Multi-stage teaching suggestion generation method and system based on student evidence

Abstract

The invention discloses a multi-stage teaching suggestion generation method and system based on student evidences, and belongs to the field of teaching suggestion generation, and the method comprises the steps: obtaining teaching course information and first student evidences in a pre-class preparation stage, and obtaining a multi-stage teaching suggestion based on the teaching course information and the first student evidences; teaching preparation stage suggestions are generated through the control Agent and the response Agent; in the in-class teaching stage, real-time teaching data and second student evidence are obtained, and based on the real-time teaching data and the second student evidence, real-time teaching stage suggestions are generated through the control Agent and the response Agent; in the post-class reflection stage, based on the first student evidence and the second student evidence of the first two stages, a conversation is actively initiated to the teacher to guide the reflection to support teaching improvement. Therefore, by implementing the method and the device, the problems of incomplete teaching strategy generation and lack of individuation and real-time adaptability in the prior art can be solved.

Description

A method and system for generating multi-stage teaching suggestions based on student evidence Technical Field

[0001] This invention relates to the field of instructional suggestion generation, and in particular to a multi-stage instructional suggestion generation method and system based on student evidence. Background Technology

[0002] The teaching suggestion generation field analyzes multi-dimensional data generated throughout the teaching cycle and, based on educational theories and learning science principles, transforms it into actionable and personalized teaching suggestions. This helps teachers optimize teaching decisions, improve teaching responsiveness, and enhance student engagement.

[0003] Existing technologies mainly fall into three typical categories: The first category is learning analytics dashboard systems, which visually present students' behavioral log data within the learning management system through charts. However, since this type of system is essentially a data presentation tool, it lacks in-depth analysis of the teaching significance behind the data and a strategy mapping mechanism. Teachers still need to rely on their own experience for interpretation and decision-making, failing to effectively reduce cognitive load. The second category is teaching support systems based on fixed rules or preset templates, which embed an "IF-THEN" type conditional rule base. However, because its rule system relies on manual pre-definition, it is difficult to cover complex real teaching situations and cannot integrate contextual semantics and individual student differences. Therefore, it suffers from rigid suggestions and poor adaptability, often failing, especially when facing unstructured scenarios such as interdisciplinary project-based learning. The third category is predictive models based on traditional machine learning algorithms, which use historical data to train classification or regression models to predict academic risk or performance ranges. However, since the model design is result-oriented, its output is mostly probability values ​​or classification labels, which cannot generate specific intervention measures with teaching logic and actionable results. Therefore, there is a problem of disconnect between prediction and action. Teachers still need to design corresponding teaching plans themselves, and a complete closed loop from diagnosis to strategy has not been formed.

[0004] In summary, existing technologies have significant shortcomings in automating and personalizing the transformation of student evidence into executable teaching strategies, and there is an urgent need for a technical solution that can deeply integrate student evidence and dynamically generate adaptive suggestions. Summary of the Invention

[0005] This invention provides a method and system for generating multi-stage teaching suggestions based on student evidence, which can solve the problem in the prior art that it is difficult to ensure the integrity of the generated teaching strategies while improving the personalization and real-time adaptability of the strategy suggestions.

[0006] In a first aspect, embodiments of the present invention provide a method for generating multi-stage teaching suggestions based on student evidence, comprising: acquiring teaching course information and basic information of a student group, and obtaining first student evidence based on the basic information of the student group; wherein the first student evidence includes evidence of the student's professional background, skill level, and learning motivation; obtaining a teaching strategy for the teaching preparation stage based on the teaching course information, the first student evidence, and a first preset control agent, and inputting the teaching strategy for the teaching preparation stage into a first preset response agent for natural language conversion to obtain teaching suggestions for the teaching preparation stage; acquiring classroom interaction information and teaching interaction data of the student group during the real-time teaching stage, and obtaining second student evidence based on the teaching interaction data; wherein the second student evidence includes cognitive evidence and state evidence; obtaining a teaching strategy for the real-time teaching stage based on the classroom interaction information, the second student evidence, and the first preset control agent, and inputting the teaching strategy for the real-time teaching stage into a first preset response agent for natural language conversion to obtain teaching suggestions for the real-time teaching stage.

[0007] This application's embodiments acquire multi-dimensional student evidence in stages, aligning with different phases of teaching preparation and real-time teaching. By combining teaching course information with a pre-set control agent, corresponding teaching strategies for each stage are derived. These strategies are then transformed into teaching suggestions in natural language by a pre-set response agent. This achieves a deep fit between teaching suggestions and students' professional background, skill level, learning motivation, classroom cognition, and state, making the suggestions more personalized and targeted. Furthermore, it dynamically captures classroom interactions and student feedback during real-time teaching, promptly responding to various needs and deviations in the teaching process. This compensates for the lack of dynamic adaptability and in-depth analysis capabilities in traditional solutions, reducing the cognitive load on teachers in interpreting data and designing their own teaching plans. It helps teachers scientifically optimize teaching decisions, forming a complete support system from teaching preparation to real-time teaching, thereby improving teaching quality and student learning outcomes.

[0008] As a preferred example of the first aspect, the step of obtaining the teaching strategy for the teaching preparation stage based on the teaching course information, the first student evidence, and the first preset control agent specifically involves: inputting the teaching course information, the student's professional background evidence, the skill level evidence, and the learning motivation evidence into the first preset control agent to identify common knowledge gaps and potential learning difficulties of the student group under the teaching course information, thereby obtaining a material-level teaching strategy; inputting the student's professional background evidence and skill level evidence into the first preset control agent to analyze the skill differences and background distribution of each student in the student group, thereby obtaining a group-level teaching strategy; and combining the material-level teaching strategy and the group-level teaching strategy to obtain the teaching strategy for the teaching preparation stage.

[0009] In this preferred example, by inputting teaching course information and first student evidence into the first preset control agent, the common knowledge gaps and potential learning difficulties of the student group under the corresponding course objectives can be accurately identified. The resulting material-level teaching strategy can closely align with students' learning needs, avoiding issues such as deviation from focus or redundancy in teaching materials, and ensuring the relevance and effectiveness of teaching content preparation. Simultaneously, by analyzing skill differences and background distribution within the group based on student professional background and skill level evidence, the resulting group-level teaching strategy can achieve scientific grouping of students, promoting complementary collaboration among students with different backgrounds and skill levels, and reducing uneven learning outcomes caused by arbitrary grouping. Furthermore, the teaching preparation stage strategy, which combines material-level and group-level teaching strategies, further integrates the two key aspects of teaching content design and student organization, ensuring that teaching preparation considers both what to teach and how to group students for instruction, laying the foundation for the orderly conduct of subsequent teaching activities and improved teaching effectiveness.

[0010] As a preferred example of the first aspect, obtaining the real-time teaching strategy based on the classroom interaction information, the second student evidence, and the first preset control agent specifically involves: inputting the classroom interaction information and the second student evidence into the first preset control agent to identify the comprehension biases of the student group, thereby obtaining a real-time classroom support teaching strategy; inputting the cognitive evidence and the state evidence into the first preset control agent to determine the student situation of the student group, thereby obtaining a support teaching strategy between two lessons; and combining the real-time classroom support teaching strategy and the support teaching strategy between two lessons to obtain the real-time teaching strategy.

[0011] In this preferred example, by inputting classroom interaction information and second student evidence into a second preset control agent, real-time classroom support strategies are obtained after identifying student group comprehension biases. This helps teachers adjust their teaching in a timely manner and avoid the accumulation of biases. Cognitive and state-based evidence is input into the agent to assess student performance, resulting in support strategies between lessons. These strategies can bridge learning gaps and prevent knowledge discontinuities. This combined real-time teaching phase strategy covers both immediate classroom intervention and continued support during breaks, reducing teacher workload while providing students with ongoing learning support and improving learning continuity.

[0012] As a preferred example of the first aspect, obtaining the first student evidence based on the basic information of the student group specifically involves: sequentially performing structured encoding on the basic information of each student in the student group using a preset natural language processing tool to obtain individual feature data corresponding to each student; and classifying the individual feature data corresponding to each student to obtain the first student evidence.

[0013] In this preferred example, by using a pre-set natural language processing tool to structure and encode students' basic information, information that may have been scattered and non-standardized can be transformed into regular individual characteristic data, avoiding information chaos and interpretation bias during manual processing and improving the accuracy of data processing. Furthermore, by classifying the individual characteristic data to form first student evidence, information such as students' professional background, skill level, and learning motivation can be clearly extracted, making the characteristics of the student group more intuitive and clear.

[0014] As a preferred example of the first aspect, after obtaining the teaching suggestions for the real-time teaching stage, the method further includes: inputting the teaching suggestions for the teaching preparation stage, the teaching suggestions for the real-time teaching stage, the first student evidence, and the second student evidence into a first preset response Agent to conduct a text dialogue, and then generating teaching reflection suggestions based on the content of the text dialogue.

[0015] In this preferred example, teaching suggestions from the teaching preparation stage and the real-time teaching stage, along with first and second student evidence obtained at different stages, are input into a third pre-set response agent to generate teaching reflection suggestions. This not only integrates key information from the entire teaching process with dynamic student evidence, avoiding the one-sidedness caused by relying solely on a single link or subjective experience, but also makes the reflection suggestions more comprehensive and objective. Furthermore, it eliminates the need for teachers to manually sort through scattered teaching data and suggestions to refine the direction of reflection, effectively reducing the burden of reflection organization on teachers.

[0016] Secondly, the present invention provides a multi-stage teaching suggestion generation system based on student evidence, comprising: a first data acquisition module, a first suggestion generation module, a second data acquisition module, and a second suggestion generation module; the first data acquisition module is used to acquire teaching course information and basic information of the student group, and obtain first student evidence based on the basic information of the student group; wherein, the first student evidence includes student professional background evidence, skill level evidence, and learning motivation evidence; the first suggestion generation module is used to obtain a teaching strategy for the teaching preparation stage based on the teaching course information, the first student evidence, and a first preset control agent, and input the teaching strategy for the teaching preparation stage into a first preset response agent for natural language conversion to obtain teaching suggestions for the teaching preparation stage; the second data acquisition module is used to acquire classroom interaction information and teaching interaction data of the student group during the real-time teaching stage, and obtain second student evidence based on the teaching interaction data; wherein, the second student evidence includes cognitive evidence and state evidence; the second suggestion generation module is used to obtain a teaching strategy for the real-time teaching stage based on the classroom interaction information, the second student evidence, and the first preset control agent, and input the teaching strategy for the real-time teaching stage into a first preset response agent for natural language conversion to obtain teaching suggestions for the real-time teaching stage.

[0017] As a preferred example of the second aspect, the first suggestion generation module includes a first suggestion generation unit, a second suggestion generation unit, and a third suggestion generation unit; the first suggestion generation unit is used to input the teaching course information, the student's professional background evidence, the skill level evidence, and the learning motivation evidence into a first preset control agent to identify the common knowledge gaps and potential learning difficulties of the student group under the teaching course information, and obtain a material-level teaching strategy; the second suggestion generation unit is used to input the student's professional background evidence and the skill level evidence into the first preset control agent to analyze the skill differences and background distribution of each student in the student group, and obtain a group-level teaching strategy; the third suggestion generation unit is used to combine the material-level teaching strategy and the group-level teaching strategy to obtain the teaching preparation stage teaching strategy.

[0018] As a preferred example of the second aspect, the second suggestion generation module includes a fourth suggestion generation unit, a fifth suggestion generation unit, and a sixth suggestion generation unit; the fourth suggestion generation unit is used to input the classroom interaction information and the second student evidence into the first preset control agent to identify the comprehension bias of the student group and obtain a real-time classroom support teaching strategy; the fifth suggestion generation unit is used to input the cognitive evidence and the state evidence into the first preset control agent to judge the student situation of the student group and obtain a support teaching strategy between two lessons; the sixth suggestion generation unit is used to combine the real-time classroom support teaching strategy and the support teaching strategy between two lessons to obtain the real-time teaching stage teaching strategy.

[0019] As a preferred example of the second aspect, obtaining the first student evidence based on the basic information of the student group specifically involves: sequentially performing structured encoding on the basic information of each student in the student group using a preset natural language processing tool to obtain individual feature data corresponding to each student; classifying the individual feature data corresponding to each student to obtain the first student evidence.

[0020] As a preferred example of the second aspect, after obtaining the teaching suggestions for the real-time teaching stage, the method further includes: inputting the teaching suggestions for the teaching preparation stage, the teaching suggestions for the real-time teaching stage, the first student evidence, and the second student evidence into a first preset response Agent to conduct a text dialogue, and then generating teaching reflection suggestions based on the content of the text dialogue.

[0021] In summary, this application's embodiments acquire multi-dimensional student evidence at different stages of teaching preparation and real-time teaching. By combining teaching course information with a pre-set control agent to deduce corresponding teaching strategies for each stage, and then converting this information into teaching suggestions in natural language through a pre-set response agent, it achieves a deep fit between teaching suggestions and students' professional background, skill level, learning motivation, classroom cognition, and state of mind. This makes the teaching suggestions more personalized and targeted. Furthermore, it dynamically captures classroom interactions and student feedback during real-time teaching, responding promptly to various needs and deviations in the teaching process. This compensates for the lack of dynamic adaptability and in-depth analysis capabilities in traditional solutions, reduces the cognitive load on teachers in interpreting data and designing their own teaching plans, and helps teachers scientifically optimize teaching decisions. This forms a complete support system from teaching preparation to real-time teaching, thereby improving teaching quality and student learning outcomes.

[0022] Another embodiment of the present invention provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the steps of the multi-stage teaching suggestion generation method based on student evidence of the present invention.

[0023] Another embodiment of the present invention also provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform the steps of the multi-stage teaching suggestion generation method based on student evidence of the present invention. Attached Figure Description

[0024] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments 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 from these drawings without creative effort.

[0025] Figure 1 is a flowchart illustrating an embodiment of a multi-stage teaching suggestion generation method based on student evidence provided by the present invention; Figure 2 is a module structure diagram illustrating an embodiment of a multi-stage teaching suggestion generation system based on student evidence provided by the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0028] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0029] 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.

[0030] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0031] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0032] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0033] Referring to Figure 1, in order to address the problem in the prior art of failing to guarantee the integrity of teaching strategy generation while improving the personalization and real-time adaptability of strategy suggestions, an embodiment of the present invention provides a multi-stage teaching suggestion generation method based on student evidence, comprising: S1, acquiring teaching course information and basic information of the student group, and obtaining first student evidence based on the basic information of the student group; wherein, the first student evidence includes student professional background evidence, skill level evidence, and learning motivation evidence; in some embodiments of this application, obtaining the first student evidence based on the basic information of the student group specifically involves: sequentially performing structured encoding on the basic information of each student in the student group using a preset natural language processing tool to obtain individual feature data corresponding to each student; classifying the individual feature data corresponding to each student to obtain the first student evidence.

[0034] It should be noted that before the formal start of teaching, during the teacher's lesson preparation stage, basic information about the student group is required. This basic information includes the students' professional background, prerequisite skills, interests, learning motivation, and project experience.

[0035] For example, the preset natural language processing tool is GPT-4. The basic information of each student in the student group is sequentially structured and encoded using GPT-4 to obtain the individual feature data corresponding to each student.

[0036] S2. Based on the teaching course information, the first student evidence, and the first preset control agent, a teaching strategy for the teaching preparation stage is obtained, and the teaching strategy for the teaching preparation stage is input into the first preset response agent for natural language conversion to obtain teaching suggestions for the teaching preparation stage. In some embodiments of this application, obtaining the teaching strategy for the teaching preparation stage based on the teaching course information, the first student evidence, and the first preset control agent specifically involves: inputting the teaching course information, the student's professional background evidence, the skill level evidence, and the learning motivation evidence into the first preset control agent to identify common knowledge gaps and potential learning difficulties of the student group under the teaching course information, thereby obtaining a material-level teaching strategy; inputting the student's professional background evidence and skill level evidence into the first preset control agent to analyze the skill differences and background distribution of each student in the student group, thereby obtaining a group-level teaching strategy; and combining the material-level teaching strategy and the group-level teaching strategy to obtain the teaching strategy for the teaching preparation stage.

[0037] It should be noted that this embodiment employs a multi-agent architecture consisting of a control agent and a response agent to collaboratively generate teaching strategy suggestions. The control agent is responsible for analyzing student evidence and the teaching context to determine the teaching strategies that the teacher may need; the response agent is responsible for translating the strategies into natural language suggestions that are easy for the teacher to understand and interacting with the teacher through dialogue. Both are implemented based on the Large Language Model API and Prompt Engineering, using different prompt templates to complete strategy judgment and language generation, and working collaboratively through a prompt relay mechanism.

[0038] In one specific embodiment, the process of the teaching preparation phase is as follows: During the teaching preparation phase, the teacher's teaching objectives involve complex AI algorithms, and the student evidence submitted shows that most students lack relevant background knowledge. This embodiment generates the following suggestion: It suggests that the teacher provide students with an additional simplified data processing template, or guide them to refer to the applications of AI in daily life as an alternative starting point. This suggestion is generated by the control agent, and the response agent translates it into an operable language and pushes it to the teacher, assisting them in adjusting resource allocation and teaching focus in advance.

[0039] S3. Obtain classroom interaction information and student group teaching interaction data during the real-time teaching phase, and obtain second student evidence based on the teaching interaction data; wherein, the second student evidence includes cognitive evidence and state evidence; in some embodiments of this application, obtaining the real-time teaching phase teaching strategy based on the classroom interaction information, the second student evidence, and the first preset control agent specifically involves: inputting the classroom interaction information and the second student evidence into the first preset control agent to identify the comprehension bias of the student group, and obtaining a real-time classroom support teaching strategy; inputting the cognitive evidence and the state evidence into the first preset control agent to determine the student situation of the student group, and obtaining a support teaching strategy between two lessons; combining the real-time classroom support teaching strategy and the support teaching strategy between two lessons to obtain the real-time teaching phase teaching strategy.

[0040] It should be noted that the real-time teaching phase transforms interactive data and task completion status during the teaching process into cognitive and state-based evidence of students, and generates classroom guidance strategies accordingly to assist teachers in dynamically adjusting their teaching methods. The teaching strategies in the real-time teaching phase include two categories: real-time classroom support strategies and support strategies between lessons.

[0041] Specifically, the cognitive evidence includes assignment results, group discussion records, and submissions, while the state evidence includes emotional reactions, points of confusion, and level of participation.

[0042] S4. Based on the classroom interaction information, the second student evidence, and the first preset control agent, obtain the real-time teaching strategy, and input the real-time teaching strategy into the first preset response agent for natural language conversion to obtain the real-time teaching suggestion.

[0043] In some embodiments of this application, after obtaining the teaching suggestions for the real-time teaching stage, the method further includes: inputting the teaching suggestions for the teaching preparation stage, the teaching suggestions for the real-time teaching stage, the first student evidence, and the second student evidence into a first preset response Agent to conduct a text dialogue, and then generating teaching reflection suggestions based on the content of the text dialogue.

[0044] It should be noted that a reflection phase can begin after the teaching unit concludes. Unlike traditional post-lesson assessments, the reflection phase in this embodiment does not passively provide data summaries or conclusive reports, but rather actively guides teachers to review the teaching process, identify potential problems, and stimulate self-reflection on their teaching through interactive dialogue. The key to this mechanism is that the system proactively initiates targeted questions based on data from the entire process, collaboratively reconstructing the understanding of the teaching process with the teacher.

[0045] For example, the generation of teaching reflection suggestions can be implemented in the following preferred manner: After the course, a series of prompting questions are proactively sent to the teacher via a response agent, guiding them to review the teaching choices made at key points. Then, the teacher engages in a multi-round interactive reflection process through methods such as checking boxes, providing brief answers, or responding via voice. This process essentially makes the teacher's implicit teaching judgments explicit and structured. By recording the results of this round of dialogue and the teacher's feedback, it serves as a closed-loop record of this teaching session and will also be used in the subsequent course preparation stage to improve the matching degree of suggestions.

[0046] In summary, this application's embodiments acquire multi-dimensional student evidence at different stages of teaching preparation and real-time teaching. By combining teaching course information with a pre-set control agent to deduce corresponding teaching strategies for each stage, and then converting this information into teaching suggestions in natural language through a pre-set response agent, it achieves a deep fit between teaching suggestions and students' professional background, skill level, learning motivation, classroom cognition, and state of mind. This makes the teaching suggestions more personalized and targeted. Furthermore, it dynamically captures classroom interactions and student feedback during real-time teaching, responding promptly to various needs and deviations in the teaching process. This compensates for the lack of dynamic adaptability and in-depth analysis capabilities in traditional solutions, reduces the cognitive load on teachers in interpreting data and designing their own teaching plans, and helps teachers scientifically optimize teaching decisions. This forms a complete support system from teaching preparation to real-time teaching, thereby improving teaching quality and student learning outcomes.

[0047] Example 2, as shown in Figure 2, provides a corresponding device example based on the above method example. An embodiment of the present invention provides a multi-stage teaching suggestion generation system based on student evidence, including: a first data acquisition module 21, a first suggestion generation module 22, a second data acquisition module 23, and a second suggestion generation module 24. The first data acquisition module 21 is used to acquire teaching course information and basic information of the student group, and obtain first student evidence based on the basic information of the student group; wherein, the first student evidence includes student professional background evidence, skill level evidence, and learning motivation evidence; the first suggestion generation module 22 is used to obtain teaching suggestions based on the teaching course information, the first student evidence, and a first preset control agent. The system employs a preparatory stage teaching strategy, inputting this strategy into a first preset response agent for natural language processing to obtain preparatory stage teaching suggestions. A second data acquisition module 23 acquires classroom interaction information and student interaction data during the real-time teaching stage, and generates second student evidence based on this data. This second student evidence includes cognitive and state-based evidence. A second suggestion generation module 24, based on the classroom interaction information, the second student evidence, and the first preset control agent, generates a real-time teaching strategy, inputting this strategy into the first preset response agent for natural language processing to obtain real-time teaching suggestions.

[0048] In some embodiments of this application, the first suggestion generation module 22 includes a first suggestion generation unit, a second suggestion generation unit, and a third suggestion generation unit. The first suggestion generation unit is used to input the teaching course information, the student's professional background evidence, the skill level evidence, and the learning motivation evidence into a first preset control agent to identify the common knowledge gaps and potential learning difficulties of the student group under the teaching course information, and obtain a material-level teaching strategy. The second suggestion generation unit is used to input the student's professional background evidence and the skill level evidence into the first preset control agent to analyze the skill differences and background distribution of each student in the student group, and obtain a group-level teaching strategy. The third suggestion generation unit is used to combine the material-level teaching strategy and the group-level teaching strategy to obtain the teaching preparation stage teaching strategy.

[0049] In some embodiments of this application, the second suggestion generation module 24 includes a fourth suggestion generation unit, a fifth suggestion generation unit, and a sixth suggestion generation unit; the fourth suggestion generation unit is used to input the classroom interaction information and the second student evidence into the first preset control agent to identify the comprehension bias of the student group and obtain a real-time classroom support teaching strategy; the fifth suggestion generation unit is used to input the cognitive evidence and the state evidence into the first preset control agent to judge the student situation of the student group and obtain a support teaching strategy between two lessons; the sixth suggestion generation unit is used to combine the real-time classroom support teaching strategy and the support teaching strategy between two lessons to obtain the real-time teaching stage teaching strategy.

[0050] In some embodiments of this application, obtaining the first student evidence based on the basic information of the student group specifically involves: sequentially performing structured encoding on the basic information of each student in the student group using a preset natural language processing tool to obtain individual feature data corresponding to each student; and classifying the individual feature data corresponding to each student to obtain the first student evidence.

[0051] In some embodiments of this application, after obtaining the teaching suggestions for the real-time teaching stage, the method further includes: inputting the teaching suggestions for the teaching preparation stage, the teaching suggestions for the real-time teaching stage, the first student evidence, and the second student evidence into a first preset response Agent to conduct a text dialogue, and then generating teaching reflection suggestions based on the content of the text dialogue.

[0052] For more detailed steps and working principles of this embodiment, please refer to the relevant description in Embodiment 1, but not limited to these descriptions.

[0053] In summary, this application's embodiments acquire multi-dimensional student evidence at different stages of teaching preparation and real-time teaching. By combining teaching course information with a pre-set control agent to deduce corresponding teaching strategies for each stage, and then converting this information into teaching suggestions in natural language through a pre-set response agent, it achieves a deep fit between teaching suggestions and students' professional background, skill level, learning motivation, classroom cognition, and state of mind. This makes the teaching suggestions more personalized and targeted. Furthermore, it dynamically captures classroom interactions and student feedback during real-time teaching, responding promptly to various needs and deviations in the teaching process. This compensates for the lack of dynamic adaptability and in-depth analysis capabilities in traditional solutions, reduces the cognitive load on teachers in interpreting data and designing their own teaching plans, and helps teachers scientifically optimize teaching decisions. This forms a complete support system from teaching preparation to real-time teaching, thereby improving teaching quality and student learning outcomes.

[0054] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the method for generating multi-stage teaching suggestions based on student evidence provided by any of the above-described method embodiments of the present invention.

[0055] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0056] Example 3: Based on the above embodiments of the multi-stage teaching suggestion generation method based on student evidence, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the multi-stage teaching suggestion generation method based on student evidence of any embodiment of the present invention.

[0057] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0058] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0059] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0060] Example 4: Based on the above method embodiments, another embodiment of the present invention provides a computer-readable storage medium, including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the student evidence-based multi-stage teaching suggestion generation method described in any of the above method embodiments of the present invention.

[0061] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0062] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating multi-stage teaching suggestions based on student evidence, characterized in that, include: The process involves: acquiring teaching course information and basic student information; obtaining first student evidence based on the basic student information; the first student evidence including evidence of student's professional background, skill level, and learning motivation; obtaining teaching strategies for the teaching preparation stage based on the teaching course information, the first student evidence, and a first preset control agent; inputting the teaching strategies for the teaching preparation stage into a first preset response agent for natural language processing to obtain teaching suggestions for the teaching preparation stage; acquiring classroom interaction information and student group teaching interaction data for the real-time teaching stage; obtaining second student evidence based on the teaching interaction data; the second student evidence including cognitive and state evidence; obtaining teaching strategies for the real-time teaching stage based on the classroom interaction information, the second student evidence, and the first preset control agent; inputting the teaching strategies for the real-time teaching stage into a first preset response agent for natural language processing to obtain teaching suggestions for the real-time teaching stage.

2. The method for generating multi-stage teaching suggestions based on student evidence as described in claim 1, characterized in that, The step of obtaining a teaching strategy for the teaching preparation stage based on the teaching course information, the first student evidence, and the first preset control agent is as follows: inputting the teaching course information, the student's professional background evidence, the skill level evidence, and the learning motivation evidence into the first preset control agent to identify the common knowledge gaps and potential learning difficulties of the student group under the teaching course information, and obtaining a material-level teaching strategy. The student's professional background evidence and skill level evidence are input into the first preset control agent to analyze the skill differences and background distribution of each student in the student group, and to obtain a group-level teaching strategy. The teaching strategy for the teaching preparation stage is obtained by combining the material-level teaching strategy and the group-level teaching strategy.

3. The method for generating multi-stage teaching suggestions based on student evidence as described in claim 1, characterized in that, The step of obtaining a real-time teaching strategy based on the classroom interaction information, the second student evidence, and the first preset control agent specifically involves: inputting the classroom interaction information and the second student evidence into the first preset control agent to identify comprehension biases among student groups, thereby obtaining a real-time classroom support teaching strategy; inputting the cognitive evidence and the state evidence into the first preset control agent to assess the student situation among student groups, thereby obtaining a support teaching strategy between two lessons; and combining the real-time classroom support teaching strategy and the support teaching strategy between two lessons to obtain the real-time teaching strategy for the current teaching stage.

4. The method for generating multi-stage teaching suggestions based on student evidence as described in claim 1, characterized in that, The step of obtaining the first student evidence based on the basic information of the student group specifically involves: using a preset natural language processing tool to sequentially perform structured encoding on the basic information of each student in the student group to obtain individual feature data corresponding to each student; and classifying the individual feature data corresponding to each student to obtain the first student evidence.

5. A method for generating multi-stage teaching suggestions based on student evidence as described in any one of claims 1-4, characterized in that, After obtaining the teaching suggestions for the real-time teaching stage, the method further includes: inputting the teaching suggestions for the teaching preparation stage, the teaching suggestions for the real-time teaching stage, the first student evidence, and the second student evidence into a first preset response Agent to conduct a text dialogue, and then generating teaching reflection suggestions based on the content of the text dialogue.

6. A multi-stage teaching suggestion generation system based on student evidence, characterized in that, include: The module comprises a first data acquisition module, a first suggestion generation module, a second data acquisition module, and a second suggestion generation module; The first data acquisition module is used to acquire teaching course information and basic information of the student group, and obtain first student evidence based on the basic information of the student group; wherein, the first student evidence includes evidence of the student's professional background, skill level, and learning motivation; the first suggestion generation module is used to obtain a teaching strategy for the teaching preparation stage based on the teaching course information, the first student evidence, and a first preset control agent, and input the teaching strategy for the teaching preparation stage into a first preset response agent for natural language conversion to obtain teaching suggestions for the teaching preparation stage; the second data acquisition module is used to acquire classroom interaction information and teaching interaction data of the student group during the real-time teaching stage, and obtain second student evidence based on the teaching interaction data; wherein, the second student evidence includes cognitive evidence and state evidence; the second suggestion generation module is used to obtain a teaching strategy for the real-time teaching stage based on the classroom interaction information, the second student evidence, and the first preset control agent, and input the teaching strategy for the real-time teaching stage into a first preset response agent for natural language conversion to obtain teaching suggestions for the real-time teaching stage.

7. The multi-stage teaching suggestion generation system based on student evidence as described in claim 6, characterized in that, The first suggestion generation module includes a first suggestion generation unit, a second suggestion generation unit, and a third suggestion generation unit. The first suggestion generation unit is used to input the teaching course information, the student's professional background evidence, the skill level evidence, and the learning motivation evidence into a first preset control agent to identify the common knowledge gaps and potential learning difficulties of the student group under the teaching course information, and obtain material-level teaching strategies. The second suggestion generation unit is used to input the student's professional background evidence and the skill level evidence into the first preset control agent to analyze the skill differences and background distribution of each student in the student group, and obtain group-level teaching strategies. The third suggestion generation unit is used to combine the material-level teaching strategy and the group-level teaching strategy to obtain the teaching preparation stage teaching strategy.

8. The multi-stage teaching suggestion generation system based on student evidence as described in claim 6, characterized in that, The second suggestion generation module includes a fourth suggestion generation unit, a fifth suggestion generation unit, and a sixth suggestion generation unit. The fourth suggestion generation unit is used to input the classroom interaction information and the second student evidence into the first preset control agent to identify the comprehension bias of the student group and obtain a real-time classroom support teaching strategy. The fifth suggestion generation unit is used to input the cognitive evidence and the state evidence into the first preset control agent to judge the student situation of the student group and obtain a support teaching strategy between two lessons. The sixth suggestion generation unit is used to combine the real-time classroom support teaching strategy and the support teaching strategy between two lessons to obtain the real-time teaching stage teaching strategy.

9. A multi-stage teaching suggestion generation system based on student evidence as described in claim 6, characterized in that, The step of obtaining the first student evidence based on the basic information of the student group specifically involves: using a preset natural language processing tool to sequentially perform structured encoding on the basic information of each student in the student group to obtain individual feature data corresponding to each student; and classifying the individual feature data corresponding to each student to obtain the first student evidence.

10. A multi-stage teaching suggestion generation system based on student evidence as described in any one of claims 6-9, characterized in that, After obtaining the teaching suggestions for the real-time teaching stage, the method further includes: inputting the teaching suggestions for the teaching preparation stage, the teaching suggestions for the real-time teaching stage, the first student evidence, and the second student evidence into a first preset response Agent to conduct a text dialogue, and then generating teaching reflection suggestions based on the content of the text dialogue.

Images