Distributed education collaborative control method and device

Abstract

This application discloses a distributed educational collaborative control method and device. Upon receiving a user's teaching service request, it generates scheduling instructions and controls a target capability clone module to execute the scheduling task. Simultaneously, it collects feature data transmitted back during the execution of the scheduling task in real time. By mining this continuous and dynamic feature data, it generates teaching pattern data reflecting the learner's real-time cognitive state and behavioral patterns. This data, combined with a preset profile, generates an adaptive service plan. By combining teaching pattern data and preset profiles to generate an adaptive service plan, the distributed education system can keenly capture the characteristics of classroom interaction and real-time assessment, and adjust recommendation strategies in a timely manner. This provides more timely, adaptive, and sensitive learning support, significantly improving the accuracy of personalized education services and user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of education management, and particularly relates to a distributed education collaborative control method and device. BACKGROUND

[0002] With the deepening of the digital transformation of education, distributed education systems gradually build an open and collaborative learning support environment by connecting and integrating multiple heterogeneous teaching resources and service modules. This system architecture aims to provide learners with more flexible, open, and personalized learning paths and experiences, meeting the needs of different backgrounds and learning paces. However, most current systems still rely on static pre-set user profiles when implementing personalized recommendations, i.e., matching content based on relatively fixed labels such as initial registration information and historical course selection records, making it difficult to continuously analyze and immediately optimize dynamic teaching interaction data such as classroom interaction, real-time evaluation, and discussion participation. This results in a lag between the recommended solution and the learner's current learning state and cognitive changes, lacking sufficient adaptability and sensitivity. SUMMARY

[0003] Therefore, the present application provides a distributed education collaborative control method and device.

[0004] The specific technical scheme of the first embodiment of the present application is as follows: a distributed education collaborative control method applied to an intelligent hub module in a distributed education system, the method comprising: receiving a teaching service request initiated by a user at an interactive entry module in the distributed education system, and generating a scheduling instruction corresponding to the teaching service request; controlling a target capability avatar module in the distributed education system corresponding to the scheduling instruction to execute a scheduling task corresponding to the scheduling instruction; receiving feature data returned by the target capability avatar module executing the scheduling task; data mining the feature data to generate teaching rule data of the user; generating an adaptive service scheme based on the user's pre-set profile and the teaching rule data, and feeding back the adaptive service scheme to the user.

[0005] Preferably, the feature data includes teaching theme feature data corresponding to the user, personal knowledge marking data, and behavior pattern feature data changing over time, and achievement quality evaluation data; the data mining of the feature data to generate the teaching rule data of the user comprises: generating first rule data representing the professional ability growth trajectory of the user according to the achievement quality evaluation data and the change trend of the behavior pattern feature data over time; clustering the teaching theme feature data according to the personal knowledge marking data to generate second rule data representing the personal teaching mode of the user; and the first rule data and the second rule data constitute the teaching rule data.

[0006] Preferably, the method further comprises: updating the preset portrait of the user according to the teaching theme feature data and the personal knowledge mark data to obtain an updated portrait; and generating the adaptive service scheme based on the preset portrait of the user and the teaching rule data comprises: generating the adaptive service scheme based on the updated portrait of the user and the teaching rule data.

[0007] Preferably, the teaching theme feature data comprises teaching reflection content and teaching notes, and the personal knowledge mark data comprises feature tags of teaching core works; and the updating of the preset portrait of the user according to the teaching theme feature data and the personal knowledge mark data to obtain an updated portrait comprises: characterizing teaching style, knowledge state vectors and theme interest weights in the preset portrait of the user according to the teaching reflection content, the teaching notes and the feature tags of the teaching core works to obtain the updated portrait.

[0008] Preferably, the generating of the adaptive service scheme based on the updated portrait of the user and the teaching rule data comprises: extracting at least one to-be-strengthened knowledge point and at least one to-be-associated knowledge point from a preset teaching resource knowledge graph according to the knowledge state vectors in the updated portrait; generating a knowledge point activation path with time constraints for the to-be-strengthened knowledge point and the to-be-associated knowledge point according to a preset knowledge mastery time sequence graph; matching a teaching style in the updated portrait for each knowledge point node in the knowledge point activation path according to the theme interest weights in the updated portrait and the teaching rule data; and generating the adaptive service scheme according to the knowledge point nodes matched with the teaching style and the knowledge mastery time sequence graph.

[0009] Preferably, the generating of the dispatching instruction corresponding to the teaching service request comprises: performing intent and theme identification on the teaching service request, and generating the dispatching instruction corresponding to the teaching service request according to the identified teaching intent and teaching theme.

[0010] Preferably, the method further comprises: simulating a service task corresponding to the adaptive service scheme, and feeding back an execution result after the simulation of the service task to the user.

[0011] The specific technical scheme of the second embodiment of the present application is: a distributed education collaborative control system, comprising: an instruction generation receiving module, an execution module, a feedback module, a teaching law data acquisition module and a scheme output module; the instruction generation receiving module is used for receiving a teaching service request initiated by a user in an interactive entry module of the distributed education system, and generating a scheduling instruction corresponding to the teaching service request; the execution module is used for controlling a target capability avatar module corresponding to the scheduling instruction in the distributed education system to execute a scheduling task corresponding to the scheduling instruction; the feedback module is used for receiving feature data fed back by the target capability avatar module at different moments of executing the scheduling task; the teaching law data acquisition module is used for generating teaching law data of the user by data mining on the feature data; and the scheme output module is used for generating an adaptive service scheme based on a preset portrait of the user and the teaching law data, and feeding back the adaptive service scheme to the user.

[0012] The specific technical scheme of the third embodiment of the present application is: a distributed education collaborative control device, comprising a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the method in any one of the first embodiments of the present application.

[0013] The specific technical scheme of the fourth embodiment of the present application is: a computer readable storage medium, storing a computer program, the computer program is executed by the processor to make the processor execute the steps of the method in any one of the first embodiments of the present application.

[0014] The present application has the following beneficial effects: The present application generates a scheduling instruction and controls a target capability avatar module to execute a scheduling task after receiving a user teaching service request, simultaneously collects feature data fed back in a scheduling task execution process in real time, mines these continuous dynamic feature data to generate teaching law data reflecting real-time cognitive state and behavior pattern of learners, and then generates an adaptive service scheme in combination with a preset portrait. The adaptive service scheme is generated in combination with the teaching law data and the preset portrait, so that the distributed education system can sensitively capture characteristics of classroom interaction, real-time evaluation and other links, timely adjust a recommendation strategy, thereby being able to provide learning support with timeliness, adaptability and sensitivity, and significantly improve the accuracy of personalized education service and user experience. BRIEF DESCRIPTION OF DRAWINGS

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating the steps of a distributed collaborative control method for education. Figure 2 This is a schematic diagram of the structure of a distributed educational collaborative control system; Figure 3 This is a diagram of the internal structure of a computer device. Among them, 201 is the instruction generation and receiving module; 202 is the execution module; 203 is the feedback module; 204 is the teaching pattern data acquisition module; and 205 is the scheme output module. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] The terms "first," "second," etc., used in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to such processes, methods, products, or apparatus.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] Please see Figure 1The above is a flowchart of the steps of the distributed education collaborative control method in the first embodiment of this application. It is applied to the intelligent central module of a distributed education system to improve the accuracy of personalized education services. The distributed education collaborative control method includes: Step 101: Receive a teaching service request initiated by the user in the interactive entry module of the distributed education system, and generate a scheduling instruction corresponding to the teaching service request; Step 102: Control the target capability clone module corresponding to the scheduling instruction in the distributed education system to execute the scheduling task corresponding to the scheduling instruction; Step 103: Receive the feature data returned by the target capability clone module when executing the scheduling task; Step 104: Perform data mining on the feature data to generate the user's teaching pattern data; Step 105: Generate an adaptive service plan based on the user's preset profile and the teaching pattern data, and feed the adaptive service plan back to the user.

[0021] Specifically, the distributed education system (hereinafter referred to as the system) in this application has a three-layer architecture, including a top layer, a middle layer, and a bottom layer.

[0022] Top level: Unified universal intelligent interaction entry point (M1, the only user interaction interface, supporting both free dialogue and quick access modes). Middle layer: Intelligent hub module (M2, control layer, containing 10 core sub-modules M2-1 to M2-10, responsible for global scheduling, data processing, intelligent service generation and other functions). Bottom layer: Distributed specialized capability clones (M3, 6 types of function execution layers, including M3-1 to M3-6, which are uniformly scheduled by the intelligent central module M2 and are responsible for special function execution and data collection).

[0023] It may also include auxiliary mechanisms: edge storage and central indexing mechanism (M5, including cold and hot data hierarchical management), external educational resource database docking module (M6, optional), and personal knowledge accumulation mechanism (M4).

[0024] The process is as follows: A user initiates a request through the top-level M1 → the middle-level M2 receives the request, identifies the intent, and schedules the bottom-level M3 → the bottom-level M3 executes tasks and collects data, which is stored at the edge of M5 → M3 sends the data index / features back to M2 → M2 completes data mining, profile updates, and adaptive service generation, and distributes the data to the corresponding M3 → M3 presents the service, while also supporting cross-scenario scheduling of M2 and personal knowledge retrieval by M4, forming a closed loop.

[0025] (1) Top level: Unified universal intelligent interaction entry point (M1) Function: As the sole user interface, it provides natural language interaction functions for teachers, students, teaching and research staff, and administrators, allowing them to freely converse, ask questions, and explore. It also sets up quick access points for each professional capability's M3 clone, supporting both automatic scheduling of general dialogue and manual triggering of quick access points. Users do not need to manually switch modules, achieving seamless access to all functions and solving the shortcomings of the existing system's scattered access points and cumbersome operation.

[0026] (2) Middle layer: Intelligent central module (M2) Functions: As the core of the system's global management, it is the sole central hub for all data flow, instruction distribution, and capability scheduling, undertaking six core functions: ① Receiving all user requests and identifying user identity, permissions, core needs, and teaching topics; ② Unifying the scheduling of underlying distributed professional capability avatars (M3), enabling cross-scenario and cross-functional module task scheduling and service linkage; ③ Receiving data returned from each M3, completing data normalization, topic extraction, and updating the user's panoramic profile; ④ Conducting multi-dimensional integrated data mining to uncover teaching patterns and user growth trajectories; ⑤ Generating non-intrusive adaptive services within tasks to feed back into each M3; ⑥ Managing data lifecycles and personal knowledge indexes, controlling storage pressure, and ensuring stable system operation.

[0027] The intelligent central module (M2) comprises 10 core sub-modules (M2-1 to M2-10), and the functions of each sub-module are as follows: ① Role Permissions and Interface Configuration Module (M2-1): Configure corresponding permissions based on user identity, allowing access to M3 and interface content, ensuring system security and targeting; ② Global Task Scheduling and Instruction Distribution Module (M2-2): Schedules tasks corresponding to M3 to execute, enabling cross-stage task flow and content transmission; ③ Unified Data Access and Normalization Module (M2-3): Unifies the reception of data returned from M3, completes format unification and normalization processing, and directly supports profiling and data mining; ④ Automatic Teaching Topic Extraction Module (M2-4): Extracts teaching topics and knowledge points, providing a basis for scheduling and analysis; ⑤ User panoramic profile module (M2-5): Build and dynamically update the full-role user profile, and accurately portray users by combining reflection, notes and M3 core content; ⑥ Multi-dimensional data mining module (M2-6): Conducts six types of core mining, integrates multiple data mining patterns, and supports service optimization and scheduling; ⑦ External Educational Resource Database Integration Module (M2-7, optional, linked with auxiliary mechanism M6): Integrates with external resources to achieve precise resource matching and retrieval; ⑧ Global Teaching Decision and Adaptive Service Module (M2-8): Generates non-intrusive adaptive services to meet users' personalized needs; ⑨ Data lifecycle and hot / cold tier management module (M2-9, linked with auxiliary mechanism M5): Enables tiered storage and lifecycle management of hot and cold data to prevent data bloat; ⑩ Personal Knowledge Index and Scheduling Module (M2-10, linked with auxiliary mechanism M4): Manages personal knowledge base indexes and enables cross-scenario knowledge retrieval.

[0028] (3) Bottom layer: Distributed specialized capability clones (M3, 6 types, all of which are functional execution units, M3-1 to M3-6) Functions: Receiving unified commands from the intelligent central module M2, it undertakes various specialized function execution, data collection, and service presentation tasks. It lacks independent decision-making and cross-avatar interaction capabilities. Simultaneously, it stores complete original content generated by user operations (including key works, reflections, notes, etc.), supporting offline access and millisecond-level retrieval. The specific functions of the six avatar types are as follows: ① Lesson Preparation Collaboration Assistant (M3-1): Provides teachers with specialized services related to lesson preparation, such as lesson plan generation and courseware optimization, and records the adjustment trajectory of the lesson preparation process; ② Classroom Teaching Collaboration Avatar (M3-2): Supports teachers in conducting classroom teaching, collects data throughout the classroom process, and provides support for reflection and analysis; ③ Collaborative Teaching Reflection Avatar (M3-3): Provides a professional reflection framework and Socratic guidance, automatically collects reflection content from general dialogues, and supports teachers' professional growth; ④ Student Learning Collaboration Avatar (M3-4): Provides students with personalized learning, Q&A, and grading services, and collects learning data to send back to M2; ⑤ Teaching and Research Activity Support Alternate Platform (M3-5): Provides teaching and research-related services for teachers and teaching and research personnel, and supports the accumulation and reuse of teaching and research results; ⑥ System Management and Configuration Entry (M3-6): Provides administrators with system management operations such as role configuration and permission allocation to ensure the standardized operation of the system.

[0029] (4) Key parts of the auxiliary mechanism (M4-M6) ① Personal knowledge accumulation mechanism (M4): Supports user tagging, collection of reflections, notes, M3 core content, etc., to form a personal knowledge base, realize cross-scenario reuse and intelligent accumulation, and link M2-10 modules.

[0030] ② Edge storage and central indexing mechanism (M5): The edge stores the user's original content (M3 local), while M2 only stores the index and features. It is equipped with cold and hot data hierarchical management to balance response speed and storage pressure, and links with M2-9 modules; ③ External Educational Resource Database Integration Module (M6, optional): Expands the system's resource supply capacity, enables precise resource delivery based on mining results and user profiles, and links with modules M2-7.

[0031] Based on the above structure, the embodiment of the distributed educational collaborative control method in this application is as follows: Take, for example, a high school Chinese teacher, Ms. Wang, who hopes to systematically prepare a new lesson on "Analysis of the Integration of Scenery and Emotion in Text B".

[0032] After logging into the system, Teacher Wang inputs in natural language on the top-level interactive interface M1: "I need to prepare a lesson on the appreciation of the scene-and-text integration technique in Text B." This request is sent to the intelligent central module M2. Upon receiving this request, M2 first identifies the requester as a teacher through its internal role permission and interface configuration module M2-1. Subsequently, the teaching theme automatic extraction module M2-4 parses the request text, extracting the core teaching theme as "Text B" and the keywords "scene-and-text integration," "appreciation," and "lesson preparation." Based on the identified user role and teaching theme, the global task scheduling and instruction distribution module M2-2 determines that the core of the request is the "lesson preparation" task. Therefore, it generates a clear scheduling instruction, the core content of which includes: the scheduling target is the lesson preparation collaboration avatar module M3-1, and the scheduling task is "to provide Teacher Wang with lesson preparation support for the appreciation of the scene-and-text integration technique in Text B." The global task scheduling and instruction distribution module M2-2 sends the generated scheduling instruction to the lesson preparation collaboration avatar module M3-1 asynchronously and non-blockingly. After receiving the scheduling instruction, the lesson preparation collaboration module M3-1 starts its special lesson preparation function.

[0033] During and after the execution of tasks, the intelligent central module of the lesson preparation collaboration avatar module M3-1 processes the feature data returned by the module. It does not upload the entire lesson plan file and all operation logs, but extracts key feature data, which may include: Index information: Task ID (e.g., Lesson Preparation - Text B - Date), associated teaching theme tags (Prose Appreciation, Author, Integration of Scenery and Emotion).

[0034] Behavioral characteristics: Teacher Wang's focus time during this lesson preparation, the adoption rate of system-recommended resources, and the number and types of teaching segments added by herself (such as adding a student imitation writing exercise segment).

[0035] Outcome characteristics: a structured summary of the final lesson plan (such as including four stages: introduction, detailed explanation, discussion and summary), tags of the core teaching methods used (case analysis, group discussion), and identified teaching difficulties (emotional experience).

[0036] M3-1 incrementally and synchronously transmits the aforementioned structured and lightweight feature data back to the unified data access and normalization module M2-3 of the intelligent central module. The unified data access and normalization module M2-3 cleans and formats the received feature data, and the processed feature data is then sent to the multi-dimensional data mining module M2-6. In this module, Mr. Wang's feature data is analyzed to generate data on his individual teaching patterns. For example, when preparing lessons on prose texts, Mr. Wang spends an average of about 2 hours; when discussing the appreciation of writing techniques, there is an 85% probability that he will voluntarily add a student imitation writing activity; and his lesson plan structure shows a clear trend of evolving from lecture-based to interactive inquiry-based. This data reflects Mr. Wang's individual lesson preparation habits, teaching style preferences, and development trajectory.

[0037] The global teaching decision-making and adaptive service module M2-8 of M2 retrieves Teacher Wang's current user profile from the user panoramic profile module M2-5. This profile is dynamically constructed based on all of Teacher Wang's past feature data, such as tags like: experienced Chinese language teacher, preference for interactive teaching, and recent focus on writing techniques. The M2-8 module integrates Teacher Wang's user profile with the teaching pattern data mined this time to generate an adaptive service plan, for example: "We detected that you have included a writing imitation exercise in your lesson preparation. Based on your profile of preferring interactive teaching and historical patterns, we recommend three student model essays (from the resource library) suitable for writing imitation comparison." This adaptive service plan is then sent back to the lesson preparation collaboration avatar module M3-1, which is currently providing services to Teacher Wang. M3-1 presents this service plan (recommended model essays and teaching suggestions) to Teacher Wang in a way that does not interrupt Teacher Wang's current lesson preparation (e.g., as a prompt card in the sidebar). Teacher Wang can immediately adopt the suggestion, review it later, or ignore it.

[0038] The method in this embodiment receives a user's teaching service request, generates a scheduling instruction, and controls the target capability clone module to execute the scheduling task. Simultaneously, it collects feature data transmitted back during the scheduling task execution in real time. By mining this continuous and dynamic feature data, it generates teaching pattern data reflecting the learner's real-time cognitive state and behavioral patterns. This data, combined with a pre-set profile, generates an adaptive service plan. By combining teaching pattern data and a pre-set profile to generate an adaptive service plan, the distributed education system can keenly capture the characteristics of classroom interaction and real-time assessment, and adjust recommendation strategies in a timely manner. This provides more timely, adaptive, and sensitive learning support, significantly improving the accuracy of personalized education services and the user experience.

[0039] In a specific embodiment, the feature data includes teaching topic feature data corresponding to the user, personal knowledge tagging data, behavioral pattern feature data changing over time, and outcome quality assessment data; the step of data mining the feature data to generate the user's teaching pattern data includes: generating first pattern data representing the user's professional ability growth trajectory based on the changing trends of the outcome quality assessment data and the behavioral pattern feature data over time; clustering the teaching topic feature data based on the personal knowledge tagging data to generate second pattern data representing the user's personal teaching mode; the first pattern data and the second pattern data constitute the teaching pattern data.

[0040] Specifically, the teaching theme characteristic data can include theme tags, knowledge point associations, and difficulty tags. Theme tags include topics such as prose appreciation and scene integration. Knowledge point associations include knowledge point networks extracted from Teacher Wang's lesson preparation, teaching, and assignments, such as "rhetorical devices such as metaphor and synesthesia" and "direct and indirect expression of emotion." Difficulty tags are the estimated difficulty level automatically marked for each teaching task based on curriculum standards and resource library association information. Personal knowledge tagging data can include tagged reflection segments, collected student works, and teaching and research materials. Behavioral pattern characteristic data can include Teacher Wang's lesson preparation behavior sequence over the past year (such as the sequence of the average proportion of student interaction in Teacher Wang's lesson plans) and resource usage preferences (the frequency with which Teacher Wang uses short video materials or pure image materials under scene integration themes). The outcome quality evaluation data can include a quantitative evaluation of Teacher Wang's teaching outcomes, such as lesson plan complexity scores and classroom interaction heat indices. Lesson plan complexity scores are used to characterize the structural integrity of the lesson plan, the diversity of teaching methods, and the degree of technology integration. Classroom interaction heat indices are used to characterize the number of questions collected and the duration of student participation.

[0041] The generation of the first regularity data: Data from Teacher Wang's past 12 months was sliced ​​into monthly segments, and four curves were plotted: lesson plan complexity score, classroom interaction intensity index, lesson preparation behavior sequence, and resource usage preference. The trends of these four curves were then analyzed. When a significant positive correlation was found among the four curves, and they were rising synchronously, the first regularity data was generated. This data can be described as: "Over the past year, the user's instructional design ability and classroom organization ability have shown a coordinated and stable upward trend. Their growth trajectory is a robust improvement type, with the key driving force being the continuous increase in the design and implementation of classroom interaction elements." If the curves for lesson preparation behavior sequence and resource usage preference show a downward trend, then the first regularity data indicates a downward trend in instructional design ability, requiring adaptive modifications. If the lesson plan complexity score and classroom interaction intensity index show a downward trend, then the first regularity data indicates a downward trend in classroom organization ability, requiring adaptive modifications.

[0042] The generation of the second pattern data involves extracting all of Teacher Wang's tagged personal knowledge data and extracting high-frequency keywords and sentiment tendencies. Simultaneously, all of Teacher Wang's teaching theme feature data are obtained, and clustering algorithms are used to group these features according to their associated personal knowledge features. For example, when the teaching theme features involve sentiment analysis, the personal knowledge data contains a large number of keywords such as life analogy, empathy, and identification. Therefore, Teacher Wang's second pattern data can be described as: He is skilled at and tends to use life analogy strategies to overcome students' emotional comprehension barriers, and his personal knowledge base is deeply rooted in this area. Conversely, when the teaching theme feature data involves writing techniques, the personal knowledge data contains a large number of imitation exercises and technique breakdowns. Therefore, the second pattern data can be described as: Teacher Wang focuses on the imitation-practice path and possesses a database of excellent student imitation examples.

[0043] In a specific embodiment, the method further includes: updating the user's preset profile based on the teaching topic feature data and the personal knowledge tag data to obtain an updated profile; then, generating an adaptive service scheme based on the user's preset profile and the teaching pattern data includes: generating an adaptive service scheme based on the user's updated profile and the teaching pattern data.

[0044] Specifically, Teacher Wang's pre-defined profile includes his historical tags, such as: high school Chinese teacher, focused on writing instruction, and with a high preference for interactive classrooms. Structured feature vectors that can be used to update the profile are identified from teaching theme characteristic data and personal knowledge tag data. For example, from teaching theme data, the following vectors are extracted: theme vector (e.g., strengthening essay appreciation) and skill vector (e.g., strengthening close reading of texts). From personal knowledge tag data, the following vectors are extracted: interest vector (e.g., adding an interest in in-depth study of synesthetic rhetoric) and teaching strategy vector (e.g., adding cross-task knowledge association strategies, i.e., connecting with students' past writing problems for targeted teaching, and being good at interaction). The newly extracted feature vectors are then fused with the corresponding vectors in the existing pre-defined profile. The updated profile of Teacher Wang may include: high school Chinese teacher, with a strong preference for interactive classrooms, and an increasing trend in the complexity of instructional design; deeply focused on writing instruction, and recently showing a clear research and teaching interest in literary rhetoric. Skilled in and frequently using cross-task knowledge association strategies, adept at using students' past achievements as entry points and comparison materials for current teaching. Experienced in essay appreciation, with comparative analysis and associative transfer being high-frequency and efficient methods in the teaching method library.

[0045] In a specific embodiment, the teaching theme feature data includes teaching reflection content and teaching notes, and the personal knowledge tag data includes feature tags of core teaching works; then, updating the user's preset profile based on the teaching theme feature data and the personal knowledge tag data to obtain an updated profile includes: characterizing the teaching style, knowledge state vector, and theme interest weight in the user's preset profile based on the teaching reflection content, the teaching notes, and the feature tags of core teaching works to obtain an updated profile.

[0046] Specifically, the teaching reflection content is a reflection on the previous classroom records, such as: "In this lesson, guiding students to find metaphors and synesthetic sentences in the text went smoothly, but when asked how these descriptions of scenery conveyed the author's complex mood of mixed sorrow and joy, most students fell silent. Reflection: Next time, we need to build a more specific emotional ladder, starting with the analysis of the emotional coloring of words, then connecting it to the author's life, and finally returning to the description of scenery itself."

[0047] Teaching notes include additional classroom notes, such as mixing articulate students with introverted students, and using group discussions to reduce the emotional pressure of answering in public.

[0048] The key features of teaching core works include immersive learning experiences, multimedia courseware, interactive Q&A design, group discussion sessions, and addressing the challenges of emotional analysis, which are the main focuses of classroom teaching.

[0049] A specific implementation of characterizing the teaching style in the pre-defined profile is as follows: add a structured facilitator style tag, indicating that the facilitator is good at breaking down complex problems into tiered tasks; at the same time, strengthen the student-centered style tag, reflecting the facilitator's tendency to adjust teaching strategies according to student responses and characteristics (introversion / extroversion), and appropriately increase group discussions.

[0050] A specific example of characterizing the knowledge state vector in the pre-defined profile is as follows: Under the knowledge domain of Chinese language teaching methodology, the proficiency assessment of the teaching strategy of deep emotional analysis of texts undergoes a dynamic adjustment: initially, it decreases slightly due to student silence during classroom feedback, and then significantly increases due to students proposing specific improvement plans. Simultaneously, the vector weights of subject content knowledge such as the knowledge of contextual integration techniques are consolidated and enhanced due to this teaching session.

[0051] A specific implementation of characterizing the thematic interest weights in the preset profile is as follows: the weight of the corresponding essay appreciation theme is significantly increased.

[0052] In a specific embodiment, generating an adaptive service scheme based on the user's updated profile and the teaching pattern data includes: extracting at least one knowledge point to be strengthened and at least one knowledge point to be associated from a preset teaching resource knowledge graph based on the knowledge state vector in the updated profile; generating time-constrained knowledge point activation paths for the knowledge point to be strengthened and the knowledge point to be associated based on a preset knowledge mastery time sequence graph; matching each knowledge point node in the knowledge point activation path with the teaching style in the updated profile based on the topic interest weight in the updated profile and the teaching pattern data; and generating the adaptive service scheme based on the knowledge point nodes with matched teaching styles and the knowledge mastery time sequence graph.

[0053] Specifically, firstly, based on the knowledge state vector in the updated profile, knowledge points are extracted from the system's preset teaching resource knowledge graph. The teaching resource knowledge graph is a structured knowledge network in the education field, where nodes represent knowledge points, teaching skills, or resources, and edges represent the logical, sequential, or relational relationships between them.

[0054] Since the proficiency level of deep sentiment analysis teaching strategies in the updated profile is "rising," it is identified as a skill point requiring reinforcement. Therefore, the core knowledge point "Building a Scaffold for Textual Sentiment Analysis" is extracted from the knowledge graph as a knowledge point to be strengthened. Simultaneously, the "Building a Scaffold for Textual Sentiment Analysis" knowledge point has strong correlation edges with the "Knowledge of the Author and Their World" and "Word Sentiment Color Analysis" knowledge points in the knowledge graph, and the high proficiency level of the "Contextual Integration Techniques" knowledge point in the updated profile can serve as a solid foundation for these connections. Therefore, "Knowledge of the Author and Their World" and "Word Sentiment Color Analysis" are extracted as knowledge points to be linked.

[0055] For building a scaffold for text sentiment analysis, the time sequence graph specifies that the mastery path is usually as follows: Stage 1: Identify explicit sentiment words; Stage 2: Connect with the creative background to understand the author and the world; Stage 3: Analyze the contextual relationship; Stage 4: Design tiered questions.

[0056] For word sentiment analysis, the time sequence graph shows that it is a relatively independent basic skill with a simple activation path, and can be arranged as a warm-up activity in the next lesson.

[0057] For path node stage 2: Connecting the creative background to understand the author and the world, and matching the teaching style: Conduct structured facilitator and life analogy, and output corresponding solution prompts: "When introducing the mood of creating this article, you can draw an analogy to the student's own experience of finding a quiet corner under pressure."

[0058] For the core objective stage 4: Design a tiered questioning approach to match the teaching style: It is recommended to use a student-centered, interactive classroom with real-life analogies, and provide corresponding solution prompts: "Design a tiered questioning approach, starting with which scenes in the text make you feel peaceful, then moving on to why the author chose these scenes, and finally to what scenes you would choose if you were describing a feeling of being bored, and use a group discussion format."

[0059] The adaptive service solution is generated based on the knowledge point nodes and knowledge mastery time sequence graph matched with the teaching style. For example, based on your recent teaching performance and reflections, the system recognizes that you are actively iterating in guiding students to conduct in-depth sentiment analysis. To consolidate this skill, the following support solution is generated: 1. Key reinforcement point: Master the strategy of "building a scaffold for text sentiment analysis".

[0060] 2. Implementation path: Recently: Before introducing new texts, insert a 5-minute interactive game on analyzing the emotional connotations of words as a warm-up for the emotional analysis.

[0061] Key point: For the design of the tiered questioning section, it is recommended to use a three-tiered questioning model: personal feelings - author's intention - application of knowledge. It is especially suggested to incorporate relatable analogies, such as: "Please use familiar scenery to describe the relaxed feeling after completing the assignment." 3. Related Resources: Based on your interests, we have matched three classic case excerpts from the knowledge graph that use real-life analogies for emotional teaching, as well as a research abstract on the teaching method of "understanding people and their times". You can view them in the lesson preparation app.

[0062] Objective: This approach will help you transform the identification of difficulties in emotion analysis teaching into a reusable and effective teaching strategy.

[0063] In a specific embodiment, generating a scheduling instruction corresponding to the teaching service request includes: identifying the intent and topic of the teaching service request, and generating a scheduling instruction corresponding to the teaching service request based on the identified teaching intent and topic.

[0064] Specifically, Teacher Wang initiates a request through a unified intelligent interaction portal, inputting, "I plan to teach the writing technique of integrating emotion and scene in Lesson B; please design a highly interactive classroom activity for me." After receiving the request, the intelligent central processing unit identifies the intent and theme. First, the natural language processing unit analyzes the request text, extracting the core verb "design" and the functional object "classroom activity." Combining this with the intent model, it determines the core teaching intent as "classroom activity design" under the "lesson preparation" framework. Simultaneously, the automatic teaching theme extraction module M2-4 parses the text, identifying the entity "Lesson B" and the core concepts "integration of emotion and scene" and "highly interactive," thus determining the precise teaching theme for this request. The learning theme is "Design of Interactive Teaching Activities Using the Contextual Integration Technique in Lesson B". Then, the global task scheduling and instruction distribution module M2-2 of M2 generates a structured scheduling instruction based on the identified "classroom activity design" intention and the theme "Lesson B / Contextual Integration / Interaction". The instruction explicitly designates the target capability clone module as the lesson preparation collaboration clone M3-1, and its core task is "to design a highly interactive classroom activity plan for this theme". The identified teaching theme is encapsulated as a context parameter in the instruction and sent to M3-1. After receiving the instruction, the M3-1 module can call its special function and start to execute the specific activity design task around the specified theme and interactivity requirements.

[0065] In a specific embodiment, the method further includes: simulating the service task corresponding to the adaptive service scheme and providing feedback to the user on the execution results after simulating the service task. Specifically, the intelligent central control schedules the classroom teaching collaboration avatar M3-2 to run the adaptive service scheme in the virtual classroom environment. M3-2 will simulate and generate text and interaction data of possible responses from different types of students to the adaptive service scheme, and quickly calculate the execution results of the simulation based on a preset teaching effectiveness evaluation model. Subsequently, M2 will summarize the core process and quantify the results of this simulation. For example, the simulation shows that the adaptive service scheme can enable about 80% of the simulated students to achieve basic understanding, but about 30% of the simulated students make inappropriate analogies. It is recommended that teachers prepare 1-2 more specific analogy examples for guidance during implementation.

[0066] In a specific embodiment, in addition to integrating data from individual users, the intelligent central module can analyze multi-user related data in teaching and research groups or teacher-student relationships through authorization. For example, it can obtain homework from the teacher in the student's class, classroom learning data during the teaching process of the course, or teacher profiles and notes information that the group teacher is willing to authorize in teaching and research scenarios, for group analysis and correlation analysis.

[0067] In a specific embodiment, this refers to the intelligent central processing unit conducting cross-individual and cross-role joint mining and analysis of multi-user data with teaching or collaborative relationships after obtaining explicit authorization from the user. It refers to extracting a collective profile reflecting group characteristics, collaboration patterns, and common rules based on individual profiles, behavioral data, and correlation analysis results of multiple authorized users within groups such as teaching and research groups and classes. This deepens the understanding of deficiencies in data mining and pattern discovery, highlighting the lack of group analysis capabilities.

[0068] Existing systems suffer from limited data mining capabilities, only able to perform simple statistics on isolated data from individual users. They lack the ability to conduct cross-individual and cross-role correlation data mining and group analysis based on user authorization and role relationships. For example, they cannot integrate "a teacher's lesson plan (preparation data)" with "the overall learning performance of students in their class (homework, classroom data)" for correlation analysis to verify the effectiveness of teaching methods. Nor can they extract group characteristics and mine excellent experience patterns from the profiles, notes, and reflection data of multiple teachers within a teaching and research group, based on member authorization. This results in the inability to discover and reuse valuable collective wisdom and collaborative patterns.

[0069] Existing technologies can only mine isolated data from single users and cannot perform cross-role or cross-group correlation analysis. This system, in its M2-6 (multi-dimensional data mining module), introduces an authorized correlation analysis mechanism. Based on explicit user authorization relationships (e.g., students authorizing their instructors, mutual authorization among teaching and research group members), it integrates multi-user data with teaching or collaborative relationships (e.g., teacher-student group data of lesson preparation / teaching data and student classroom / homework data; group data such as profiles, notes, and achievements of multiple teachers within a teaching and research group). This allows for cross-individual temporal correlation mining, teaching behavior-learning effect transmission analysis, extraction of common group characteristics, and discovery of collaborative patterns. In teaching and research group scenarios, by analyzing the profiles and notes of authorized teachers within the group, common characteristics and implicit experiences of excellent teachers can be discovered, forming a "group excellent practice model." This model can then be adaptively recommended to other teachers within the group through central scheduling, achieving a "1+1>2" effect of group collaboration and intelligent reuse.

[0070] In a specific embodiment, this application also includes a data authorization and privacy management module (M2-11), which is used to manage the data authorization relationship between users (such as students authorizing teachers to view their learning data, and teaching and research group members authorizing each other to share profile features), record the scope of authorization, validity period and permission level, and ensure that all cross-user data mining and analysis operations are carried out in compliance with the authorization framework. It is the core control unit to ensure the legality and security of group analysis.

[0071] After obtaining explicit authorization from relevant users (recorded via M2-11), M2-6 can proactively or on-demand initiate authorized association analysis. For example, targeting "Teacher Zhang" and the students in her classes, M2-6 integrates Teacher Zhang's lesson preparation notes and teaching trajectory (M3-1 / M3-2) with the classroom interactions and homework completion data of all students (M3-4) to perform association rule mining and analyze the correlation between "the design of a certain teaching segment" and students' "knowledge mastery level." Similarly, within the "Junior High School Mathematics Teaching and Research Group" group, with member authorization, M2-6 can perform cluster analysis on the profiles, reflection notes, and excellent lesson plans of multiple teachers in the group to extract "efficient lesson preparation models" or "common teaching pitfalls." The resulting group patterns and insights are stored in the group profile library of M2-5 and serve as a higher-level basis for M2-8 to generate adaptive services (such as recommending "excellent experiences" to new teachers in the group).

[0072] By leveraging the newly introduced authorized correlation analysis technology in M2-6, combined with the data authorization and privacy management technology in M2-11, the system achieves correlation verification of closed-loop teaching-learning data between teachers and students, as well as collaborative mining of collective wisdom within teaching and research groups. Its effects include: 1. Quantitative closure of teaching effectiveness: Teachers can clearly see how their lesson plans influence students' classroom performance and homework results, upgrading teaching reflection from "subjective feelings" to "data-driven precise verification"; 2. Reuse of excellent group experiences: Teaching and research groups can automatically extract "excellent practice models" from the group data of authorized members and adaptively push them to other teachers within the group (especially new teachers), greatly accelerating teachers' professional growth and the transformation of teaching and research results; 3. Leap in system value: This system evolves from an intelligent tool serving "individuals" into a collaborative and empowering platform connecting "individuals-classes-teaching and research groups," forming a unique technological advantage and market competitive barrier.

[0073] In a specific embodiment, please refer to Figure 2This is a schematic diagram of a distributed educational collaborative control system according to this application. The system includes: an instruction generation and receiving module 201, an execution module 202, a feedback module 203, a teaching pattern data acquisition module 204, and a scheme output module 205. The instruction generation and receiving module 201 is used to receive teaching service requests initiated by users through the interactive entry module of the distributed education system and generate scheduling instructions corresponding to the teaching service requests. The execution module 202 is used to control the target capability clone module corresponding to the scheduling instructions in the distributed education system to execute the scheduling tasks corresponding to the scheduling instructions. The feedback module 203 is used to receive feature data returned by the target capability clone module at different times when executing the scheduling tasks. The teaching pattern data acquisition module 204 is used to perform data mining on the feature data to generate teaching pattern data for the user. The scheme output module 205 is used to generate adaptive service schemes based on the user's preset profile and the teaching pattern data, and feed the adaptive service schemes back to the user.

[0074] In a specific embodiment, the third embodiment of this application provides a distributed educational collaborative control device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method as described in any one of the first embodiments of this application.

[0075] In a specific embodiment, the fourth embodiment of this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the method as described in any one of the first embodiments of this application.

[0076] Figure 3 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. See also... Figure 3 The computer device includes a processor, memory, etc., connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program causes the processor to implement the method described in this embodiment. The internal memory may also store a computer program, which, when executed by the processor, causes the processor to perform the method described in this embodiment. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0077] The above embodiments merely illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

[0078] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments for application in other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A distributed educational collaborative control method, applied to the intelligent central module of a distributed educational system, characterized in that, The method includes: Receive teaching service requests initiated by users in the interactive entry module of the distributed education system, and generate scheduling instructions corresponding to the teaching service requests; Control the target capability clone module corresponding to the scheduling instruction in the distributed education system to execute the scheduling task corresponding to the scheduling instruction; Receive the feature data returned by the target capability clone module when executing the scheduling task; Data mining is performed on the feature data to generate the user's teaching pattern data; An adaptive service plan is generated based on the user's preset profile and the teaching pattern data, and the adaptive service plan is fed back to the user.

2. The distributed educational collaborative control method as described in claim 1, characterized in that, The feature data includes the user's corresponding teaching topic feature data, personal knowledge mark data, behavioral pattern feature data that changes over time, and outcome quality assessment data; The step of generating the user's teaching pattern data by performing data mining on the feature data includes: Based on the changing trends of the outcome quality assessment data and the behavioral pattern characteristic data over time, first regularity data representing the user's professional ability growth trajectory is generated. Clustering the teaching topic feature data based on the personal knowledge tagging data generates second pattern data that represents the user's personal teaching mode; the first pattern data and the second pattern data constitute the teaching pattern data.

3. The distributed educational collaborative control method as described in claim 1, characterized in that, The method further includes: The user's preset profile is updated based on the teaching topic feature data and the personal knowledge tag data to obtain an updated profile; The adaptive service solution generated based on the user's preset profile and the teaching pattern data includes: An adaptive service solution is generated based on the updated user profile and the teaching pattern data.

4. The distributed educational collaborative control method as described in claim 3, characterized in that, The teaching theme feature data includes teaching reflection content and teaching notes, and the personal knowledge tagging data includes feature tags of core teaching works; The step of updating the user's preset profile based on the teaching topic feature data and the personal knowledge tag data to obtain an updated profile includes: Based on the teaching reflection content, the teaching notes, and the feature tags of the core teaching works, the teaching style, knowledge state vector, and topic interest weights in the user's preset profile are characterized to obtain an updated profile.

5. The distributed educational collaborative control method as described in claim 4, characterized in that, The adaptive service solution generated based on the user's updated profile and the teaching pattern data includes: Based on the knowledge state vector in the updated profile, at least one knowledge point to be strengthened and at least one knowledge point to be associated are extracted from the preset teaching resource knowledge graph. Based on the preset knowledge mastery time sequence map, time-constrained knowledge point activation paths are generated for the knowledge points to be strengthened and the knowledge points to be associated, respectively. Based on the topic interest weights in the updated profile and the teaching pattern data, the teaching style in the updated profile is matched for each knowledge point node in the knowledge point activation path. The adaptive service solution is generated based on the knowledge point nodes that match the teaching style and the knowledge mastery time sequence graph.

6. The distributed educational collaborative control method as described in claim 1, characterized in that, The generation of the scheduling instruction corresponding to the teaching service request includes: The teaching service request is subjected to intent and topic identification, and a scheduling instruction corresponding to the teaching service request is generated based on the identified teaching intent and topic.

7. The distributed educational collaborative control method as described in claim 1, characterized in that, The method further includes: simulating the service task corresponding to the adaptive service scheme, and providing feedback to the user on the execution result after simulating the service task.

8. A distributed collaborative education control system, characterized in that, The system includes: an instruction generation and receiving module, an execution module, a feedback module, a teaching pattern data acquisition module, and a scheme output module; The instruction generation and receiving module is used to receive teaching service requests initiated by users in the interactive entry module of the distributed education system, and generate scheduling instructions corresponding to the teaching service requests. The execution module is used to control the target capability clone module corresponding to the scheduling instruction in the distributed education system to execute the scheduling task corresponding to the scheduling instruction; The feedback module is used to receive feature data fed back by the target capability clone module at different times when it executes the scheduling task; The teaching pattern data acquisition module is used to perform data mining on the feature data to generate the user's teaching pattern data; The solution output module is used to generate an adaptive service solution based on the user's preset profile and the teaching pattern data, and to feed the adaptive service solution back to the user.

9. A distributed educational collaborative control device, comprising a memory and a processor, characterized in that, The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the processor to perform the steps of the method as described in any one of claims 1 to 7.

Images