysis is performed to obtain the learning quality requirement information, including: According to the historical class scheduling information and historical learning information, a correlation analysis between course recording quality and learning is performed to obtain a learning correlation coefficient; Collecting a set of sample learning correlation coefficients, and setting annotations according to the size of the sample learning correlation coefficients to obtain a set of sample learning quality requirement information; Using the sample learning association coefficient set and the sample learning quality requirement information set to train a learning quality requirement analyzer; The learning quality requirement analyzer is used to perform a learning quality requirement analysis on the learning association coefficient to obtain learning quality requirement information.

5. The digital school curriculum integrated management method according to claim 4, characterized in that: According to the historical class scheduling information and historical learning information, a correlation analysis between course recording quality and learning is performed, including: Constructing a history course quality information sequence according to the plurality of history course quality information in the history course scheduling information; Constructing a historical learning evaluation information sequence according to the plurality of learning evaluation information in the historical learning information; Based on grey correlation analysis, the history course quality information sequence is used as the main data sequence, and the history learning evaluation information sequence is used as the influencing data sequence, and correlation analysis is performed to obtain the learning correlation coefficient.

6. The digital school curriculum integrated management method according to claim 1, characterized in that: According to the subscription characteristic information, the subscription quality requirement analysis of the current course recording to be recorded is performed to obtain the subscription quality requirement information; according to the device characteristic information, the quality requirement analysis of the current digital course production is performed to obtain the device quality requirement information, including: Obtain a sample subscription feature information set, and set a label according to each sample subscription feature information to obtain a sample subscription quality requirement information set; Using the sample subscription feature information set and the sample subscription quality requirement information set, constructing a subscription quality requirement classifier, classifying the subscription feature information, and obtaining subscription quality requirement information; Collecting a set of sample equipment characteristic information, and setting annotations based on each sample equipment characteristic information to obtain a set of sample equipment quality requirement information; The sample device feature information set and the sample device quality requirement information set are used to train a device quality requirement analyzer, and the device feature information is input and analyzed to obtain device quality requirement information.

7. The digital school curriculum integrated management method according to claim 1, characterized in that: Acquire the produced digital course content, perform quality identification, obtain course quality information, and perform integrated evaluation on the course quality information based on the progress quality requirement information, learning quality requirement information, subscription quality requirement information, and device quality requirement information to obtain course quality annotation information, including: Acquire the produced digital course content, perform quality identification on the digital course content, and obtain course quality information, wherein the course quality information is obtained by weighted calculation of image quality information and coherence quality information of quality identification and coherence quality identification; Calculate and obtain comprehensive quality requirement information according to the progress quality requirement information, the learning quality requirement information, the subscription quality requirement information, and the device quality requirement information; The course quality information is evaluated and calculated according to the comprehensive quality requirement information to obtain course quality marking information.

8. The digital school curriculum integrated management method according to claim 7, characterized in that: Performing quality identification on the digital course content to obtain course quality information, including: Collecting a sample digital course content set, marking the course image quality of the sample digital course content, and marking the coherence quality of the sample digital course content, to obtain a sample image quality information set and a sample coherence quality information set; Using the sample digital course content set as input data, using the sample image quality information set and the sample coherence quality information set as output supervision data, respectively, training a course image quality recognition branch and a course coherence quality recognition branch based on a convolutional neural network, and obtaining a course quality identifier; The course quality identifier is used to identify the quality of the digital course content, obtain image quality information and coherence quality information, and obtain course quality information through weighted calculation.

9. A digital school curriculum integrated management system, characterized in that: The steps for implementing the digital school curriculum integrated management method as described in any one of claims 1 to 8 include: The information collection module is used to collect the information of the course to be recorded and the device feature information of the current device when the user is making a digital course. According to the information of the course to be recorded, the subscription feature information, historical class scheduling information and historical learning information of the course are obtained by indexing; A recording progress quality requirement analysis module is used to analyze the recording progress quality requirements of the current course to be recorded based on the historical course scheduling information to obtain progress quality requirement information; A learning quality requirement analysis module is used to analyze the correlation between course recording quality and learning based on the historical course scheduling information and historical learning information, and to analyze the learning quality requirements to obtain learning quality requirement information; A course quality analysis module, configured to analyze the subscription quality requirements of the current digital course production according to the subscription feature information to obtain the subscription quality requirement information, and to analyze the quality requirements of the current digital course production according to the device feature information to obtain the device quality requirement information; The course quality evaluation module is used to obtain the completed digital course content, perform quality identification, obtain course quality information, perform an integrated evaluation of the course quality information based on the progress quality requirement information, learning quality requirement information, subscription quality requirement information and device quality requirement information, obtain course quality marking information, mark the digital course content and feedback to the user.

10. An electronic device, comprising: at least one processor; a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions executable 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 steps of a digital school course integrated management method as described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Teaching quality management method and system

    CN108009761A

  • Teaching quality evaluation method and system

    CN108288124A

  • Course resource labeling method, device, system and equipment and storage medium

    CN114691904A

  • Classroom record digital course resource quality evaluation method and system

    CN115619279A