Online teaching collaborative management system and method based on cloud platform

Abstract

The invention relates to the technical field of data processing, in particular to an online teaching collaborative management system based on a cloud platform, which comprises a multi-source data acquisition module, a candidate resource screening module, a collaborative strategy generation module, an interaction channel distribution module, a collaborative data acquisition module and a collaborative resume recording module. According to the system, key information in the online teaching process is comprehensively acquired through the multi-source data acquisition unit, the key information comprises multi-party participation subject information, teaching resource metadata, collaborative scene parameters and the like, a rich data basis is provided for follow-up management, the integrity and pertinence of data are ensured through accurate data positioning and preliminary processing, and the online teaching efficiency is improved. The efficiency and accuracy of teaching collaboration are improved, teaching resource allocation is optimized, personalized teaching collaboration is realized, the collaboration process is guaranteed to be smooth, evaluation and tracing are facilitated, and education informatization development is promoted.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an online teaching collaborative management system and method based on a cloud platform. Background Technology

[0002] In the context of the rapid development of educational informatization, traditional teaching management models are no longer able to meet the increasingly complex needs of online teaching.

[0003] With the widespread application of technologies such as cloud computing, big data, and artificial intelligence, the education sector is undergoing profound changes. Online teaching, in particular, as an emerging teaching model, has been welcomed by teachers and students alike for its flexibility and convenience. However, online teaching also faces many challenges, such as low collaboration efficiency among multiple stakeholders (teachers, students, administrators, etc.), uneven distribution of teaching resources, and difficulty in meeting personalized teaching needs.

[0004] Most existing online teaching management systems focus on single functions, such as resource management, student management, or course management, lacking comprehensive management and optimization of collaborative processes among multiple stakeholders. These systems often cannot dynamically adjust the allocation of teaching resources according to real-time needs, nor can they provide personalized teaching collaboration strategies.

[0005] Furthermore, due to the lack of a unified data collection and analysis mechanism, teaching administrators find it difficult to fully grasp the various data in the teaching collaboration process, thus making it impossible to adjust and optimize teaching strategies in a timely manner. Summary of the Invention

[0006] The purpose of this invention is to address the shortcomings of existing technologies by proposing a cloud-based online teaching collaborative management system and method.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] Design a cloud-based online teaching collaborative management system, including:

[0009] The multi-source data acquisition module is used to collect information on multiple participating entities in online teaching, teaching resource metadata, and collaborative scenario parameters from the multi-source data interface of the cloud platform, based on a pre-set list of teaching collaboration needs.

[0010] The candidate resource screening module is used to associate and store information of multiple participating entities, teaching resource metadata information and collaborative scenario parameter information in the collaborative database of the cloud platform, and to screen out candidate collaborative resource set data information that meet the basic collaborative conditions according to the preset threshold of participating entity type and resource adaptation rules.

[0011] The collaborative strategy generation module is used to dynamically generate personalized teaching collaborative strategies based on the candidate collaborative resource set, the real-time demand characteristics of multiple participating entities, and historical collaborative interaction data information through the reinforcement learning model built into the cloud platform.

[0012] The interactive channel allocation module is used to allocate interactive channels from the candidate collaborative resource set to multiple participating entities based on personalized teaching collaboration strategies.

[0013] The collaborative data acquisition module is used to collect data on resource usage, interaction records, and teaching effectiveness feedback from each participating entity during the collaborative process.

[0014] The collaborative history recording module is used to record the execution data of the personalized teaching collaboration strategy, the feedback information of the participating entities, and the full life cycle log of resource usage, forming a closed-loop history of the entire process of online teaching collaboration management.

[0015] Preferably, the multi-source data acquisition module includes:

[0016] The requirements list parsing unit is used to parse the preset teaching collaboration requirements list, determine the specific role types and identity fields covered by the information of the multiple participating entities to be collected, the resource categories and attribute tags included in the teaching resource metadata, and the key factors of time, space, and interaction mode in the collaboration scenario parameters.

[0017] The data channel positioning unit is used to accurately locate the corresponding data acquisition channel among the multi-source data interfaces of the cloud platform based on the parsing results, covering user management interface, resource storage interface and scenario configuration interface;

[0018] The data acquisition and processing unit is used to collect information on multiple participating entities, teaching resource metadata, and collaborative scenario parameters through the positioning interface, and to perform preliminary data processing.

[0019] The data encapsulation and temporary storage unit is used to encapsulate the processed data in a unified format and temporarily store it in a temporary storage area.

[0020] Preferably, the candidate resource screening module includes:

[0021] The associated data table creation unit is used to create associated data tables in the collaborative database of the cloud platform, and store the collected information of multiple participating entities, teaching resource metadata and collaborative scenario parameters in a one-to-one correspondence according to the preset association rules.

[0022] The participant classification and filtering unit is used to classify and filter the stored multi-party participant information according to the preset participant type threshold, and divide the participant into different types of participant sets;

[0023] The resource matching degree analysis unit is used to perform matching degree analysis on teaching resource metadata by using preset resource adaptation rules and combining collaborative scenario parameters;

[0024] The candidate resource set forming unit is used to select matching resources from the teaching resource metadata to form a candidate collaborative resource set that meets the basic collaborative conditions.

[0025] Preferably, the collaborative strategy generation module includes:

[0026] The resource feature extraction unit is used to extract features from the candidate collaborative resource set and clarify the attributes, availability and relationships of various resources;

[0027] The real-time demand analysis unit is used to analyze the real-time demand characteristics of multiple participating entities and determine their specific requirements in terms of resource type, quantity, and usage time.

[0028] The historical data mining unit is used to sort out the historical collaborative interaction data of multiple participating entities and to uncover their past interaction patterns, preferences, and issues.

[0029] The strategy generation unit is used to input the extracted feature weights, urgency of demand, preference, and matching degree into the reinforcement learning model built into the cloud platform to dynamically generate personalized teaching collaboration strategies.

[0030] Preferably, the interaction channel allocation module includes:

[0031] The strategy analysis unit is used to analyze personalized teaching collaboration strategies and determine the specific requirements for resource allocation priorities, interaction timing rules, and cross-subject collaboration permission configuration.

[0032] The resource matching unit is used to select resources from the candidate collaborative resource set according to the resource allocation priority, and to perform preliminary matching according to the type of participating entity and its needs;

[0033] The timing planning unit is used to combine interactive timing rules to plan the time sequence of resource usage for multiple participating entities.

[0034] The permission configuration unit is used to build corresponding interaction channels for participating entities based on cross-entity collaboration permission configuration, and to set the access permissions and functions of the channels;

[0035] The information push unit is used to push the matched resources and the information of the opened interaction channels to the corresponding multi-party participants through the cloud platform.

[0036] Preferably, the collaborative data acquisition module includes:

[0037] The data acquisition and deployment unit is used to deploy the data acquisition module in the cloud platform and set up corresponding monitoring points for the allocated resources and interaction channels.

[0038] The resource usage data acquisition unit is used to obtain real-time information on the use of allocated resources by each participating entity through monitoring points, thereby generating resource usage data.

[0039] The interactive operation recording unit is used to track and record the operation behavior of the participants in the interactive channel and generate interactive operation record data.

[0040] The teaching effectiveness feedback unit is used to design forms or interfaces for collecting teaching effectiveness feedback data, guiding participants to actively provide feedback on learning outcomes, satisfaction with resources and collaborative processes, and other information.

[0041] Preferably, the collaborative resume recording module includes:

[0042] The data recording system building unit is used to build a data recording system on the cloud platform and set up storage modules corresponding to the execution data of personalized teaching collaboration strategies, feedback information from participating entities, and the full lifecycle logs of resource usage.

[0043] The execution data selection unit is used to select various data records during the execution of personalized teaching collaboration strategies in real time as execution data;

[0044] The history generation unit is used to integrate and associate the above-mentioned execution data, feedback information, and resource usage lifecycle logs to form and store a closed-loop history of the entire online teaching collaborative management process.

[0045] Preferably, the data acquisition and processing unit includes a data cleaning subunit and a data conversion subunit. The data cleaning subunit is used to remove noise and redundant information from the acquired data, and the data conversion subunit is used to convert the cleaned data into a unified format.

[0046] Preferably, the strategy generation unit further includes a strategy optimization subunit, which is used to iteratively optimize the generated strategy based on real-time feedback data to improve the adaptability of the strategy to the actual scenario.

[0047] Preferably, the cloud-based online teaching collaborative management method includes the following steps:

[0048] Based on the pre-set list of collaborative teaching needs, information on multiple participating entities in online teaching, metadata of teaching resources, and parameters of collaborative scenarios are collected from the multi-source data interface of the cloud platform.

[0049] Information on multiple participating entities, teaching resource metadata, and collaborative scenario parameters are associated and stored in the collaborative database of the cloud platform. Based on preset thresholds for participating entity types and resource adaptation rules, candidate collaborative resource sets that meet the basic collaborative conditions are selected.

[0050] Based on the candidate collaborative resource set, the real-time demand characteristics of multiple participating entities, and historical collaborative interaction data, personalized teaching collaborative strategies are dynamically generated through the reinforcement learning model built into the cloud platform.

[0051] Based on personalized teaching collaboration strategies, interactive channels are allocated to the corresponding candidate collaboration resource sets for multiple participating entities;

[0052] Collect data on resource usage, interaction records, and teaching effectiveness feedback from all participating entities during the collaborative process;

[0053] Record the execution data of the personalized teaching collaboration strategy, the feedback information of the participating entities, and the full life cycle log of resource usage to form a closed-loop history of the entire process of online teaching collaboration management.

[0054] The online teaching collaborative management system and method based on a cloud platform proposed in this invention have the following advantages:

[0055] Improving the efficiency of collaborative teaching: This system comprehensively acquires key information in the online teaching process through multi-source data acquisition units, including information on multiple participating entities, teaching resource metadata, and collaborative scenario parameters, providing a rich data foundation for subsequent management. Through precise data positioning and preliminary processing, the system ensures the integrity and relevance of the data, thereby improving the efficiency and accuracy of collaborative teaching.

[0056] Optimize the allocation of teaching resources: The candidate resource screening unit can accurately select a set of candidate collaborative resources that meet the basic collaborative conditions based on the preset threshold of the participating subject type and resource adaptation rules. This process not only improves the efficiency of resource utilization, but also ensures the adaptability of the selected resources to the needs of the participating subjects and the collaborative scenario, providing appropriate resource support for personalized teaching collaboration.

[0057] Achieving personalized collaborative teaching: The collaborative strategy generation unit, leveraging a reinforcement learning model, can dynamically generate personalized collaborative teaching strategies. These strategies comprehensively consider candidate collaborative resource sets, the real-time needs of multiple participating entities, and historical collaborative interaction data, thus better meeting diverse requirements. Simultaneously, iterative optimization of strategy adaptability through real-time feedback data ensures the effectiveness and flexibility of the collaborative teaching strategies.

[0058] Ensuring a smooth collaborative process: Based on personalized teaching collaboration strategies, the interactive channel allocation unit assigns corresponding interactive channels for multiple participating entities to the corresponding candidate collaborative resource pool. By reasonably allocating resource priorities, planning the order of resource usage time, and setting cross-entity collaboration permissions, the smoothness of the collaborative process is ensured, and the fluency and effectiveness of teaching collaboration are improved.

[0059] Facilitating evaluation and traceability: The collaborative data acquisition unit collects resource usage data, interaction records, and teaching effectiveness feedback data from each participant in real time during the collaborative process, providing rich data support for a comprehensive evaluation of the teaching collaboration effect. At the same time, the collaborative history recording unit fully records the execution data of personalized teaching collaboration strategies, feedback information from participating entities, and resource usage lifecycle logs, forming a closed-loop history of the entire online teaching collaboration management process. This facilitates the traceability and analysis of the teaching collaboration process, the summarization of experiences and lessons learned, and provides a strong basis for the optimization and improvement of subsequent teaching collaboration.

[0060] Promoting the development of educational informatization: The implementation of this system has promoted the development of educational informatization to a higher level, realizing efficient, accurate, flexible and traceable online teaching collaborative management based on the cloud platform. This not only improves teaching quality and efficiency, but also promotes the balanced distribution of educational resources and the satisfaction of personalized teaching needs, providing strong support for cultivating innovative talents. Attached Figure Description

[0061] Figure 1 This is an overall flowchart of an online teaching collaborative management system and method based on a cloud platform proposed in this invention.

[0062] Figure 2 for Figure 1 A schematic diagram of the data acquisition and processing flow of a cloud-based online teaching collaborative management system and method is presented.

[0063] Figure 3 for Figure 1 A schematic diagram of the candidate resource screening and collaborative strategy generation process of a cloud-based online teaching collaborative management system and method is presented.

[0064] Figure 4 for Figure 1 A schematic diagram of the interactive channel allocation and collaborative data collection process of a cloud-based online teaching collaborative management system and method is presented. Detailed Implementation

[0065] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0066] Reference Figure 1-4 A cloud-based online teaching collaborative management system, comprising:

[0067] Multi-source data acquisition unit: Based on the pre-set list of teaching collaboration needs, it collects information on multiple participating entities in online teaching, metadata of teaching resources, and parameters of collaborative scenarios from the multi-source data interface of the cloud platform;

[0068] The teaching collaboration requirements list is a pre-defined list that clarifies the types and scope of data to be collected during online teaching collaboration, providing guidance for data collection. Multi-source data interfaces are interfaces on the cloud platform that connect to various data sources, enabling data access and allowing the acquisition of online teaching-related data from different channels. Information on multiple participating entities includes basic information and role information of all parties involved in online teaching (such as teachers, students, and administrators). Teaching resource metadata information is descriptive data about teaching resources (such as courseware, videos, and documents), including resource type, size, creation time, and author. Collaboration scenario parameter information reflects the characteristics of the online teaching collaboration scenario, such as teaching time, teaching location (virtual or real), and teaching scale.

[0069] Candidate resource screening unit: It associates and stores information of multiple participating entities, teaching resource metadata information and collaborative scenario parameter information in the collaborative database of the cloud platform, and filters out candidate collaborative resource set data information that meet the basic collaborative conditions according to the preset threshold of participating entity type and resource adaptation rules.

[0070] Specifically: The collaborative database is a dedicated database on the cloud platform for storing data related to online teaching collaboration, providing support for data storage, retrieval, and management. The participant type threshold is a standard boundary used to classify different participant types. Resource adaptation rules define the matching relationships between teaching resources and participant types, collaborative scenarios, etc., used to filter suitable resources. The candidate collaborative resource set data information is a set of resources that, after filtering, meet the basic collaboration conditions and are available for further collaborative use.

[0071] Collaborative strategy generation unit: Based on the candidate collaborative resource set, the real-time demand characteristics of multiple participating entities, and historical collaborative interaction data, the unit dynamically generates personalized teaching collaborative strategies through the reinforcement learning model built into the cloud platform. The personalized teaching collaborative strategies include resource allocation priority, interaction timing rules, and cross-entity collaborative permission configuration. The reinforcement learning model iteratively optimizes the strategy adaptability through real-time feedback data.

[0072] The candidate collaborative resource set is a collection of resources comprised of candidate collaborative resource set data, serving as the foundation for generating collaborative strategies. Real-time demand characteristics refer to the specific needs of multiple participating entities regarding teaching resources and interaction methods at the current moment. Historical collaborative interaction data includes records of interactions and resource usage among participating entities during past online teaching collaborations. The reinforcement learning model is a machine learning model built into the cloud platform that continuously adjusts its parameters by receiving real-time feedback data to optimize the generated strategy. Personalized teaching collaboration strategies are specific teaching collaboration schemes generated based on the aforementioned resources, demands, and historical data, tailored to different participating entities and collaborative scenarios. These include resource allocation priorities, interaction timing rules, and cross-entity collaboration permission configurations. Resource allocation priorities are the order in which different participating entities or resource needs are prioritized during resource allocation. Interaction timing rules define the time sequence and rhythm of interactions between participating entities. Cross-entity collaboration permission configuration sets permissions for collaboration between different participating entities, clarifying the operational scope and permissions of each entity in the collaboration process. Strategy fit is the degree to which personalized teaching collaboration strategies match the actual online teaching collaboration scenarios and the needs of participating entities. It is evaluated and optimized through real-time feedback data.

[0073] Interactive channel allocation unit: Based on personalized teaching collaboration strategies, allocate corresponding interactive channels from the candidate collaborative resource set to multiple participating entities;

[0074] This includes specific channels or methods provided for collaborative activities such as information exchange and resource sharing among multiple participating entities, such as online chat tools and shared document platforms.

[0075] Collaborative Data Acquisition Unit: Collects resource usage data, interaction operation records, and teaching effect feedback data of each participating entity during the collaboration process. Resource usage data and interaction operation records are generated based on allocated resources and interaction channels.

[0076] Specifically: Resource usage data comprises data generated by each participant during the use of allocated teaching resources, such as the number of resource accesses, usage duration, and download counts. Interaction operation records are detailed records of various interactive operations performed by participants during the collaboration process, such as speech content, operation steps, and collaborative actions. Teaching effectiveness feedback data includes participants' evaluations, opinions, and suggestions regarding teaching effectiveness, used to assess the quality and effectiveness of collaborative teaching.

[0077] Collaborative history recording unit: Records the execution data of the personalized teaching collaboration strategy, feedback information from participating entities, and resource usage lifecycle logs, forming a closed-loop history of the entire online teaching collaboration management process.

[0078] The data includes: Personalized teaching collaboration strategy execution data, which records various data points during the actual implementation of personalized teaching collaboration strategies, such as the execution time, steps, and effects; participant feedback information, which includes feedback and evaluations from participants regarding the collaboration strategy, process, and teaching resources; a resource usage lifecycle log, which records detailed information about teaching resources throughout their entire lifecycle, from creation and use to destruction, including creation time, modification records, and usage status; and a closed-loop history of online teaching collaboration management, which comprehensively records the entire process from start to finish, forming a complete closed-loop management record for easy traceability and analysis.

[0079] This design achieves the following: a multi-source data acquisition unit comprehensively acquires key information, providing a rich data foundation for subsequent management; a candidate resource screening unit accurately selects suitable resources, improving resource utilization efficiency; a collaborative strategy generation unit dynamically generates personalized strategies using reinforcement learning models, better meeting diverse needs and iteratively optimizing; an interaction channel allocation unit rationally allocates channels according to strategies, ensuring smooth collaboration; a collaborative data acquisition unit collects various types of data in real time, facilitating the evaluation of collaborative effects; and a collaborative history recording unit fully records the entire process, forming a closed-loop history, which is conducive to traceability analysis and experience summarization, ultimately realizing efficient, accurate, flexible, and traceable online teaching collaborative management based on a cloud platform.

[0080] In one embodiment, the multi-source data acquisition unit step includes:

[0081] The pre-set list of collaborative teaching needs is analyzed to determine the specific role types and identity fields covered by the information of the multiple participating entities that need to be collected, the resource categories and attribute tags included in the teaching resource metadata, and the key factors of time, space, and interaction mode in the collaborative scenario parameters.

[0082] Based on the analysis results, the corresponding data acquisition channels are accurately located in the multi-source data interfaces of the cloud platform, covering user management interface, resource storage interface and scenario configuration interface;

[0083] Through the positioning interface, information on multiple participating entities, teaching resource metadata, and collaborative scenario parameters are collected and preliminary data processing is performed.

[0084] The processed data is packaged in a uniform format and temporarily stored in a temporary storage area.

[0085] The benefits are as follows: By accurately analyzing the list of teaching collaboration needs, we can comprehensively and accurately locate the data acquisition channels, ensuring that the collected information on multiple participating entities, teaching resource metadata, and collaboration scenario parameters are complete and targeted; preliminary data processing and unified format packaging improve the standardization and usability of the data, providing a high-quality data foundation for subsequent analysis, which helps to more accurately understand the various elements in teaching collaboration and improve the overall efficiency and accuracy of teaching collaboration.

[0086] In one embodiment, the candidate resource screening unit step includes:

[0087] Create associated data tables in the collaborative database of the cloud platform, and store the collected information of multiple participating entities, teaching resource metadata and collaborative scenario parameters according to the preset association rules to ensure that the logical connection between the data is clear and searchable.

[0088] Based on a preset threshold for participant types, the stored information on multiple participating entities is categorized and filtered to create different types of participant sets. The formula for determining the participant type is as follows:

[0089]

[0090] In the formula: For the first The type of participating subject and the result For the first Participating entities set tags, For the first The weights of each principal attribute, , For the first The first subject Each attribute value (normalized to) , For the first The type threshold of the class body;

[0091] Data statistics: Collected attribute scores of various subjects (teachers, students, administrators) over the past year. The initial threshold is calculated as the "mean + 0.5 standard deviation" of the score for each subject category. .

[0092] Expert calibration: Invite 2-3 teaching management experts to verify the initial threshold. If the misjudgment rate of a certain type of subject is >10%, then adjust the threshold ±0.05.

[0093] Dynamic updates: The score distribution is recalculated and the thresholds are updated every quarter to ensure that the false positive rate is below 8%.

[0094] Example: If the initial scores for the teacher category are mean 0.7 and standard deviation 0.1, then... = 0.7 + 0.5 * 0.1 = 0.75.

[0095] Using the Analytic Hierarchy Process (AHP): Invite 3-5 online teaching management experts to score the importance of subject attributes (such as teachers' "teaching qualifications" and "taught subjects", students' "grade" and "major", and administrators' "management authority" and "responsible modules") on a 1-9 level to construct a judgment matrix.

[0096] Consistency check: Calculate the consistency ratio CR of the judgment matrix. CR should be < 0.1. If this is not met, experts should be invited to adjust the scores again until the check is passed.

[0097] Data validation and optimization: Based on the main classification data of the past 3 months, calculate the classification accuracy under the weight of each attribute. If the accuracy is lower than 85%, the weights are fine-tuned (the adjustment range does not exceed ±0.1) to ensure accurate classification.

[0098] Constraint: Sum of weights of all attributes Each core attribute should have a weight of no less than 0.2 (e.g., a teacher's "teaching qualifications" or a student's "major").

[0099] Using preset resource adaptation rules and combined with collaborative scenario parameters, a matching degree analysis is performed on the teaching resource metadata;

[0100]

[0101] In the formula: For the first Class subject and the first The matching degree of each resource, with values... , These are the weighting coefficients, and , For resources With the Class subject requirements cosine similarity, For resources Collaborative Scenarios The adaptation coefficient, For resources Real-time availability;

[0102] Scenario Classification and Assignment: Online teaching collaboration scenarios are divided into 3 categories, with preset basic weights, as shown in Table 1:

[0103] Collaborative Scenarios (Demand similarity weight) (Scene adaptation weight) (Resource availability weight) Formal teaching 0.3 0.5 0.2 Self-directed learning 0.5 0.2 0.3 Group collaboration task 0.4 0.4 0.2

[0104] Table 1

[0105] Historical data iteration: Quarterly statistics on "matching degree" under different scenarios Overall score of teaching effectiveness The correlation between a weighted factor and teaching effectiveness is assessed. If the correlation between a weighted factor and teaching effectiveness is less than 0.3, the weight is adjusted by ±0.1, while ensuring... .

[0106] Constraints: All values ​​are ∈ [0.2, 0.5], to avoid a single factor dominating the matching results.

[0107] Filter the matching degree from the metadata of teaching resources. Resources To preset the basic matching threshold, This forms a candidate collaborative resource set that meets the basic collaborative conditions. .

[0108] The advantages are: creating related data tables to store data ensures clear logical connections between data, making it easy to query and manage; classifying and filtering participating entities and analyzing matching degree teaching resources can quickly filter out candidate resource sets that meet the basic collaborative conditions from massive resources, improving resource filtering efficiency and ensuring that the selected resources are compatible with the needs of participating entities and collaborative scenarios, providing appropriate resource support for personalized teaching collaboration.

[0109] In one embodiment, the cooperative strategy generation unit step includes:

[0110] Feature extraction is performed on the candidate collaborative resource set to clarify the attributes, availability, and relationships of various resources. The resource feature weights are calculated using the entropy weight method.

[0111]

[0112]

[0113] In the formula: For the first The weight of each resource feature, For the first Information entropy of each feature For the first The feature in the first The proportion in each sample The number of feature samples;

[0114] Feature preprocessing: Normalize resource features (such as type, size, creation time, author) and remove redundant features (such as features with a correlation of less than 0.2 with resource suitability).

[0115] Entropy weight calculation: Calculate the entropy of each feature information according to the formula in the data. Then derive the weights .

[0116] Consistency check: Calculate the consistency ratio (CR) of the feature weights, requiring CR < 0.1; if it fails, delete 1-2 features with the highest information entropy (lowest discrimination), and recalculate until the check passes.

[0117] Constraints: The weight of a single feature shall not exceed 0.4, and over-reliance on a single feature shall be avoided.

[0118] Analyze the real-time demand characteristics of multiple participating entities to determine their specific requirements in terms of resource type, quantity, and usage time. The formula for quantifying demand urgency is as follows:

[0119]

[0120] In the formula: for The urgency of the needs of the subject The smaller the size, the higher the urgency. The deadline for the request. Current time, For the collaborative cycle.

[0121] We analyzed historical collaborative interaction data from multiple participating entities to uncover their past interaction patterns, preferences, and issues; the formula for calculating entity preference is as follows:

[0122]

[0123] In the formula, For the first Class subject to the first Preference for similar resources For historical usage counts, This represents the historical average usage time.

[0124] The extracted feature weights Urgency of demand Preference and matching degree Input the reinforcement learning model built into the cloud platform.

[0125] The reinforcement learning model dynamically generates personalized teaching collaboration strategies based on input information, covering resource allocation priorities, interaction timing rules, and cross-subject collaboration permission configuration; among them, the immediate reward function of reinforcement learning is:

[0126]

[0127] In the formula, for The reward value at any moment, To improve resource utilization, For the main body's interaction satisfaction, For resource conflict rate, , , As a reward weight.

[0128] Combinatorial assignment method: Five educational technology experts were invited to conduct a comprehensive evaluation. (Resource utilization rate) (Interaction satisfaction) The importance score of (resource conflict rate) is used as the initial subjective weight, and the average value is taken.

[0129] Entropy weight correction: Based on the reward data of the past 6 months, the information entropy of each factor is calculated, and the subjective weights are corrected to reduce subjective bias.

[0130] Dynamic adjustment: If the resource conflict rate is high in 3 consecutive iterations... >0.3”, then improve Up to 0.4-0.5; if "resource utilization rate" If the value is less than 0.5, then increase the value. To ensure real-time coordination of weight adaptation, the weight should be adjusted to 0.4-0.5.

[0131] Constraints: , , ∈[0.2,0.5], and .

[0132] Based on real-time feedback data, the generated strategy is iteratively optimized to improve its adaptability to the actual scenario. The optimization formula is as follows:

[0133]

[0134] In the formula, The optimized strategy, For action, (for state) For learning rate , For policy gradient, For feedback adjustment coefficient, Based on historical average reward values, improve the adaptability of strategies to real-world scenarios.

[0135] Learning rate Initial value: 0.05 (to balance convergence speed and stability).

[0136] Dynamic adjustment: If the "fit improvement rate is less than 1%" in 5 consecutive strategy iterations, then... Increase to 0.08-0.1; if the fitness fluctuation range during iteration is > 5% (oscillation), then Reduced to 0.01-0.03.

[0137] Feedback adjustment coefficient Initial value: 0.2.

[0138] Dynamic adjustment: If (If the real-time reward deviates significantly from the historical average reward), then... ;like (Small deviation) .

[0139] The advantages are: extracting resource characteristics, analyzing subject needs, and mining historical data, comprehensively considering multiple factors of teaching collaboration; strengthening the dynamic generation of personalized strategies by the learning model, covering multiple configurations such as resource allocation, and iteratively optimizing based on real-time feedback, making the strategies more in line with actual scenarios, improving the personalization and adaptability of teaching collaboration, and enhancing resource utilization and subject interaction satisfaction.

[0140] In one embodiment, the interactive channel allocation unit step includes:

[0141] This study analyzes personalized teaching collaboration strategies and determines specific requirements for resource allocation priorities, interaction timing rules, and cross-subject collaboration permission configurations. The resource allocation priority scoring formula is as follows:

[0142]

[0143] In the formula: For the first Class body corresponds to the first Each resource has a priority score; the higher the score, the higher the priority. Priority weights, ;

[0144] The subject type adaptation is shown in Table 2:

[0145] Main type (Matching degree) (Preference level) ( (urgency) (Resource characteristics) student 0.2 0.3 0.3 0.2 teacher 0.3 0.2 0.2 0.3 Management personnel 0.3 0.1 0.3 0.3

[0146] Table 2

[0147] Iterative optimization: Monthly statistics of "priority score" The correlation with "resource usage satisfaction" is assessed. If the correlation of a factor corresponding to a certain weight is less than 0.25, the weight is adjusted by ±0.05 to ensure that the total weight is 1.

[0148] Constraints: Individual weights must be no less than 0.1 and no more than 0.35.

[0149] Based on resource allocation priority, select from the candidate collaborative resource set Resources Priority thresholds are set, and initial matching is performed based on the type of participating entity and its needs;

[0150] By combining interaction timing rules, the time sequence of resource usage is planned for multiple participating entities to ensure the orderly progress of the collaborative process. The timing scheduling formula is as follows:

[0151]

[0152] in:

[0153] In the formula, For the first Class body uses the first The time window for each resource The start time, End time, as the main body Resources Demand duration coefficient, For resources Standard usage time;

[0154] Based on cross-entity collaboration permission configuration This involves creating corresponding interaction channels for participating entities, setting access permissions and functions for these channels, where the elements of the permission matrix are defined as follows:

[0155]

[0156] In the formula: For the first Individual entities Permission levels for each resource interaction channel;

[0157] The matched resources and the information on the opened interaction channels are pushed to the corresponding participating entities through the cloud platform to complete the allocation.

[0158] The advantages are: based on personalized strategies to determine specific requirements, resource priorities are reasonably allocated through scoring formulas, the order of resource usage is planned in combination with time-series rules, and the permission matrix sets the permissions of interactive channels, ensuring that the collaborative process is orderly, efficient and secure; push matching resources and channel information so that multiple parties can clearly obtain the content they need, improving the smoothness and effectiveness of teaching collaboration.

[0159] In one embodiment, the collaborative data acquisition unit steps include:

[0160] Deploy a data acquisition module in the cloud platform and set up corresponding monitoring points for the allocated resources and interaction channels;

[0161] The system monitors real-time data on resource usage by each participant, including resource access time, usage duration, and usage frequency, generating resource usage data. The formula for calculating resource usage efficiency is as follows:

[0162]

[0163] In the formula: For the first Class subject to the first Resource utilization efficiency For effective usage time, To allocate time, This refers to the access frequency per unit of time.

[0164] The interactive behaviors of participating entities are tracked and recorded, covering the type of operation, the object of operation, and the order of operation, generating interactive operation record data. The formula for measuring interactive behavior activity is as follows:

[0165]

[0166] In the formula: For the first The interaction activity of the class subject, normalized to , This represents the total number of operation types. For the first Class subject to the first The number of times the class operation is executed. For all subjects, the first The maximum number of times a class operation can be executed;

[0167] Design forms or interfaces for collecting teaching effectiveness feedback data, guiding participants to proactively provide feedback on learning outcomes, satisfaction with resources and the collaborative process, etc.; the comprehensive scoring formula for teaching effectiveness is as follows:

[0168]

[0169] In the formula: For the first Overall score of teaching effectiveness for each subject , To determine the score for the learning outcome test, Rate the satisfaction level. To achieve the learning progress completion rate, As the scoring weight, .

[0170] The adaptation of teaching stages is shown in Table 3:

[0171] Teaching stage (Test score) (Satisfaction level) (Progress completion rate) New teaching phase 0.3 0.4 0.3 Review and consolidation stage 0.5 0.2 0.3 Assessment and evaluation stage 0.6 0.2 0.2

[0172] Table 3

[0173] Data validation: Based on historical teaching effectiveness data, the Pearson correlation coefficient between each factor and "actual learning outcomes" was calculated. Higher correlation coefficients corresponded to higher weightings. Adjustments were made to ensure... (k=1-3).

[0174] Constraints: ≥0.3, to avoid neglecting core indicators of learning outcomes.

[0175] The collected resource utilization efficiency Interaction activity Overall score of teaching effectiveness The collected raw data information is organized and stored according to a preset format.

[0176] The advantages are: deploying data collection modules and setting up monitoring points can obtain real-time information on the use of resources and interaction records of participating entities, and quantify usage efficiency and interaction activity through relevant formulas; designing feedback forms to collect teaching effectiveness data, organizing and storing it according to preset formats, provides rich data for a comprehensive evaluation of teaching collaboration effects, and helps to identify problems and improve teaching.

[0177] In one embodiment, the collaborative resume recording unit step includes:

[0178] Build a data recording system on the cloud platform and set up storage modules corresponding to the execution data of personalized teaching collaboration strategies, feedback information from participating entities, and the full lifecycle logs of resource usage.

[0179] Real-time selection of various data records during the implementation of personalized teaching collaboration strategies as execution data;

[0180] The aforementioned execution data, feedback information, and resource usage lifecycle logs are integrated and linked to form a closed-loop history of the entire online teaching collaborative management process, which is then stored.

[0181] The advantages are: By establishing a data recording system and setting up corresponding storage modules, it is possible to select and integrate execution data, feedback information, and resource logs in real time, forming and storing a closed-loop history of the entire online teaching collaboration management process. This helps to trace the teaching collaboration process, summarize lessons learned, and provide a strong basis for the optimization and improvement of subsequent teaching collaboration.

[0182] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A cloud-based online teaching collaborative management system, characterized in that, include: The multi-source data acquisition module is used to collect information on multiple participating entities in online teaching, teaching resource metadata, and collaborative scenario parameters from the multi-source data interface of the cloud platform, based on a pre-set list of teaching collaboration needs. The candidate resource screening module is used to associate and store information of multiple participating entities, teaching resource metadata information and collaborative scenario parameter information in the collaborative database of the cloud platform, and to screen out candidate collaborative resource set data information that meet the basic collaborative conditions according to the preset threshold of participating entity type and resource adaptation rules. The collaborative strategy generation module is used to dynamically generate personalized teaching collaborative strategies based on the candidate collaborative resource set, the real-time demand characteristics of multiple participating entities, and historical collaborative interaction data information through the reinforcement learning model built into the cloud platform. The interactive channel allocation module is used to allocate interactive channels from the candidate collaborative resource set to multiple participating entities based on personalized teaching collaboration strategies. The collaborative data acquisition module is used to collect data on resource usage, interaction records, and teaching effectiveness feedback from each participating entity during the collaborative process. The collaborative history recording module is used to record the execution data of the personalized teaching collaboration strategy, the feedback information of the participating entities, and the full life cycle log of resource usage, forming a closed-loop history of the entire process of online teaching collaboration management.

2. The cloud-based online teaching collaborative management system according to claim 1, characterized in that, The multi-source data acquisition module includes: The requirements list parsing unit is used to parse the preset teaching collaboration requirements list, determine the specific role types and identity fields covered by the information of the multiple participating entities to be collected, the resource categories and attribute tags included in the teaching resource metadata, and the key factors of time, space, and interaction mode in the collaboration scenario parameters. The data channel positioning unit is used to accurately locate the corresponding data acquisition channel among the multi-source data interfaces of the cloud platform based on the parsing results, covering user management interface, resource storage interface and scenario configuration interface; The data acquisition and processing unit is used to collect information on multiple participating entities, teaching resource metadata, and collaborative scenario parameters through the positioning interface, and to perform preliminary data processing. The data encapsulation and temporary storage unit is used to encapsulate the processed data in a unified format and temporarily store it in a temporary storage area.

3. The cloud-based online teaching collaborative management system according to claim 1, characterized in that, The candidate resource filtering module includes: The associated data table creation unit is used to create associated data tables in the collaborative database of the cloud platform, and store the collected information of multiple participating entities, teaching resource metadata and collaborative scenario parameters in a one-to-one correspondence according to the preset association rules. The participant classification and filtering unit is used to classify and filter the stored multi-party participant information according to the preset participant type threshold, and divide the participant into different types of participant sets; The resource matching degree analysis unit is used to perform matching degree analysis on teaching resource metadata by using preset resource adaptation rules and combining collaborative scenario parameters; The candidate resource set forming unit is used to select matching resources from the teaching resource metadata to form a candidate collaborative resource set that meets the basic collaborative conditions.

4. The cloud-based online teaching collaborative management system according to claim 1, characterized in that, The collaborative strategy generation module includes: The resource feature extraction unit is used to extract features from the candidate collaborative resource set and clarify the attributes, availability and relationships of various resources; The real-time demand analysis unit is used to analyze the real-time demand characteristics of multiple participating entities and determine their specific requirements in terms of resource type, quantity, and usage time. The historical data mining unit is used to sort out the historical collaborative interaction data of multiple participating entities and to uncover their past interaction patterns, preferences, and issues. The strategy generation unit is used to input the extracted feature weights, urgency of demand, preference, and matching degree into the reinforcement learning model built into the cloud platform to dynamically generate personalized teaching collaboration strategies.

5. The cloud-based online teaching collaborative management system according to claim 1, characterized in that, The interaction channel allocation module includes: The strategy analysis unit is used to analyze personalized teaching collaboration strategies and determine the specific requirements for resource allocation priorities, interaction timing rules, and cross-subject collaboration permission configuration. The resource matching unit is used to select resources from the candidate collaborative resource set according to the resource allocation priority, and to perform preliminary matching according to the type of participating entity and its needs; The timing planning unit is used to combine interactive timing rules to plan the time sequence of resource usage for multiple participating entities. The permission configuration unit is used to build corresponding interaction channels for participating entities based on cross-entity collaboration permission configuration, and to set the access permissions and functions of the channels; The information push unit is used to push the matched resources and the information of the opened interaction channels to the corresponding multi-party participants through the cloud platform.

6. The cloud-based online teaching collaborative management system according to claim 1, characterized in that, The collaborative data acquisition module includes: The data acquisition and deployment unit is used to deploy the data acquisition module in the cloud platform and set up corresponding monitoring points for the allocated resources and interaction channels. The resource usage data acquisition unit is used to obtain real-time information on the use of allocated resources by each participating entity through monitoring points, thereby generating resource usage data. The interactive operation recording unit is used to track and record the operation behavior of the participants in the interactive channel and generate interactive operation record data. The teaching effectiveness feedback unit is used to design forms or interfaces for collecting teaching effectiveness feedback data, guiding participants to actively provide feedback on learning outcomes, satisfaction with resources and collaborative processes, and other information.

7. The cloud-based online teaching collaborative management system according to claim 1, characterized in that, The collaborative resume recording module includes: The data recording system building unit is used to build a data recording system on the cloud platform and set up storage modules corresponding to the execution data of personalized teaching collaboration strategies, feedback information from participating entities, and the full lifecycle logs of resource usage. The execution data selection unit is used to select various data records during the execution of personalized teaching collaboration strategies in real time as execution data; The history generation unit is used to integrate and associate the above-mentioned execution data, feedback information, and resource usage lifecycle logs to form and store a closed-loop history of the entire online teaching collaborative management process.

8. The cloud-based online teaching collaborative management system according to claim 2, characterized in that, The data acquisition and processing unit includes a data cleaning subunit and a data conversion subunit. The data cleaning subunit is used to remove noise and redundant information from the acquired data, and the data conversion subunit is used to convert the cleaned data into a unified format.

9. The cloud-based online teaching collaborative management system according to claim 4, characterized in that, The strategy generation unit also includes a strategy optimization subunit, which is used to iteratively optimize the generated strategy based on real-time feedback data to improve the adaptability of the strategy to the actual scenario.

10. A cloud-based collaborative management method for online teaching according to any one of claims 1-9, characterized in that, Includes the following steps: Based on the pre-set list of collaborative teaching needs, information on multiple participating entities in online teaching, metadata of teaching resources, and parameters of collaborative scenarios are collected from the multi-source data interface of the cloud platform. Information on multiple participating entities, teaching resource metadata, and collaborative scenario parameters are associated and stored in the collaborative database of the cloud platform. Based on preset thresholds for participating entity types and resource adaptation rules, candidate collaborative resource sets that meet the basic collaborative conditions are selected. Based on the candidate collaborative resource set, the real-time demand characteristics of multiple participating entities, and historical collaborative interaction data, personalized teaching collaborative strategies are dynamically generated through the reinforcement learning model built into the cloud platform. Based on personalized teaching collaboration strategies, interactive channels are allocated to the corresponding candidate collaboration resource sets for multiple participating entities; Collect data on resource usage, interaction records, and teaching effectiveness feedback from all participating entities during the collaborative process; Record the execution data of the personalized teaching collaboration strategy, the feedback information of the participating entities, and the full life cycle log of resource usage to form a closed-loop history of the entire process of online teaching collaboration management.

Images