Multimedia teaching system and method based on book information popularization

Abstract

The invention discloses a multimedia teaching system and method based on book information promotion, and relates to the technical field of multimedia teaching. Learning resources are collected according to a learning resource list and then classified, low-quality classes are screened out after the quality of the resource classes is evaluated, and the low-quality resource classes are updated; tracking the learning progress of the student, obtaining learning state data after regular detection, evaluating the learning state of the student according to the learning state data, and collecting learning feedback data of the student; after learning resources are recommended for students, corresponding learning state data are collected, learning state values describing learning results are generated, different learning strategies are automatically configured according to learning module changes, an alarm instruction is triggered when teaching indexes are lower than expectation, and corresponding intervention strategies are matched through the alarm state data. An education manager can take targeted intervention measures in advance, and resource waste caused by repeated tutoring can be reduced by automatically configuring a collaborative teaching strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of multimedia teaching, in particular to a multimedia teaching system and method based on book and information promotion. Background Art

[0002] With the rapid development of information technology and the widespread application of digital resources, the modern education model is undergoing profound changes. Multimedia teaching, as a teaching method that integrates audio-visual and interactive learning, has been widely used in educational institutions at all levels and types. The integration of library and information resources not only enriches the teaching content and improves the teaching effect, but also meets the diverse learning needs of students and promotes the development of personalized learning. In this context, scene measurement, as an effective teaching environment evaluation method, can accurately depict the teaching scene and students' learning behavior through multi-dimensional data collection and analysis, and provide a scientific basis for the optimization of multimedia teaching systems. However, with the increasing diversification of student groups and the increasing complexity of learning needs, traditional teaching resource allocation and management methods have been difficult to adapt to the requirements of the current educational environment.

[0003] In the Chinese invention patent with application publication number CN104484040A, a multimedia interactive teaching control system and teaching control method are disclosed, including: a data acquisition module: to collect video streams; characterized in that it also includes: a matte module: to process the collected video streams, extract the moving targets of interest, and obtain the foreground image; an image synthesis module: to display the obtained foreground image in the form of a special-shaped window at the forefront of all windows in real time; an image transmission and real-time display module: to transmit the special-shaped window containing the synthesized image on the teacher's computer to the student computer through the network in real time and display it in real time. The teacher's lecture screen is obtained through a camera, and is transmitted to the matte module in real time through the network to extract the foreground character image. The extracted foreground character image is superimposed on the courseware being played on the teacher's computer in the form of a special-shaped window through the image synthesis module, and is displayed in real time on the teacher's computer. At the same time, the synthesized image is transmitted to the student computer in real time through the network in the form of a video stream.

[0004] In the actual teaching process, teachers and education administrators often face a series of technical difficulties, such as how to effectively collect and analyze students' learning needs, how to reasonably configure and manage multimedia teaching resources, and how to provide timely feedback and adjustments based on students' learning status. Existing teaching methods have many shortcomings in meeting personalized learning needs, optimizing resource utilization efficiency, and improving the accuracy of teaching management. For example, the traditional data collection method is single and it is difficult to fully reflect students' learning behaviors and needs; resource management lacks intelligent means, resulting in low resource utilization efficiency; the teaching feedback mechanism lags behind and it is difficult to respond to changes in students' learning status in a timely manner. In addition, the application of scene measurement in existing systems is still imperfect, and it is difficult to achieve real-time and dynamic monitoring and evaluation of teaching environment and student behavior. These problems not only restrict the full play of multimedia teaching effects, but also affect the optimal configuration of teaching resources and the scientific nature of teaching management.

[0005] Therefore, the present invention proposes a multimedia teaching system and method based on book and information promotion. Summary of the invention

[0006] 1. Technical issues to be resolved In view of the deficiencies of the prior art, the present invention provides a multimedia teaching system and method based on the promotion of book information. The system collects learning resources according to the learning resource list and then classifies them. After evaluating the quality of the resource class, the low-quality class is screened out and the low-quality resource class is updated. The learning progress of students is tracked and the learning status data is obtained after regular testing. The learning status of students is evaluated by the learning status data, and the learning feedback data of students is collected. After recommending learning resources to students, the corresponding learning status data is collected, and a learning status value describing the learning results is generated. Different learning strategies are automatically configured according to the changes in the learning modules. When the teaching indicators are lower than expected, an alarm instruction is triggered, and the corresponding intervention strategy is matched by the alarm status data. Education managers can take targeted intervention measures in advance by automatically configuring collaborative teaching strategies, thereby solving the technical problems recorded in the background technology.

[0007] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: Multimedia teaching methods based on library and information promotion include: collecting students' basic learning data through multiple channels to generate students' learning needs portraits, analyzing and obtaining the similarity between learning needs portraits, and constructing demand diversity from similarity data. If the demand diversity Exceeding diversity thresholds, setting instructional goals for each student and creating lists of learning resources; Collect learning resources according to the learning resource list and classify them to obtain several learning resource classes. After evaluating the quality of the resource classes, filter out low-quality classes. Update the low-quality resource classes at the update nodes that meet the constraint conditions to obtain updated learning resources. After modularizing the learning content, assign learning tasks, track students' learning progress and obtain learning status data after regular testing. Use the learning status data to evaluate students' learning status. If the obtained learning evaluation does not exceed expectations, collect students' learning feedback data. After recommending learning resources to students, the corresponding learning status data is collected, and the learning status value describing the learning outcomes is generated from the learning status data. , if the learning state value If the status is lower than the threshold, a monitoring instruction is issued to the outside; Build an association graph model and automatically configure different learning strategies according to the changes in learning modules. When the teaching indicators are lower than expected, trigger the alarm command and summarize the obtained alarm status data. Generate intervention degree from the summarized alarm status data , according to the degree of intervention The relationship between the corresponding threshold value matches the corresponding intervention strategy, where the intervention degree is generated by the alarm status data in the alarm information set , as follows: ; Where: is the spatial domain of the learning module, and is the time interval of integration; is the index or identifier of the learning module, is the current time node; For learning modules The weight function at time t is, For learning modules The alarm ratio at time t, is the time decay parameter.

[0008] Furthermore, data on students’ basic knowledge level, information acquisition habits, multimedia usage preferences, degree of awareness of library and information resources, and potential learning barriers are collected and summarized as a set of basic learning data; The collected needs of each student are mapped into a feature vector, and the feature vector is used as input to form a portrait of the student's learning needs using a density-based clustering algorithm.

[0009] Furthermore, after similarity analysis is performed on different learning demand portraits, several similarity data are obtained, and the corresponding demand diversity is constructed from the similarity data. , as follows: ; in: The number of learning needs profiles, Probability distribution of learning needs portrait, is the weight coefficient, is the similarity between the i-th and j-th learning need portraits.

[0010] Further, learning resources related to the teaching content are collected according to the learning resource list, and the collected learning resources are classified by a pre-trained classification algorithm to obtain several learning resource categories and number them respectively; Taking the resource class as input, the trained resource quality assessment model is used to evaluate the quality of the resource and then the corresponding quality score is output; if the obtained quality score is lower than the preset quality threshold, the corresponding quality class is regarded as a low-quality class.

[0011] Furthermore, the low-quality classes are updated and the update frequency of the low-quality classes is constrained as follows: ; Where: is the update frequency of the low-quality class at time t and location i, is the mass score of the low-quality class at time t and position i, is the threshold of quality score; is the learning diversity at time t, is the weight coefficient, is a nonlinear adjustment parameter, and i represents a specific low-quality class.

[0012] Furthermore, the learning content is modularized in advance, and tasks are assigned to students after setting learning goals and corresponding teaching content for each learning module; students' learning progress is tracked and tested regularly, test scores are obtained and learning status data is recorded and summarized as learning status data; students' feedback data on classroom content, teaching methods and resource usage is collected and summarized as learning feedback data.

[0013] Furthermore, a learning report is generated based on students' learning behaviors, preferences and learning feedback data. The pre-trained recommendation algorithm recommends learning resources to students from the collected learning resources, records students' classroom participation, online resource usage and learning evaluation values, and summarizes the learning status data set.

[0014] Furthermore, after continuously obtaining the learning status data of each student at each time point, the learning status value describing the learning outcome is obtained from the learning status data set. , as follows: ; Where: kis the total number of students, , is the total duration of the current stage; is the learning evaluation value of student i at time t, is the learning diversity at time t, is the weight function for learning diversity, where is the weight coefficient.

[0015] Furthermore, after receiving the monitoring instruction, the knowledge points in the teaching system are modeled as nodes in the graph, and the successor relationship and mutual support relationship between the knowledge points are modeled as directed edges in the graph, so as to construct a correlation graph model that depicts the internal structure and correlation of the teaching content; when it is detected that the student's learning status value on multiple highly correlated learning modules is When both are insufficient, different learning strategies are automatically configured.

[0016] Furthermore, the following teaching indicators are collected: processing delay, resource click rate, and student completion rate. A target value is set for each indicator. When the teaching indicator is lower than the target value, an alarm command is triggered, and the alarm-related information obtained, including the alarm time node, the corresponding learning module, and the proportion exceeding the threshold, is summarized to generate an alarm information set.

[0017] Furthermore, some predictions Higher than the preset first intervention threshold, collect cases of successful application of multimedia teaching methods and organize them into a case library; Between the first and second state thresholds, introduce advanced equipment and tools for the current teaching process; some predictions When the second intervention threshold is lower than the threshold, the multimedia resources are updated and supplemented.

[0018] The multimedia teaching system based on the promotion of library information includes a diversity analysis unit, which collects students' basic learning data from multiple channels to generate students' learning needs portraits, analyzes and obtains the similarity between learning needs portraits, and constructs demand diversity based on similarity data. If the demand diversity Exceeding diversity thresholds, setting instructional goals for each student and creating lists of learning resources; A resource classification unit collects and classifies learning resources according to the learning resource list to obtain several learning resource classes, selects low-quality classes after evaluating the quality of the resource classes, updates the low-quality resource classes at the update nodes that meet the constraint conditions, and obtains updated learning resources; The learning evaluation unit modularizes the learning content and assigns learning tasks, tracks students' learning progress and obtains learning status data after regular testing. The learning status data is used to evaluate students' learning status. If the obtained learning evaluation does not exceed expectations, the learning feedback data of students is collected. The status evaluation unit collects the corresponding learning status data after recommending learning resources for students, and generates a learning status value describing the learning outcomes from the learning status data , if the learning state value obtained If the status is lower than the threshold, a monitoring instruction is issued to the outside; The learning intervention unit builds an association graph model and automatically configures different learning strategies according to the changes in the learning modules. When the teaching indicators are lower than expected, the alarm command is triggered and the obtained alarm status data is summarized. The intervention degree is generated from the summarized alarm status data. , according to the degree of intervention The relationship with the corresponding threshold matches the corresponding intervention strategy.

[0019] (III) Beneficial effects The present invention provides a multimedia teaching system and method based on book and information promotion, which has the following beneficial effects:

[0020] 1. Use density-based clustering algorithm to cluster feature vectors and form a portrait of students' learning needs, which can effectively identify student groups with similar learning needs. By quantifying the diversity of learning needs and judging the degree of dispersion of student needs, the subsequent resource recommendation and teaching arrangement can be managed in a refined manner.

[0021] 2. By constructing and applying resource quality assessment models, we can reduce the adverse effects of inefficient or ineffective resources on the teaching process, continuously follow up and regularly update quality resources, and ensure the cutting-edge nature and practicality of teaching content.

[0022] 3. By introducing a constraint mechanism for resource update frequency, we ensure that low-quality resources can be updated and replaced in a timely and effective manner, thus avoiding the negative impact of obsolescence and failure of teaching resources on the teaching process. By dynamically adjusting the resource update frequency, we can speed up the pace of resource updates when demand is highly dispersed and resource quality is low, prevent excessive resource updates, and avoid excessive burdens on resource management and waste of resources.

[0023] 4. By understanding students' learning status in each module in real time, timely and targeted guidance and resource recommendations can be provided; by generating learning status assessment reports, it can provide teachers with a scientific basis for teaching decision-making and improve the accuracy and effectiveness of teaching.

[0024] 5. Based on these evaluation values ​​and feedback data, more targeted coaching and resource recommendations are implemented to enhance the accuracy and effectiveness of the teaching process. The generation of learning reports and the formation of learning status data sets can adjust teaching strategies and resource allocation to ensure that teaching activities are highly matched with student needs.

[0025] 6. Learning state value through comprehensive calculation , realizing the comprehensive evaluation and monitoring of students' overall learning status. When it is lower than the preset threshold, relevant multimedia resources will be updated or supplemented in a timely manner to ensure the continuous optimization and timeliness of teaching content.

[0026] 7. By constructing an association graph model and implementing learning gap detection, the dependency relationship between knowledge points can be intuitively displayed, allowing education administrators to take targeted intervention measures in advance. By automatically configuring collaborative teaching strategies, the waste of resources caused by repeated tutoring can be reduced.

[0027] 8. Generate intervention degree by calculating the alarm status data in the alarm information set , quantify the severity and urgency of problems in the current teaching process and resource allocation, automatically determine the specific intervention measures that need to be taken, and ensure the continuous optimization and efficient allocation of teaching resources and teaching strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flowchart of a multimedia teaching method based on book and information promotion of the present invention; Figure 2 It is a schematic diagram of the structure of the multimedia teaching system based on book and information promotion of the present invention. DETAILED DESCRIPTION

[0029] 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.

[0030] See also Figure 1 The present invention provides a multimedia teaching method based on book and information promotion, including: Step 1: Collect students’ basic learning data from multiple channels to generate students’ learning needs portraits, analyze and obtain the similarities between learning needs portraits, and construct demand diversity based on similarity data If the demand diversity Exceeding diversity thresholds, setting instructional goals for each student and creating lists of learning resources; The step 1 includes the following contents: Step 101: Use questionnaire surveys, interviews, and online data monitoring to collect data on students' basic knowledge level, information acquisition habits, multimedia usage preferences, degree of awareness of library and information resources, and potential learning barriers, and summarize them as a learning basic data set; Map the collected needs of each student into a feature vector, which may include multiple dimensions such as "need for database retrieval ability", "need for paper writing guidance", "preference for video resources", etc.; use the feature vector as input and use a density-based clustering algorithm to form a student's learning needs profile; When used, the multi-channel and multi-dimensional data collection method not only improves the integrity and accuracy of the data, but also enables the subsequent demand analysis and resource allocation to more accurately and scientifically reflect the actual needs of students, avoiding the deviations and limitations that may be caused by a single data source. It can improve the allocation efficiency of teaching resources and enhance the pertinence and personalization of teaching design; Step 102: Perform similarity analysis on different learning demand profiles to obtain a number of similarity data, and construct the corresponding demand diversity from the similarity data. , analyze the diversity of learning needs in the following ways: ; in: The number of learning needs profiles, The probability distribution of the learning demand portrait represents its proportion in the overall demand. is the weight coefficient, which ranges from 0 to 1 and reflects the importance of the differences between demand profiles. The similarity between the i-th and j-th learning need portraits; Based on historical data and management expectations of the teaching process, the diversity threshold is set in advance; if the diversity required When the diversity threshold is exceeded and student needs are very dispersed, it indicates that the demand diversity is high and a more personalized teaching design is needed. The KMeans clustering algorithm can be used to divide students with similar needs into several groups, so that more detailed classification management can be performed in subsequent resource recommendations and teaching arrangements; Use the SMART principle to set teaching goals for each student, such as: "Complete database search subject practice in the third week. Each student needs to search more than 10 high-quality journal articles and master Boolean logic." "Complete the introduction to academic writing in the sixth week. Students can independently use reference management tools to mark citations." Make a list of learning resources based on teaching goals, and clarify the types, quantities, usage permissions, and applicable course modules of multimedia courseware, electronic journals, database links, online tools, etc. to be used later; The SMART principle is an effective goal-setting framework that ensures that goals are clear and achievable. SMART stands for Specific, Measurable, Achievable, Relevant, and Time-bound. By clarifying the various dimensions of the goal, the SMART principle helps educators and managers set clear, quantifiable, and feasible teaching goals, thereby improving teaching effectiveness and the accuracy of resource allocation. This principle is widely used in multimedia teaching methods to achieve personalized and efficient teaching management.

[0031] When using, combine the contents in steps 101 and 102: The density-based clustering algorithm is used to cluster the feature vectors to form a portrait of students' learning needs, which can effectively identify groups of students with similar learning needs; By constructing similarity data, quantifying the diversity of learning needs, and comparing it with the preset diversity threshold, we can determine the degree of dispersion of student needs. Using the K-Means clustering algorithm, students with similar needs can be further divided into several groups, which can achieve refined management of subsequent resource recommendations and teaching arrangements.

[0032] Step 2: Collect learning resources according to the learning resource list and classify them to obtain several learning resource classes. After evaluating the quality of the resource classes, filter out low-quality classes, and update the low-quality resource classes at the update nodes that meet the constraints to obtain updated learning resources. The step 2 includes the following contents: Step 201: Collect learning resources such as books, journals, databases, electronic resources and multimedia materials related to the teaching content according to the learning resource list. The following examples are given: library and information resources: paper books, electronic books, journal databases, academic papers, industry reports, conference proceedings, patent documents, etc.; multimedia resources: teaching videos (self-made by the school or external open courses), interactive courseware, virtual laboratory software, VR / AR teaching modules, etc.; auxiliary tools: document management software, translation software, online collaboration platform, academic search engine, etc.; classify the collected learning resources by a pre-trained classification algorithm, obtain several learning resource categories and number them respectively; When in use, the pre-trained classification algorithm is used to automatically classify a variety of learning resources, which can improve the accuracy and efficiency of classification; through the numbering management of resources of different categories, the resource calling and tracking process is simplified, making it easier for teachers and teaching managers to quickly locate and use the required resources.

[0033] Step 202: train a machine learning algorithm with the labeled sample data to obtain a trained resource quality assessment model; use the resource class as input, use the trained resource quality assessment model to assess the quality of the resource, and then output a corresponding quality score; if the obtained quality score is lower than the preset quality threshold, the corresponding quality class is regarded as a low-quality class; resources with low quality scores or extremely poor student feedback can be replaced, removed from the shelves, or updated first; high-quality resources are continuously followed up, such as updating the journal database once a month or updating the online video course once a semester; When in use, by constructing and applying a resource quality assessment model, the high quality and applicability of teaching resources can be ensured, reducing the adverse effects of inefficient or invalid resources on the teaching process; continuous follow-up and regular updating of quality resources can ensure the cutting-edge and practical nature of teaching content, and enhance students' learning experience and teaching effectiveness; it can improve the overall quality and utilization efficiency of teaching resources, ensuring the smooth progress of the teaching process and the achievement of teaching objectives.

[0034] Step 203: Update the low-quality class and constrain the update frequency of the low-quality class. Update the low-quality resource class on the update node that meets the constraint conditions to obtain the updated learning resources. The constraint method is as follows: ; Where: is the update frequency of the low-quality class at time t and location i, is the quality score of the low-quality class at time t and position i, and its value range is , is the threshold of quality score; is the learning diversity at time t, is the weight coefficient, and its value falls between 0 and 1. is a nonlinear adjustment parameter used to control learning diversity The nonlinear response in the update frequency constraint has a value greater than 0, t is the time variable, i represents the specific low-quality class, and e can be 2.718; When using, combine the contents in steps 201 to 203: By introducing a constraint mechanism for resource update frequency, we ensure that low-quality resources can be updated and replaced in a timely and effective manner, thus avoiding the negative impact of obsolescence and failure of teaching resources on the teaching process. We take into account the diversity of learning needs and resource quality scores, and dynamically adjust the resource update frequency, so that when the needs are highly dispersed and the resource quality is low, the pace of resource updates can be accelerated to ensure the timeliness and relevance of teaching content. At the same time, this mechanism also prevents excessive resource updates, avoiding excessive burdens on resource management and waste of resources. The introduction of the learning diversity coefficient reflects the heterogeneity of student groups in learning needs, guides resource updating strategies to be more in line with actual teaching needs, enhances the scientificity and accuracy of teaching resource allocation, and improves the dynamic adaptability and continuous optimization capabilities of teaching resource management.

[0035] Step 3: After modularizing the learning content, assign learning tasks, track students' learning progress, and obtain learning status data after regular testing. Use the learning status data to evaluate students' learning status. If the obtained learning evaluation does not exceed expectations, collect students' learning feedback data; The step three includes the following contents: Step 301: modularize the learning content in advance, such as information retrieval methods, resource evaluation standards, citation management skills, etc., set specific learning goals and corresponding teaching content for each learning module, and then assign tasks to students; Track students' learning progress and regularly test their understanding of knowledge points, obtain corresponding test scores, record learning status data such as discussion times and learning resource usage frequency, and summarize them as learning status data; When in use, the modular design of teaching content and the tracking and detection of learning progress improve the structure and manageability of the teaching process. It is convenient for teachers to conduct in-depth explanations and guidance on each knowledge point or skill point, ensuring that students can achieve the predetermined learning goals in each module; By conducting regular tests and recording learning behavior data, we can understand students' learning status in each module in real time, promptly identify students' weaknesses and learning difficulties in specific knowledge points, and provide timely targeted tutoring and resource recommendations; by comprehensively analyzing multi-dimensional data such as test scores, number of discussions, and frequency of resource use, we can generate a learning status assessment report, which can provide teachers with a scientific basis for teaching decision-making and improve the accuracy and effectiveness of teaching.

[0036] Step 302: training a neural convolutional network using the labeled sample data to obtain a trained learning state evaluation model; Taking learning status data as input, the trained learning status evaluation model is used to evaluate the current learning status of the learning content module and generate a learning evaluation value. If the obtained learning evaluation does not exceed expectations, it means that the learning effect of the current learning module is poor and needs to be optimized. At this time, students’ feedback data on classroom content, teaching methods and resource use are collected and summarized as learning feedback data; When used, combine the contents in steps 301 and 302: The learning evaluation value comprehensively considers multiple dimensions such as test scores, discussion participation, and frequency of resource use, measures students' learning outcomes and behaviors, automatically identifies student groups with learning difficulties or poor learning outcomes, and timely collects and analyzes students' subjective feedback data to form a direct evaluation of teaching content and methods, which helps to adjust teaching strategies and resource allocation in a targeted manner, and improve teaching outcomes and student satisfaction.

[0037] Based on these evaluation values ​​and feedback data, more targeted tutoring and resource recommendations are implemented to help students overcome learning barriers, improve their academic performance and abilities, and enhance the accuracy and effectiveness of the teaching process.

[0038] Step 4: After recommending learning resources to students, collect the corresponding learning status data, and generate a learning status value describing the learning outcomes from the learning status data , if the learning state value If the status is lower than the threshold, a monitoring instruction is issued to the outside; The step 4 includes the following contents: Step 401: Generate a learning report based on the student's learning behavior, preference and learning feedback data, recommend learning resources to the student from the collected learning resources using a pre-trained recommendation algorithm, record the student's class participation, online resource usage and learning evaluation value, and summarize and obtain a learning status data set; The generation of learning reports and the formation of learning status data sets provide teachers and teaching managers with detailed information on student learning dynamics and resource usage, enabling them to timely understand students' feedback on different resources and learning paths, adjust teaching strategies and resource allocation, and ensure that teaching activities are highly matched with student needs.

[0039] Step 402: After continuously acquiring the learning status data of each student at each time point, a learning status value describing the learning outcome is acquired from the learning status data set. , based on the learning status value, the overall learning and teaching effect in the current stage is evaluated as follows: ; Where: k is the total number of students, , is the total duration of the current stage; is the learning evaluation value of student i at time t, is the learning diversity at time t, is the weight function for learning diversity, where is the weight coefficient, and its value falls between 0 and 1; According to historical data and management expectations of students' learning status, the status threshold is set in advance; if the learning status value obtained is If the value is lower than the preset status threshold, it means that the current learning and teaching status is poor and needs to be deeply monitored. At this time, a monitoring instruction is issued to the outside. When using, combine the contents in steps 401 and 402: Learning state values ​​through comprehensive calculation , which realizes the comprehensive evaluation and monitoring of students' overall learning status, can ensure the multi-dimensional measurement of students' learning status, comprehensively reflect students' actual performance and learning input in the learning process, and help teachers and teaching managers accurately grasp students' learning progress and status; when the learning status value When the level falls below the preset threshold, the resource replenishment mechanism is automatically triggered to update or supplement relevant multimedia resources in a timely manner to ensure the continuous optimization and timeliness of teaching content.

[0040] Step 5: Build an association graph model and automatically configure different learning strategies according to the changes in learning modules. When the teaching indicators are lower than expected, trigger the alarm command and summarize the obtained alarm status data. Generate the intervention degree from the summarized alarm status data. , according to the degree of intervention The relationship with the corresponding threshold is matched with the corresponding intervention strategy; The step five includes the following contents: Step 501: after receiving the monitoring instruction, the knowledge points in the teaching system are modeled as nodes in a graph, and the predecessor and successor relationships and mutual support relationships between the knowledge points are modeled as directed edges in the graph, so as to construct an association graph model that depicts the internal structure and association of the teaching content; When a node has a significant learning loss, that is, the student fails to master it or has a weak link, other nodes that are highly associated (or strongly dependent) with it will be affected; for example, a learning loss on the "paper format management" node may directly affect the mastery quality of the "paper writing" module node; when it is detected that the student's learning status value in multiple highly associated learning modules such as retrieval, management and writing is poor, the learning state value of the node will be affected. When there are deficiencies in both, different learning strategies are automatically configured to collaboratively make up for multiple knowledge or skill deficiencies through packaged training in a single teaching activity; When in use, by constructing an association graph model and implementing learning loss detection, an association graph model that fully reflects the internal structure and relevance of teaching content is formed, which can intuitively display the dependency relationship between various knowledge points, allowing education managers to take targeted intervention measures in advance to prevent the spread of learning loss in the knowledge network; By automatically configuring collaborative teaching strategies, it can reduce the waste of resources caused by repeated tutoring, help students comprehensively improve relevant knowledge and skills, effectively improve the overall coordination and efficiency of the teaching process, and ensure the efficient use of teaching resources and the overall improvement of students' learning effects; Step 502: The following teaching indicators are collected for the teaching process and learning gap repair: Processing delay: refers to the time lag between teaching adjustments (such as courseware changes or resource push) and students' effective feedback; Resource click rate: used to measure students' willingness to access and use frequency of learning resources (literature, videos, question banks, etc.) recommended by the system or assigned by teachers; Student completion rate, which counts the proportion of students who submit homework, complete tests, or conduct online activities within a certain teaching cycle; Set an acceptable range or target value for each indicator. When the teaching indicator is lower than the target value for multiple times or for a long time at a certain stage, trigger an alarm command, and collect the alarm-related information, including the alarm time node, the corresponding learning module, and the proportion exceeding the threshold, to generate an alarm information set. When in use, key teaching indicators such as collection and processing delay, resource click rate and student completion rate are collected to comprehensively and in real time monitor all aspects of teaching activities and students' learning behaviors; through a multi-dimensional monitoring system, it can effectively identify possible problems and bottlenecks in the teaching process, ensure the smooth progress of teaching activities and the achievement of teaching objectives; by automatically identifying indicators with poor performance in teaching activities and building an automated alarm mechanism, it can improve the timeliness and response speed of teaching management, ensuring that problems in the teaching process can be quickly discovered and resolved.

[0041] Step 503: Under dimensionless conditions, generate intervention degree from alarm status data in the alarm information set , the specific method is as follows: ; Where: is the spatial domain of learning modules, representing the set of all learning modules, and is the time interval of integration; is the index or identifier of the learning module, is the current time node; For learning modules The weight function at time t takes a value greater than 0. For learning modules The alarm ratio at time t, the value range is [0,1], is the time decay parameter, and its value range is ; The value of e can be 2.718; Based on historical data and management expectations of students' learning status, a pre-trained clustering algorithm determines a first intervention threshold and a second intervention threshold; the first intervention threshold is higher than the second intervention threshold; If the intervention If the threshold is higher than the preset first intervention threshold, cases of successful application of multimedia teaching methods in other schools or institutions can be collected and compiled into a case library, including the teaching methods, multimedia tools used, results achieved and lessons learned in the cases; If the intervention When between the first and second status thresholds, introduce advanced equipment and tools into the current teaching process; If the intervention When it is lower than the second intervention threshold, it indicates that the current teaching and learning methods and current learning resources may be insufficient, and multimedia resources need to be updated and supplemented to ensure the timeliness and relevance of teaching content; When using, combine the contents in steps 501 to 503: Generate intervention degree by calculating alarm status data in alarm information set , quantify the severity and urgency of the problems in the current teaching process and resource allocation, and can be based on the degree of intervention The system can automatically determine the specific intervention measures that need to be taken based on the level of intervention, thereby improving the scientificity and efficiency of teaching management. It can effectively guide teaching managers to take corresponding measures under different intervention levels, ensure the continuous optimization and efficient allocation of teaching resources and teaching strategies, and improve the response speed and adaptability of teaching management.

[0042] See also Figure 2 The present invention provides a multimedia teaching system based on book and information promotion, including: The diversity analysis unit collects students’ basic learning data from multiple channels to generate students’ learning needs portraits, analyzes and obtains the similarity between learning needs portraits, and constructs demand diversity based on similarity data If the demand diversity Exceeding diversity thresholds, setting instructional goals for each student and creating lists of learning resources; A resource classification unit collects and classifies learning resources according to the learning resource list to obtain several learning resource classes, selects low-quality classes after evaluating the quality of the resource classes, updates the low-quality resource classes at the update nodes that meet the constraint conditions, and obtains updated learning resources; The learning evaluation unit modularizes the learning content and assigns learning tasks, tracks students' learning progress and obtains learning status data after regular testing. The learning status data is used to evaluate students' learning status. If the obtained learning evaluation does not exceed expectations, the learning feedback data of students is collected. The status evaluation unit collects the corresponding learning status data after recommending learning resources for students, and generates a learning status value describing the learning outcomes from the learning status data , if the learning state value obtained If the status is lower than the threshold, a monitoring instruction is issued to the outside; The learning intervention unit builds an association graph model and automatically configures different learning strategies according to the changes in the learning modules. When the teaching indicators are lower than expected, the alarm command is triggered and the obtained alarm status data is summarized. The intervention degree is generated from the summarized alarm status data. , according to the degree of intervention The relationship with the corresponding threshold matches the corresponding intervention strategy.

[0043] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0044] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0045] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0046] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0047] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A multimedia teaching method based on the promotion of library and information, characterized by: include, After collecting basic learning data from students through multiple channels, we generate a profile of students’ learning needs, analyze and obtain the similarities between the profiles of learning needs, and build demand diversity If the demand diversity Exceeding diversity thresholds, setting instructional goals for each student and creating lists of learning resources; According to the learning resource list, learning resources are collected and classified to obtain several learning resource classes. After evaluating the quality of the resource classes, low-quality classes are screened out. The low-quality resource classes are updated at the update nodes that meet the constraint conditions to obtain updated learning resources. After modularizing the learning content, assign learning tasks, track students' learning progress and obtain learning status data after regular testing. Use the learning status data to evaluate students' learning status. If the obtained learning evaluation does not exceed expectations, collect students' learning feedback data. After recommending learning resources to students, the corresponding learning status data is collected, and the learning status value describing the learning outcomes is generated from the learning status data. , if the learning state value If the status is lower than the threshold, a monitoring instruction is issued to the outside; Build an association graph model and automatically configure different learning strategies according to the changes in learning modules. When the teaching indicators are lower than expected, trigger the alarm command and summarize the obtained alarm status data. Generate intervention degree from the summarized alarm status data , according to the degree of intervention The relationship with the corresponding threshold matches the corresponding intervention strategy.

2. The multimedia teaching method based on book and information promotion according to claim 1 is characterized by: Collect students' basic knowledge level, information acquisition habits, multimedia usage preferences, degree of knowledge of library and information resources, and potential learning obstacles, and summarize them as a set of basic learning data; The collected needs of each student are mapped into a feature vector, and the feature vector is used as input to form a portrait of the student's learning needs using a density-based clustering algorithm.

3. The multimedia teaching method based on book and information promotion according to claim 2 is characterized by: After similarity analysis between different learning demand portraits, similarity data is obtained, and the corresponding demand diversity is constructed based on the similarity data. , as follows: ； in: The number of learning needs profiles, Probability distribution of learning needs portrait, is the weight coefficient, is the similarity between the i-th and j-th learning need portraits.

4. The multimedia teaching method based on book and information promotion according to claim 3 is characterized by: Learning resources related to the teaching content are collected according to the learning resource list, and the collected learning resources are classified by a pre-trained classification algorithm to obtain several learning resource classes and number them respectively; taking the resource class as input, the trained resource quality assessment model is used to assess the quality of the resource and then output the corresponding quality score; if the obtained quality score is lower than the preset quality threshold, the corresponding quality class is regarded as a low-quality class.

5. The multimedia teaching method based on book and information promotion according to claim 4 is characterized by: Update the low-quality classes and constrain the update frequency of the low-quality classes. The constraints are as follows: ； Where: is the update frequency of the low-quality class at time t and location i, is the mass score of the low-quality class at time t and position i, is the threshold of quality score; is the learning diversity at time t, is the weight coefficient, is a nonlinear adjustment parameter, and i represents a specific low-quality class.

6. The multimedia teaching method based on book and information promotion according to claim 5 is characterized by: Modularize the learning content in advance, set learning goals and corresponding teaching content for each learning module, and then assign tasks to students; track students' learning progress and conduct regular tests, obtain test scores and record learning status data, which will be summarized as learning status data; Collect students' feedback data on classroom content, teaching methods and resource usage, and summarize them as learning feedback data.

7. The multimedia teaching method based on book and information promotion according to claim 6 is characterized by: A learning report is generated based on students' learning behaviors, preferences and learning feedback data. The pre-trained recommendation algorithm recommends learning resources to students from the collected learning resources, records students' classroom participation, online resource usage and learning evaluation values, and summarizes the learning status data set.

8. The multimedia teaching method based on book and information promotion according to claim 7 is characterized by: After continuously obtaining the learning status data of each student at each time node, the learning status value describing the learning outcome is obtained from the learning status data set. , as follows: ； Where: k is the total number of students, , is the total duration of the current stage; is the learning evaluation value of student i at time t, is the learning diversity at time t, is the weight function for learning diversity, where is the weight coefficient.

9. The multimedia teaching method based on book and information promotion according to claim 8 is characterized by: After receiving the monitoring instruction, the knowledge points in the teaching system are modeled as nodes in the graph, and the successor relationship and mutual support relationship between the knowledge points are modeled as directed edges in the graph. A correlation graph model is constructed to describe the internal structure and correlation of the teaching content. When it is detected that the student's learning status value is on multiple highly correlated learning modules, When both are insufficient, different learning strategies are automatically configured.

10. The multimedia teaching method based on book and information promotion according to claim 9 is characterized by: The following teaching indicators are collected: processing delay, resource click rate and student completion rate. Target values ​​are set for each indicator. When the teaching indicator is lower than the target value, an alarm command is triggered. The alarm-related information obtained, including the alarm time node, the corresponding learning module and the proportion exceeding the threshold, is summarized to generate an alarm information set.

11. The multimedia teaching method based on book and information promotion according to claim 10 is characterized by: If the intervention Above the preset first intervention threshold, collect cases of successful application of multimedia teaching methods and organize them into a case library; If the intervention Between the first and second state thresholds, introduce advanced equipment and tools for the current teaching process; some predictions When the second intervention threshold is lower than the threshold, the multimedia resources are updated and supplemented.

12. A multimedia teaching system based on the promotion of library information, characterized by: include, The diversity analysis unit collects students’ basic learning data from multiple channels to generate students’ learning needs portraits, analyzes and obtains the similarity between learning needs portraits, and constructs demand diversity based on similarity data If the demand diversity Exceeding diversity thresholds, setting instructional goals for each student and creating lists of learning resources; A resource classification unit collects and classifies learning resources according to the learning resource list to obtain several learning resource classes, selects low-quality classes after evaluating the quality of the resource classes, updates the low-quality resource classes at the update nodes that meet the constraint conditions, and obtains updated learning resources; The learning evaluation unit modularizes the learning content and assigns learning tasks, tracks students' learning progress and obtains learning status data after regular testing. The learning status data is used to evaluate students' learning status. If the obtained learning evaluation does not exceed expectations, the learning feedback data of students is collected. The status evaluation unit collects the corresponding learning status data after recommending learning resources for students, and generates a learning status value describing the learning outcomes from the learning status data , if the learning state value obtained If the status is lower than the threshold, a monitoring instruction is issued to the outside; The learning intervention unit builds an association graph model and automatically configures different learning strategies according to the changes in the learning modules. When the teaching indicators are lower than expected, the alarm command is triggered and the obtained alarm status data is summarized. The intervention degree is generated from the summarized alarm status data. , according to the degree of intervention The relationship with the corresponding threshold matches the corresponding intervention strategy.

Images