Teaching quality continuous improvement system and method based on ai and pdca nested loop

Abstract

The application provides a teaching quality continuous improvement system and method based on AI and PDCA nested cycles, and relates to the technical field of teaching quality improvement.The application comprises an outer, middle and inner three-layer PDCA cycle framework nested with each other, and a student personal ability growth data bus; the inner cycle constructs a three-dimensional ability knowledge correlation graph with weights through an intelligent planning module, and calculates the value-added amount of each ability point and forms a value-added vector according to the score of the examination items and the preset weight by using an intelligent diagnosis module and an ability value-added evaluation model.The inner cycle data is gradually aggregated upwards through the bus to drive the continuous improvement of the middle and outer cycles, and the outer cycle macroscopically adjusts and transfers new targets downwards step by step.The application can break the data island, realize the objective quantitative evaluation of teaching effectiveness, and realize the organic linkage of micro teaching optimization and macro talent training system.

Description

Technical Field

[0001] This invention relates to the field of teaching quality improvement technology, and more specifically, to a teaching quality continuous improvement system and method based on a nested cycle of AI and PDCA. Background Technology

[0002] With the deepening development of educational informatization, combining artificial intelligence technology with the traditional PDCA quality management cycle has become an important means to improve teaching quality. Current technical solutions typically utilize AI algorithms to analyze student behavioral data on learning platforms, including video viewing time, assignment submissions, and test scores, to examine the gap between teaching effectiveness and preset goals and to provide teachers with improvement suggestions. While these systems have achieved a certain degree of digitalization in teaching evaluation, they still face significant limitations in practical applications.

[0003] Existing teaching quality improvement systems generally suffer from reactive limitations in their evaluation models. Their core focus is on post-event gap analysis, which, while capable of identifying problems during teaching, fails to objectively and quantitatively measure students' actual skill growth—the added value—over the entire teaching cycle, resulting in a relatively singular evaluation dimension. Furthermore, when dealing with the relationship between knowledge points and skills, existing systems often employ a flat data structure, lacking structured and computable internal connections. This flat data structure cannot reveal the differences in the contribution of different knowledge points to the development of specific skills, nor can it form a computable and reasonable structured teaching objective model. Moreover, the improvement cycles of existing systems exhibit significant siloed characteristics. Their PDCA cycle typically operates on a single, flat level for a single course or teaching activity, with each course's improvement process independent of the others. There is a lack of effective data linkage mechanisms between micro-level course optimization and macro-level optimization of professional talent training programs, creating data silos and preventing systematic and comprehensive improvements from the micro to the macro level.

[0004] In view of the above, this application is hereby submitted. Summary of the Invention

[0005] This invention aims to provide a teaching quality continuous improvement system and method based on AI and PDCA nested cycle, in order to solve the problems of "reactive" evaluation model, "flat" data association, and "isolated" improvement cycle in existing teaching quality improvement systems.

[0006] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0007] A teaching quality continuous improvement system based on AI and PDCA nested loop, including mutually nested outer loop, middle loop and inner loop; Wherein, PDCA stands for the planning phase (P), the execution phase (D), the checking phase (C), and the improvement phase (A), respectively. The outer cycle is used for the PDCA cycle of the professional talent training program, and its planning phase includes the middle cycle planning phase for all students. The middle cycle is used for the PDCA cycle of individual student's personal ability development. Its planning phase is nested within the planning phase of the outer cycle and includes the planning phase of the inner cycle for all courses taken by the student. The inner loop is used for the PDCA cycle of teaching a single course, and its planning phase is nested within the planning phase of the middle loop. The capability enhancement data package generated by the inner loop during the inspection phase is fed into the middle and outer loops step by step through the student's personal capability growth data bus. The adjustments made to the talent development program by the external circulation are transmitted down the hierarchy, setting new goals and constraints for the planning stages of the medium and internal circulation.

[0008] Preferably, the inner loop includes an intelligent planning module, a process tracking and data acquisition module, an intelligent diagnosis module, and a collaborative feedback improvement module; The intelligent planning module, corresponding to the planning stage of the inner loop, is used to construct a three-dimensional ability knowledge association graph. The three-dimensional ability knowledge association graph is used to define the relationship between knowledge points, ability points and literacy points, and to configure the contribution weight of several ability points for each assessment item, forming a structured data containing assessment item identifiers, ability point identifiers and weights stored in the system database. The process tracking and data acquisition module is used to collect and record students' operational behavior data in the learning management system during the execution phase of the inner loop, including assessment item score data associated with the three-dimensional ability knowledge association map, and interaction logs generated during the interaction between students and the AI ​​learning companion agent. The intelligent diagnostic module is used to execute the capability enhancement evaluation model during the inspection phase of the inner loop. The capability enhancement evaluation model is based on the three-dimensional capability knowledge association map and the collected operational behavior data to calculate the single contribution of each student's assessment item to each associated capability point, and accumulates them to obtain the total capability enhancement of each capability point, forming a capability enhancement vector, thereby obtaining a capability enhancement data package. The collaborative feedback improvement module is used to convert the capability enhancement vector into a personal capability radar chart or a class learning heat map during the improvement stage of the inner loop, and provide visualization results to teachers, students and teaching administrators respectively. At the same time, the generated capability enhancement data package is encapsulated and integrated into the student personal capability growth data bus to drive the improvement of the inner loop, middle loop and outer loop.

[0009] Preferably, the construction process of the three-dimensional capability knowledge association graph is as follows: First, define the course quality standards and break down the three-dimensional teaching objectives: based on the professional talent training program and graduation requirement indicators, and combined with the historical learning data in the student's total data stream, formulate the course teaching syllabus and clarify the three-dimensional objectives of knowledge, ability, and quality. Next, a knowledge graph of ideological and political education is constructed: the course content is broken down into detailed knowledge points in the form of a mind map, each knowledge point is marked with knowledge attributes and associated with corresponding ability point tags, while the ideological and political elements in the knowledge points are explored, the literacy point tags are extracted, and an ideological and political education graph is constructed to link knowledge points, ability points, and literacy points; finally, all teaching resources of the course are linked with the corresponding knowledge points to complete the construction of the knowledge graph of ideological and political education. Then, a competency graph is designed to achieve a visual association between knowledge points and competency points: based on the competency point tags of the ideological and political knowledge graph, a course-level competency objective system is established, and the competency objectives are bound one by one to the knowledge points in the ideological and political knowledge graph; Finally, based on the course syllabus and competency development objectives, weights are assigned to each competency point in the ideological and political knowledge graph, and assessment items are linked to competency points. The contribution weight of assessment items to competency points is set, forming a structured, computable, and weighted three-dimensional competency knowledge graph.

[0010] Preferably, the student personal ability growth data bus is configured with a unified data exchange protocol.

[0011] Preferably, the improvement stage of the intermediate cycle generates a student's ability growth trajectory map based on the ability value-added data package of multiple courses extracted from the student's personal ability growth data bus, and pushes personalized learning suggestions or practice projects accordingly.

[0012] Preferably, the expression for the capability enhancement data packet is: ; ; in, Add value to students' abilities with data packages; For ability points Total added value; This represents the total number of ability points in the three-dimensional course map. For the course and the key skills The total number of related assessment items; It is the transpose symbol; As assessment item For ability points The amount of contribution of a single item; Complete the assessment items for students The actual score; As assessment item For ability points The contribution weight.

[0013] Preferably, the knowledge point tags in the three-dimensional ability knowledge association map include key and difficult knowledge points, test points, corresponding ability points, and corresponding literacy points.

[0014] Preferably, the AI ​​learning companion agent is deployed in the form of a chatbot, and the interaction log includes the semantic depth of the student's questions and the response method to system prompts.

[0015] Preferably, the outer loop inspection phase aggregates all students' ability value-added data packages to construct big data on the quality of professional talent training, performs statistical analysis by major, grade or course group, identifies systemic shortcomings in the talent training program, and revises the curriculum, credit allocation or ability training objectives during the outer loop planning phase.

[0016] This invention also provides a method for continuous improvement of teaching quality based on a nested cycle of AI and PDCA, including: First, a nested system architecture is established, with the professional talent training program as the outer loop, the individual student's personal ability growth as the middle loop, and the teaching of a single course as the inner loop. The planning stage of the outer loop includes the planning stage of the middle loop for all students. The planning stage of each middle loop includes the planning stage of the inner loop for all courses taken by the student, forming a hierarchical nested data dependency relationship. A student personal ability growth data bus is established as the sole channel for transmitting ability value-added data packets from the inner loop to the middle loop and from the middle loop to the outer loop; the ability value-added data packets are structured ability value-added data generated by the inner loop during the inspection phase. Then execute the PDCA process of the inner loop: The planning phase P of the inner loop: For a single course, construct a weighted three-dimensional ability knowledge association graph; wherein, the three-dimensional ability knowledge association graph is used to define the relationship between knowledge points, ability points and literacy points, and to configure the contribution weight of several corresponding ability points for each assessment item, forming a structured data containing assessment item identifiers, ability point identifiers and weights stored in the system database. The inner loop execution phase D: Collect and record students' operational behavior data in the learning management system, including assessment item score data associated with the three-dimensional ability knowledge association map, as well as interaction logs generated during the interaction between students and the AI ​​learning companion agent; Inner loop inspection phase C: Based on the three-dimensional ability knowledge association map and the collected operation behavior data, calculate the single contribution of each student's assessment item to each associated ability point, and accumulate them to obtain the total ability value-added of each ability point, forming an ability value-added vector, thereby obtaining the ability value-added data package; Phase A of the internal circulation improvement: The capability enhancement vector is converted into a personal capability radar chart or a class learning heat map, and the visualization results are provided to teachers, students and teaching administrators respectively. At the same time, the capability enhancement vector is encapsulated and integrated into the student personal capability growth data bus to drive the improvement of the internal circulation, middle circulation and external circulation.

[0017] The present invention also provides a teaching quality continuous improvement device based on AI and PDCA nested cycle, including a processor and a memory, wherein the memory stores a computer program that can be executed by the processor to realize the teaching quality continuous improvement method based on AI and PDCA nested cycle as described above.

[0018] The present invention also provides a computer-readable storage medium storing computer-readable instructions, which, when executed by a processor of the device on which the computer-readable storage medium resides, implement the above-described method for continuous improvement of teaching quality based on a nested cycle of AI and PDCA.

[0019] In summary, compared with the prior art, the present invention has the following beneficial effects: First, this invention employs a three-layer nested PDCA cycle architecture. The structured capability-added data (capability-added vector) generated by the inner cycle is aggregated upwards through the student's individual capability growth data bus, driving the decisions of the middle and outer cycles. Meanwhile, the adjustments made to the talent training program by the outer cycle are transmitted downwards, setting new planning goals for the middle and inner cycles. This breaks down the "data silos" between courses and between courses and majors, and achieves the organic linkage between micro-level teaching optimization and macro-level talent training system.

[0020] Secondly, by constructing a weighted three-dimensional ability knowledge association graph during the planning stage and using the weight as an intrinsic attribute of the graph data model, this invention transforms the teaching objectives from vague qualitative descriptions into a calculable and reasonable structured model, laying a data foundation for intelligent teaching throughout the entire process.

[0021] Furthermore, this invention generates an initial ability state vector at the beginning of the teaching cycle through an ability value-added evaluation model. During the teaching process, it dynamically calculates the contribution of each item based on the scores of the assessment items and preset weights, and finally accumulates them to obtain an ability value-added vector. This provides an objective and quantitative answer to the core question of "how much progress have students made," and completes a paradigm shift from traditional "gap evaluation" to "value-added evaluation."

[0022] Finally, by providing teachers, students, and teaching administrators with visualized analysis results based on capability-added vectors, this invention forms a multi-role collaborative ecosystem for ensuring teaching quality, enabling teaching improvement decisions to be based on objective data evidence and improving the scientific nature and accuracy of teaching management. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a teaching quality continuous improvement system based on a nested cycle of AI and PDCA, as provided in Example 1.

[0025] Figure 2 The overall flowchart (outer loop) of the PDCA system for the talent development program provided in Example 1.

[0026] Figure 3 The PDCA flowchart (middle loop) for student personal growth is provided in Example 1.

[0027] Figure 4 The PDCA system flowchart (inner loop) for each course provided in Example 1.

[0028] Figure 5 The five-level ability development model and the four-dimensional iterative cognitive process diagram provided in Example 1.

[0029] Figure 6 The data flow diagram of ability growth formed by PDCA for different courses for students provided in Example 1.

[0030] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0032] Example 1 Embodiment 1 of the present invention provides a method for continuous improvement of teaching quality based on AI and PDCA nested cycle, which can be implemented by a teaching quality continuous improvement device based on AI and PDCA nested cycle (hereinafter referred to as improvement device), specifically, executed by one or more processors within the improvement device.

[0033] In this embodiment, the improved device may be an electronic device equipped with a processor, which carries a computer program for the continuous improvement of teaching quality based on the AI ​​and PDCA nested cycle and the computer program can be executed, such as a computer, smartphone, smart tablet, workstation, etc., which are not limited here.

[0034] like Figure 1 As shown, a teaching quality continuous improvement system based on AI and PDCA nested loop includes mutually nested outer, middle and inner loops. It is used to quantify the value-added of students' abilities, structure and model teaching objectives, and break down the barriers between micro-optimization of courses and macro-optimization of majors.

[0035] The core of this system lies in constructing a data-driven, spiraling quality assurance system that extends from micro-level courses to macro-level professional standards. Here, PDCA stands for Planning (P), Execution (D), Checking (C), and Improvement (A), respectively.

[0036] The outer cycle is used for the PDCA cycle of the professional talent training program, and its planning phase includes the middle cycle planning phase for all students. The middle cycle is used for the PDCA cycle of individual student's personal ability development. Its planning phase is nested within the planning phase of the outer cycle and includes the planning phase of the inner cycle for all courses taken by the student. The inner loop is used for the PDCA cycle of teaching a single course, and its planning phase is nested within the planning phase of the middle loop. The capability enhancement data package generated by the inner loop during the inspection phase is fed into the middle and outer loops step by step through the student's personal capability growth data bus. The adjustments made to the talent development program by the external circulation are transmitted down the hierarchy, setting new goals and constraints for the planning stages of the medium and internal circulation.

[0037] Specifically, this system organically integrates macro-level professional development with micro-level classroom teaching through a hierarchical nesting of outer, middle, and inner loops. In this system, each PDCA cycle is configured as a data-driven, dynamic improvement process. The outer loop corresponds to... Figure 2 The talent development program illustrated uses the PDCA system, which, as the outermost quality framework, is responsible for defining the overall training specifications and quality standards for the major. The middle cycle corresponds to... Figure 3 The PDCA process for student personal development, as shown, is nested within the planning phase (P) of the outer loop, focusing on the longitudinal evolution of an individual student's abilities over their four years of university. The inner loop corresponds to... Figure 4 The PDCA system shown for each course is nested within the planning phase P of the middle cycle, and is the most basic and data-producing micro-unit in the entire system.

[0038] The single-course PDCA internal loop (basic loop, each course forms an independent loop): its core objective is to achieve a closed loop within a single course, namely "learning analysis → instructional design → instructional implementation → quantitative evaluation → instructional improvement", generating course-level competency development and value-added evaluation data, and providing basic data support for the overall student data flow.

[0039] The inner loop includes an intelligent planning module, a process tracking and data acquisition module, an intelligent diagnosis module, and a collaborative feedback improvement module.

[0040] The intelligent planning module, corresponding to the planning stage P of the inner loop, is used to construct a three-dimensional ability knowledge association graph. The three-dimensional ability knowledge association graph is used to define the relationship between knowledge points, ability points and literacy points, and to configure the contribution weight of several ability points for each assessment item, forming a structured data containing assessment item identifiers, ability point identifiers and weights stored in the system database.

[0041] Specifically, the construction process of the three-dimensional capability knowledge association graph is as follows: First, define the course quality standards and break down the three-dimensional teaching objectives: Based on the professional talent training program and graduation requirement indicators, and combined with the historical learning data in the student's total data stream, formulate the course teaching syllabus and clarify the three-dimensional objectives (quality standards) of knowledge, ability, and quality. Next, a knowledge graph of ideological and political education is constructed: the course content is broken down into detailed knowledge points in the form of a mind map, each knowledge point is marked with knowledge attributes and associated with corresponding ability point tags, while the ideological and political elements in the knowledge points are explored, the literacy point tags are extracted, and an ideological and political education graph is constructed to link knowledge points, ability points, and literacy points; finally, all teaching resources of the course are linked with the corresponding knowledge points to complete the construction of the knowledge graph of ideological and political education. Then, a competency graph is designed to achieve a visual association between knowledge points and competency points: based on the competency point tags of the ideological and political knowledge graph, a course-level competency objective system is established, and the competency objectives are bound one by one to the knowledge points in the ideological and political knowledge graph; Finally, based on the course syllabus and competency development objectives, weights are assigned to each competency point in the ideological and political knowledge graph, and assessment items are linked to competency points. The contribution weight of assessment items to competency points is set, forming a structured, computable, and weighted three-dimensional competency knowledge graph.

[0042] The knowledge point tags in the three-dimensional ability knowledge association map include key and difficult knowledge points, test points, corresponding ability points, and corresponding literacy points.

[0043] For example, teachers pre-determine the weight value of each competency point based on the teaching syllabus. For instance, the contribution weight W of the knowledge point "Thevenin's Theorem" to the competency point "Circuit Analysis and Design Ability" is 0.1. Therefore, the weight of all items associated with this competency point (including tests, assignments, project explorations, etc.) is pre-set to 0.1. For example, when generating a test in the system, selecting questions related to "Circuit Analysis and Design Ability" and assigning them 10% of the total score will give the corresponding "Circuit Analysis and Design Ability" data in the test results a weight of 0.1. Secondly, the assignment is associated with "Engineering Problem Analysis Ability" and its total score is set to 10 points. Other weight associations are similar. This set of {Assessment Item ID, Competency Point ID, Weight} correspondences is stored as a structured data unit in the system database.

[0044] This design transforms weights from external, post-analysis parameters into an integral part of the system's internal logic. It provides the foundation for automatic weighted calculations during the subsequent Check (C) phase, achieving full automation and intelligence from goal setting to performance evaluation. This graph model not only defines "what to teach," but more importantly, it pre-quantifies the contribution of each teaching element to the development of higher-order competencies at the system level, before the teaching activities even begin.

[0045] The process tracking and data acquisition module is used to implement precise teaching based on a three-dimensional capability knowledge association graph during the execution phase D of the inner loop.

[0046] Based on the learning situation analysis and three-dimensional ability knowledge association map of the P stage, teachers design teaching activities (including theoretical teaching, practical teaching, and inquiry-based activities) that are tailored to students' existing abilities. During teaching implementation, all teaching activities and assessment items (homework, quizzes, experiments, project reports, etc.) are linked to the knowledge points / ability points / competency points of the three-dimensional map. Process data during the teaching process can be collected through the Learning Management System (LMS) platform, recording students' operational behavior data within the LMS, including assessment item scores associated with the three-dimensional ability knowledge association map, and interaction logs generated during student interactions with the AI ​​learning assistant, generating individual course learning process data. The AI ​​learning assistant is deployed in the form of a chatbot, and the interaction logs include the semantic depth of student questions and their response methods to system prompts.

[0047] like Figure 5 As shown, in the practical teaching process, we innovated the "question-think-explore-understand-create" teaching model and created a unique five-stage progressive variation BOPPPS teaching model.

[0048] Question (Problem Discovery): Students generate cognitive conflict scenarios (such as "Does 5G base station radiation cause cancer?") through a three-dimensional ability knowledge association map and an AI-assisted learning agent, which stimulates the generation of questions; Thinking (Inspiring Reflection): Visualizing and linking target graphs (such as electromagnetic spectrum and biological effects), with AI-assisted learning agents, inspires thinking and critically forms preliminary solutions.

[0049] Explore (investigate and solve): Knowledge graphs guide theoretical reasoning and practical exploration (such as measuring radiation dose in different frequency bands), cultivate higher-order thinking skills, and promote the spirit of investigating things to seek truth.

[0050] Enlightenment (Sublimation and Internalization): Guide students to understand, absorb, and internalize the knowledge, and discuss the scientific ethical choices of scientists such as Qian Xuesen in conjunction with the ideological and political framework, so as to inspire a sense of identity with serving the country through science and technology. Innovation (Comprehensive Application): With the help of AI-assisted learning agents, knowledge and skills are transferred to engineering practice for comprehensive application and innovative practice (such as designing a security inspection optimization scheme based on terahertz waves).

[0051] Relying on the digital scaffold of "three-dimensional ability knowledge association map + AI-assisted learning intelligent agent", students are driven to complete the full cognitive leap of "discovering problems → analyzing and attributing causes → verifying solutions → constructing meaning → transferring and applying", thus creating a personalized teaching model.

[0052] At the same time, we fully promote project-based learning (PBL) to create a classroom revolution driven by real projects. For example, we have transformed core courses such as "Digital Signal Processing" into "Product Workshops," where student teams work on real industry projects such as "Smart Heart Rate Monitoring Bracelet," driving the entire process of requirements analysis, algorithm design, and hardware implementation. Through "learning by doing and creating while learning," students develop their abilities and achieve a cognitive sublimation through "four iterations (sensory, intellectual, rational, and spiritual)."

[0053] The intelligent diagnostic module is used to execute the capability value-added evaluation model in the inspection phase C of the inner loop. The capability value-added evaluation model is based on the three-dimensional capability knowledge association map and process data and operation behavior data collected by the LMS platform. Combined with the weight system preset in the P phase, it calculates the single contribution of each student's assessment item to each associated capability point, and accumulates them to obtain the total capability value-added amount of each capability point, forming a capability value-added vector, thereby obtaining the capability value-added data package.

[0054] The core of the intelligent diagnostic module lies in quantifying students' actual ability growth.

[0055] At the start of the teaching cycle, the system generates an initial ability state vector for each student using pre-assessment or historical data. Each dimension of this vector corresponds to an ability point node in the graph.

[0056] Specifically, the expression for the capability enhancement data packet is: ; ; in, Add value to students' abilities with data packages; For ability points Total added value; This represents the total number of ability points in the three-dimensional course map. For the course and the key skills The total number of related assessment items; It is the transpose symbol; As assessment item For ability points The amount of contribution of a single item; Complete the assessment items for students The actual score; As assessment item For ability points The contribution weight.

[0057] like Figure 4As shown, the ability enhancement data package is visualized in the form of individual ability enhancement evaluation radar charts and class learning heat maps, which solves the problem of difficulty in quantifying teaching effectiveness and answers the question "how much students have improved" with objective data.

[0058] For example, three types of evaluation data can be generated: process evaluation (scores for classroom activities, assignments, experiments, etc.), summative evaluation (scores for the final exam / course completion assessment), and value-added evaluation (scores for abilities at the end of the course minus scores for basic abilities at the beginning of the course). All evaluation data are linked to individual students to form quantitative data on student ability development for a single course, which is then synchronized to the course-level evaluation database.

[0059] The collaborative feedback improvement module is used to convert the capability enhancement vector into a personal capability radar chart or a class learning heat map in the improvement stage A of the inner loop, and provide visualization results to teachers, students and teaching administrators respectively. At the same time, it encapsulates the generated capability enhancement data package and integrates it into the student personal capability growth data bus to drive the improvement of the inner loop, middle loop and outer loop layer by layer.

[0060] Furthermore, the student personal ability growth data bus is configured with a unified data exchange protocol.

[0061] Specifically, the improvements driving the internal, middle, and external circulation are as follows: Summarize the evaluation data of the C phase of the course, analyze teaching problems (such as weak mastery of knowledge points, low rate of achievement of ability training, and mismatch between teaching design and students' learning situation), organize teachers, learning situation analysis team and industry mentors to carry out multi-party collaborative improvement, and formulate a course teaching improvement plan.

[0062] For example, students can use "ability radar charts" for self-diagnosis to identify their personalized learning priorities. Instructional administrators can then use class learning heatmaps or evaluation data to scientifically assess course quality and promote successful learning models.

[0063] Data Branch 1 (Internal Loop Self-Improvement): Feeds the improvement plan and problem data back to the P phase of the PDCA cycle (internal loop) of this course, guiding teachers to modify the teaching design, adjust the weight configuration / assessment items, and achieve precise optimization of the next round of teaching.

[0064] Data Branch 2 (Integration into Total Data Stream): This integrates individual student's single-course ability enhancement evaluation data and weighted score data for each ability point into the student's overall data stream. This serves as the input for the P-stage of the student's ability development cycle and also forms the basis for learning analysis in the P-stage of the PDCA cycle for the next course. Teaching administrators can access and analyze large datasets of students across semesters, grades, and years on this data stream to identify students' strengths and weaknesses and implement targeted teaching. Students can then use their own growth data to make self-adjustments, leverage their strengths, and mitigate their weaknesses, thereby planning their future and receiving positive guidance for their future development.

[0065] The data stream of all students' growth converges into the external loop of the talent development program, thereby revealing systemic issues at the level of the entire professional talent development program. Based on this macro-level insight, the professional curriculum and syllabus are revised. This is a longer-term and broader external loop.

[0066] Specifically, the PDCA cycle (middle cycle) for students' personal ability development: Planning Phase P: Based on the professional training objectives of the external cycle and combined with the historical data packages in the student's personal ability growth data bus, formulate a personalized ability training plan (including course selection suggestions and practical project selection). Phase D: Students complete courses and participate in practical activities according to the plan, and the internal cycle steps of all their courses are executed. Phase C of the inspection: Extract the value-added data packages of multiple courses from the data bus, generate student ability growth trajectory maps, and quantitatively assess individual ability weaknesses and strengths; Improvement Phase A: Based on the ability growth trajectory map, push personalized learning suggestions or practical project recommendations to students, and at the same time summarize individual ability growth data into the external loop; Professional talent development program PDCA (external cycle): Planning Phase P: Based on industry needs, graduation requirements indicators, and the mid-cycle summary data of the previous cohort of students, formulate / revise the professional talent training program (including curriculum design, credit allocation, and competency development objectives). Phase D: Organize teaching according to the curriculum plan, and implement the corresponding steps for all students' mid-cycle and intra-course cycles; Inspection Phase C: Aggregate the mid-cycle summary data of all students to construct big data on the quality of professional talent training, and conduct statistical analysis by major, grade, and course group to identify systemic shortcomings in talent training; Improvement Phase A: Based on the analysis results, revise the professional talent training program for the next cohort, and pass on the adjusted goals and constraints to the planning stages of the central and internal circulation.

[0067] During system operation, all learning behaviors and performance data of students during their time at school are collected in real time and aggregated into a total data stream. For example... Figure 6 As shown, during the execution of each course's inner loop, the input data for its planning phase P comes partly from the learning analysis provided by the overall data stream, allowing teachers to conduct precise instructional design. The process-oriented and summative evaluation data generated during teaching implementation, as well as the capability enhancement data packets calculated using specific algorithms, are structurally extracted in the inspection phase C. This data flows into the improvement phase A of the inner loop, driving teachers to adjust their teaching strategies; it also converges into the planning phase P of the middle loop via the student's individual capability growth data bus, becoming the starting point for the next course or the next stage of learning. The improvement phase of the middle loop generates a student capability growth trajectory map based on the capability enhancement data packets extracted from multiple courses from the student's individual capability growth data bus, and accordingly pushes personalized learning suggestions or practical projects. Finally, all students' capability enhancement data is aggregated into the planning phase P of the outer loop upon graduation, providing a quantitative basis for revising the professional talent training program. The external cycle inspection phase aggregates all students' ability value-added data to construct big data on the quality of professional talent training. Statistical analysis is conducted by major, grade, or course group to identify systemic shortcomings in the talent training program. Curriculum settings, credit allocation, or ability training objectives are revised during the external cycle planning phase.

[0068] Therefore, the internal circulation is the data foundation for the middle circulation, which in turn is the data foundation for the external circulation. Each level of the external circulation provides macro-level guidance for its respective internal circulation, forming a nested relationship. The internal circulation provides "fuel" for the middle circulation: the "capability-added" data generated by the internal circulation is the structured input driving macro-level decision-making in the middle and external circulations. Meanwhile, the external circulation sets the "course" for the middle and internal circulations: the macro-level adjustments made by the external circulation to talent development programs will, in turn, change the initial goals and constraints of the P-stage (planning) of the middle and internal circulations.

[0069] In summary, compared with the prior art, the present invention has the following beneficial effects: This invention constructs a three-layer nested architecture, utilizes AI technology for full-process data collection, and combines a weighted competency knowledge graph with a value-added evaluation model to form a closed-loop, interconnected, and quantitative continuous improvement system for teaching quality. This system connects all levels of teaching management through a data bus, enabling the improvement of teaching quality to no longer rely on isolated, accidental improvements, but rather become a systematic, spiraling, and inevitable process, breaking through the architectural barriers from "island-style" improvement to "systematic" improvement.

[0070] This technological solution not only improves the efficiency of teaching management, but also provides solid technical support for cultivating high-quality, multi-skilled talents.

[0071] This invention achieves a fundamental innovation in the paradigm of education quality evaluation and improvement by digitally reconstructing the entire teaching chain.

[0072] Example 2 The second embodiment of the present invention also provides a method for continuous improvement of teaching quality based on a nested cycle of AI and PDCA, including: First, a nested system architecture is established, with the professional talent training program as the outer loop, the individual student's personal ability growth as the middle loop, and the teaching of a single course as the inner loop. The planning stage of the outer loop includes the planning stage of the middle loop for all students. The planning stage of each middle loop includes the planning stage of the inner loop for all courses taken by the student, forming a hierarchical nested data dependency relationship. A student personal ability growth data bus is established as the sole channel for transmitting ability value-added data packets from the inner loop to the middle loop and from the middle loop to the outer loop; the ability value-added data packets are structured ability value-added data generated by the inner loop during the inspection phase. Then execute the PDCA process of the inner loop: The planning phase P of the inner loop: For a single course, construct a weighted three-dimensional ability knowledge association graph; wherein, the three-dimensional ability knowledge association graph is used to define the relationship between knowledge points, ability points and literacy points, and to configure the contribution weight of several corresponding ability points for each assessment item, forming a structured data containing assessment item identifiers, ability point identifiers and weights stored in the system database. The inner loop execution phase D: Collect and record students' operational behavior data in the learning management system, including assessment item score data associated with the three-dimensional ability knowledge association map, as well as interaction logs generated during the interaction between students and the AI ​​learning companion agent; Inner loop inspection phase C: Based on the three-dimensional ability knowledge association map and the collected operation behavior data, calculate the single contribution of each student's assessment item to each associated ability point, and accumulate them to obtain the total ability value-added of each ability point, forming an ability value-added vector, thereby obtaining the ability value-added data package; Phase A of the internal circulation improvement: The capability enhancement vector is converted into a personal capability radar chart or a class learning heat map, and the visualization results are provided to teachers, students and teaching administrators respectively. At the same time, the capability enhancement vector is encapsulated and integrated into the student personal capability growth data bus to drive the improvement of the internal circulation, middle circulation and external circulation.

[0073] Example 3 The third embodiment of the present invention also provides a teaching quality continuous improvement device based on AI and PDCA nested cycle, which includes a memory and a processor. The memory stores a computer program, which can be executed by the processor to realize the teaching quality continuous improvement method based on AI and PDCA nested cycle as described above.

[0074] Example 4 The fourth embodiment of the present invention also provides a computer-readable storage medium storing computer-readable instructions. When the computer-readable instructions are executed by the processor of the device where the computer-readable storage medium is located, the teaching quality continuous improvement method based on AI and PDCA nested loop described above is implemented.

[0075] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A teaching quality continuous improvement system based on AI and a nested PDCA cycle, characterized in that, This includes nested outer loops, middle loops, and inner loops; Wherein, PDCA stands for Planning (P), Execution (D), Checking (C), and Improvement (A), respectively. The outer cycle is used for the PDCA cycle of the professional talent training program, and its planning phase includes the middle cycle planning phase for all students. The middle cycle is used for the PDCA cycle of individual student's personal ability development. Its planning phase is nested within the planning phase of the outer cycle and includes the planning phase of the inner cycle for all courses taken by the student. The inner loop is used for the PDCA cycle of teaching a single course, and its planning phase is nested within the planning phase of the middle loop. The capability enhancement data package generated by the inner loop during the inspection phase is fed into the middle and outer loops step by step through the student's personal capability growth data bus. The adjustments made to the talent development program by the external circulation are transmitted down the hierarchy, setting new goals and constraints for the planning stages of the medium and internal circulation.

2. The teaching quality continuous improvement system based on AI and PDCA nested cycle as described in claim 1, characterized in that... The inner loop includes an intelligent planning module, a process tracking and data acquisition module, an intelligent diagnosis module, and a collaborative feedback improvement module; The intelligent planning module, corresponding to the planning stage of the inner loop, is used to construct a three-dimensional ability knowledge association graph. The three-dimensional ability knowledge association graph is used to define the relationship between knowledge points, ability points and literacy points, and to configure the contribution weight of several ability points for each assessment item, forming a structured data containing assessment item identifiers, ability point identifiers and weights stored in the system database. The process tracking and data acquisition module is used to collect and record students' operational behavior data in the learning management system during the execution phase of the inner loop, including assessment item score data associated with the three-dimensional ability knowledge association map, and interaction logs generated during the interaction between students and the AI ​​learning companion agent. The intelligent diagnostic module is used to execute the capability enhancement evaluation model during the inspection phase of the inner loop. The capability enhancement evaluation model is based on the three-dimensional capability knowledge association map and the collected operational behavior data to calculate the single contribution of each student's assessment item to each associated capability point, and accumulates them to obtain the total capability enhancement of each capability point, forming a capability enhancement vector, thereby obtaining a capability enhancement data package. The collaborative feedback improvement module is used to convert the capability enhancement vector into a personal capability radar chart or a class learning heat map during the improvement stage of the inner loop, and provide visualization results to teachers, students and teaching administrators respectively. At the same time, the generated capability enhancement data package is encapsulated and integrated into the student personal capability growth data bus to drive the improvement of the inner loop, middle loop and outer loop.

3. The teaching quality continuous improvement system based on AI and PDCA nested cycle as described in claim 2, characterized in that... The construction process of the three-dimensional capability knowledge association graph is as follows: First, define the course quality standards and break down the three-dimensional teaching objectives: based on the professional talent training program and graduation requirement indicators, and combined with the historical learning data in the student's total data stream, formulate the course teaching syllabus and clarify the three-dimensional objectives of knowledge, ability, and quality. Next, a knowledge graph of ideological and political education is constructed: the course content is broken down into detailed knowledge points in the form of a mind map, each knowledge point is marked with knowledge attributes and associated with corresponding ability point tags, while the ideological and political elements in the knowledge points are explored, the literacy point tags are extracted, and an ideological and political education graph is constructed to link knowledge points, ability points, and literacy points; finally, all teaching resources of the course are linked with the corresponding knowledge points to complete the construction of the knowledge graph of ideological and political education. Then, a competency graph is designed to achieve a visual association between knowledge points and competency points: based on the competency point tags of the ideological and political knowledge graph, a course-level competency objective system is established, and the competency objectives are bound one by one to the knowledge points in the ideological and political knowledge graph; Finally, based on the course syllabus and competency development objectives, weights are assigned to each competency point in the ideological and political knowledge graph, and assessment items are linked to competency points. The contribution weight of assessment items to competency points is set, forming a structured, computable, and weighted three-dimensional competency knowledge graph.

4. The teaching quality continuous improvement system based on AI and PDCA nested cycle as described in claim 1, characterized in that... The student personal ability growth data bus is configured with a unified data exchange protocol.

5. A teaching quality continuous improvement system based on AI and PDCA nested cycle as described in claim 4, characterized in that... The improvement stage of the intermediate cycle is based on the ability value-added data package of multiple courses extracted from the student's personal ability growth data bus, which generates the student's ability growth trajectory map and pushes personalized learning suggestions or practice projects accordingly.

6. A teaching quality continuous improvement system based on AI and PDCA nested cycle as described in claim 4, characterized in that... The expression for the capability enhancement data packet is: ； ； in, Add value to students' abilities with data packages; For ability points Total added value; This represents the total number of ability points in the three-dimensional course map. For the course and the key skills The total number of related assessment items; It is the transpose symbol; As assessment item For ability points The amount of contribution of a single item; Complete the assessment items for students The actual score; As assessment item For ability points The contribution weight.

7. A teaching quality continuous improvement system based on AI and PDCA nested cycle as described in claim 3, characterized in that... The knowledge point tags in the three-dimensional ability knowledge association map include key and difficult knowledge points, test points, corresponding ability points, and corresponding literacy points.

8. A teaching quality continuous improvement system based on AI and PDCA nested cycle as described in claim 2, characterized in that... The AI-powered learning assistant is deployed in the form of a chatbot, and the interaction log includes the semantic depth of the student's questions and the response to system prompts.

9. A teaching quality continuous improvement system based on AI and PDCA nested cycle as described in claim 2, characterized in that... The outer loop inspection phase aggregates all students' ability value-added data packages to construct big data on the quality of professional talent training. Statistical analysis is conducted according to the dimensions of major, grade, or course group to identify systemic shortcomings in the talent training program. In the outer loop planning phase, the curriculum, credit allocation, or ability training objectives are revised.

10. A method for continuous improvement of teaching quality based on a nested cycle of AI and PDCA, wherein the method is based on the continuous improvement system for teaching quality based on a nested cycle of AI and PDCA as described in any one of claims 1-8, characterized in that... include: First, a nested system architecture is established, with the professional talent training program as the outer loop, the individual student's personal ability growth as the middle loop, and the teaching of a single course as the inner loop. The planning stage of the outer loop includes the planning stage of the middle loop for all students. The planning stage of each middle loop includes the planning stage of the inner loop for all courses taken by the student, forming a hierarchical nested data dependency relationship. A student personal ability growth data bus is established as the sole channel for transmitting ability value-added data packets from the inner loop to the middle loop and from the middle loop to the outer loop; the ability value-added data packets are structured ability value-added data generated by the inner loop during the inspection phase. Then execute the PDCA process of the inner loop: The planning phase P of the inner loop: For a single course, construct a weighted three-dimensional ability knowledge association graph; wherein, the three-dimensional ability knowledge association graph is used to define the relationship between knowledge points, ability points and literacy points, and to configure the contribution weight of several corresponding ability points for each assessment item, forming a structured data containing assessment item identifiers, ability point identifiers and weights stored in the system database. The inner loop execution phase D: Collect and record students' operational behavior data in the learning management system, including assessment item score data associated with the three-dimensional ability knowledge association map, as well as interaction logs generated during the interaction between students and the AI ​​learning companion agent; Inner loop inspection phase C: Based on the three-dimensional ability knowledge association map and the collected operation behavior data, calculate the single contribution of each student's assessment item to each associated ability point, and accumulate them to obtain the total ability value-added of each ability point, forming an ability value-added vector, thereby obtaining the ability value-added data package; Phase A of the internal circulation improvement: The capability enhancement vector is converted into a personal capability radar chart or a class learning heat map, and the visualization results are provided to teachers, students and teaching administrators respectively. At the same time, the capability enhancement vector is encapsulated and integrated into the student personal capability growth data bus to drive the improvement of the internal circulation, middle circulation and external circulation.

Images