Intelligent teaching material generation method, device, equipment, product and system based on problem chain

Abstract

The invention provides an intelligent teaching material generation method, device, equipment, product and system based on a problem chain, and the method comprises the steps: obtaining teaching task information which comprises the course content of a target course and a teaching target; calling a pre-trained large language model to generate a problem chain of the target course based on the teaching task information, and generating a teaching design of the target course based on the problem chain; wherein the question chain comprises a plurality of questions which are used for guiding students to learn the course content and achieve the teaching target and have the association relationship. The problem is intelligently generated through the large language model to solve the guided teaching design, the students can be guided to gradually and deeply learn, the learning interest of the students is stimulated, the teaching process is more orderly and coherent, the students are helped to form a systematic knowledge framework, and the learning effect is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment, product and system for intelligently generating teaching materials based on question chains. Background Art

[0002] In the field of education, the design and implementation of teaching materials have always been a key link in improving teaching quality, especially teaching design, which is a textual result of the teacher's lesson preparation process. It directly reflects the teacher's advance planning for classroom teaching and is one of the key factors affecting teaching effectiveness.

[0003] The current method of generating teaching materials is mainly through manual compilation by teachers and other professionals based on their personal experience. This process is time-consuming and laborious, and it is difficult to ensure the quality and pertinence of teaching materials. In recent years, although some computer-aided teaching design tools have emerged, most of them remain at the stage of simple template filling or content recommendation, lacking the ability of deep understanding and intelligent generation. Summary of the invention

[0004] In view of this, the embodiments of the present application are committed to providing a method, device, equipment, product and system for intelligently generating teaching materials based on a question chain, which intelligently generates problem-solving-oriented teaching designs through a large language model, significantly improving the pertinence of teaching materials and students' learning outcomes.

[0005] According to a first aspect of an embodiment of the present application, a method for intelligently generating teaching materials based on a question chain is provided, comprising:

[0006] Acquiring teaching task information, wherein the teaching task information includes course content and teaching objectives of a target course;

[0007] Calling a pre-trained large language model to generate a question chain for the target course based on the teaching task information, and generating a teaching design for the target course based on the question chain;

[0008] The question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives.

[0009] Optionally, the teaching task information also includes learning information of the target students and / or teaching strategies, and the learning information includes the target students' mastery of each knowledge point of the target course.

[0010] Optionally, calling a pre-trained large language model to generate a question chain of the target course based on the teaching task information includes:

[0011] Call the pre-trained large language model to perform the following processing:

[0012] According to the dependency relationship between the knowledge points in the course content and the teaching objectives, at least one core question of the target course is generated, and the order of solving the core questions is determined, and each core question corresponds to at least one knowledge point;

[0013] According to the core question and the dependency relationship between the knowledge points corresponding to the core question, at least one sub-question of the core question is generated, and the order of solving the sub-questions is determined. The sub-questions are used to guide students to correctly answer the core question.

[0014] Optionally, the teaching task information further includes learning information of the target student, and the learning information includes the mastery degree of each knowledge point of the target course by the target student;

[0015] According to the core question and the dependency relationship between the knowledge points corresponding to the core question, at least one sub-question of the core question is generated, including:

[0016] At least one sub-problem corresponding to the core problem is generated based on the core problem, the dependency relationship between the knowledge points corresponding to the core problem, and the optimal problem chain construction mode corresponding to the core problem. The optimal problem chain construction mode is determined based on the attribute information of the core problem and / or the learning situation information of the target student.

[0017] Optionally, the teaching task information further includes learning information of the target student, and the learning information includes the mastery degree of each knowledge point of the target course by the target student;

[0018] After generating at least one core question of the target course according to the dependency relationship of each knowledge point in the course content and the teaching objective, the method further comprises: determining a final core question from the multiple core questions, and the mastery degree of the knowledge point corresponding to the final core question by the target student meets a preset degree threshold;

[0019] and / or,

[0020] Determine the order in which the core issues should be addressed, including:

[0021] The order of solving the core problems is determined based on the dependency relationship between the knowledge points in the course content and the learning information of the target students.

[0022] Optionally, the teaching task information also includes teaching strategies;

[0023] The pre-trained large language model is called to generate the teaching design of the target course based on the question chain, including:

[0024] Call the pre-trained large language model to perform the following processing:

[0025] Determine the teaching links according to the question chain, wherein each teaching link corresponds to a question in the question chain, and the teaching order of each teaching link matches the logical relationship between the questions in the question chain;

[0026] Determine the teaching activities corresponding to each teaching link according to the teaching strategy;

[0027] According to the teaching activities corresponding to each teaching link and the course content corresponding to each teaching link, the teaching design content corresponding to each teaching link is generated.

[0028] Optionally, the method further includes:

[0029] The pre-trained large language model is called to generate the courseware of the target course according to the teaching design of the target course.

[0030] Optionally, the teaching task information further includes context information, and the context information includes at least one of the target student's environment information and the teacher's preference;

[0031] The pre-trained large language model is called to generate the courseware of the target course according to the teaching design of the target course, including:

[0032] Call the pre-trained large language model to perform the following processing:

[0033] Generate a courseware outline for the target course according to the teaching sequence of each teaching link in the teaching design;

[0034] Determine, according to the teaching design content corresponding to each teaching link and the context information, the teaching resources corresponding to the teaching design content of each teaching link, wherein the teaching resources involve at least one modality;

[0035] The courseware of the target course is generated according to the courseware outline and the teaching resources corresponding to the teaching design content of each teaching link.

[0036] Optionally, after calling the large language model to generate a question chain for the target course based on the teaching task information, and before calling the large language model to generate a teaching design for the target course based on the question chain, the method further includes:

[0037] Acquiring question chain adjustment feedback information, wherein the question chain adjustment feedback information is used to adjust the questions in the question chain;

[0038] The large language model is called to adjust the feedback information based on the question chain, and the question chain is updated to obtain an updated question chain.

[0039] According to a second aspect of an embodiment of the present application, there is provided a device for intelligently generating teaching materials based on a question chain, comprising:

[0040] The first unit is used to obtain teaching task information, wherein the teaching task information includes the course content and teaching objectives of the target course;

[0041] The second unit is used to call a pre-trained large language model to generate a question chain of the target course based on the teaching task information, and generate a teaching design of the target course based on the question chain;

[0042] The question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives.

[0043] According to a third aspect of an embodiment of the present application, there is provided an electronic device, including a memory and a processor;

[0044] The memory is connected to the processor and is used to store programs;

[0045] The processor is used to implement the intelligent generation method of teaching materials based on question chains as described in any one of the first aspects of the embodiments of the present application by running the program in the memory.

[0046] According to a fourth aspect of an embodiment of the present application, a computer program product is provided, comprising computer program instructions, which, when executed by a processor, enable the processor to implement a method for intelligently generating teaching materials based on a question chain as described in any one of the first aspects of the embodiments of the present application.

[0047] According to a fifth aspect of the embodiment of the present application, there is provided a system for intelligently generating teaching materials based on a question chain, comprising: an input module, a processing module and an output module, wherein the processing module is communicatively connected to the input module and the output module respectively;

[0048] The input module is used to obtain user input information and send the user input information to the processing module;

[0049] The processing module is used to obtain teaching task information, wherein the teaching task information includes the course content and teaching objectives of the target course; call the pre-trained large language model to generate a question chain of the target course based on the teaching task information, and generate a teaching design of the target course based on the question chain; wherein the question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives;

[0050] The output module is used to output the teaching materials of the target course, and the teaching materials include the teaching design.

[0051] The method for intelligently generating teaching materials based on question chains provided in an embodiment of the present application first obtains teaching task information, wherein the teaching task information includes the course content and teaching objectives of the target course; then, a pre-trained large language model is called to generate a question chain for the target course based on the teaching task information, and a teaching design for the target course is generated based on the question chain; wherein the question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives.

[0052] The intelligent generation method of teaching materials based on the problem chain provided by the embodiment of the present application, on the one hand, utilizes the powerful language understanding and generation ability of the large language model, can deeply understand the course content and teaching objectives in the teaching task information, so as to ensure that the generated teaching design is closely centered on the teaching core, accurately reflects the teaching intention, and avoids the subjectivity and inconsistency of the traditional manual preparation of teaching design, and improves the professionalism and accuracy of the teaching design; on the other hand, introduces the problem chain of generating the target course according to the teaching task information, and then generates the teaching design based on the problem chain. The problem chain not only covers the core knowledge points of the course, but also includes a series of guiding questions with internal logical relationships, from shallow to deep, from easy to difficult, paving a clear problem-solving oriented learning path for students. In such a teaching design, students are guided to explore in depth step by step, which not only stimulates their interest in learning, but also promotes the systematic construction and in-depth understanding of knowledge. The orderliness and coherence of the teaching process are therefore significantly enhanced, which helps students form a stable and systematic knowledge framework, and then achieves a comprehensive improvement in learning effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0054] Figure 1 A structural diagram of a system for intelligently generating teaching materials based on question chains provided in an embodiment of the present application.

[0055] Figure 2 A flowchart of a method for intelligently generating teaching materials based on question chains provided in an embodiment of the present application.

[0056] Figure 3 A flowchart of another method for intelligently generating teaching materials based on question chains provided in an embodiment of the present application.

[0057] Figure 4 A flowchart of another method for intelligently generating teaching materials based on question chains provided in an embodiment of the present application.

[0058] Figure 5 A schematic diagram of the structure of a device for intelligently generating teaching materials based on question chains provided in an embodiment of the present application.

[0059] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The technical solution of the embodiment of the present application is suitable for use in various scenarios where intelligent generation of teaching materials is required, and is suitable for various application scenarios such as school teaching, online education platforms, corporate training, scientific research institutions, etc. In the application scenario, when the user needs to generate teaching materials, specific teaching task information will be input, including the course content and teaching objectives of the target course, etc. The system will call the pre-trained large language model, and intelligently generate a series of related question chains based on these teaching task information, and further generate a complete teaching design based on these question chains. The technical solution of the embodiment of the present application can make the generation process of teaching materials more efficient and intelligent, and closely fit the teaching needs, thereby significantly improving the quality and pertinence of teaching materials, and helping to optimize teaching effects and improve learning experience.

[0061] The technical solution provided in the embodiments of the present application can be exemplarily applied to hardware devices such as processors, electronic devices, servers (including cloud servers), or packaged into software programs to be run. When the hardware device executes the processing of the technical solution of the embodiments of the present application, or the above-mentioned software program is run, the automatic splitting of the target task and the automatic calling of the application program interface required for the task can be achieved to complete the purpose of the target task. The embodiments of the present application only exemplarily introduce the specific processing of the technical solution of the present application, and do not limit the specific implementation form of the technical solution of the present application. Any technical implementation form that can execute the processing of the technical solution of the present application can be adopted by the embodiments of the present application.

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] Before introducing this application solution, the relevant technologies are first introduced:

[0064] In the field of education, the design and implementation of teaching materials have always been a key link in improving teaching quality, especially teaching design, which is a textual result of the teacher's lesson preparation process. It directly reflects the teacher's advance planning for classroom teaching and is one of the key factors affecting teaching effectiveness.

[0065] The current method of generating teaching materials is mainly through manual compilation by teachers and other professionals based on their personal experience. This process is time-consuming and laborious, and it is difficult to ensure the quality and pertinence of teaching materials. In recent years, although some computer-aided teaching design tools have emerged, most of them remain at the stage of simple template filling or content recommendation, lacking the ability of deep understanding and intelligent generation.

[0066] In view of this, the embodiments of the present application are committed to providing a method, device, equipment, product and system for intelligently generating teaching materials based on a problem chain. By intelligently generating problem-solving-oriented teaching designs through a large language model, the pertinence of teaching materials and students' learning effects are significantly improved, which are described in detail one by one in the following embodiments.

[0067] Exemplary Systems

[0068] For ease of understanding, firstly, an exemplary introduction is given to the implementation environment of the method for intelligently generating teaching materials based on question chains provided in the embodiment of the present application. Figure 1 , Figure 1 A structural schematic diagram of a system for intelligently generating teaching materials based on a question chain is provided in an embodiment of the present application. The method for intelligently generating teaching materials based on a question chain provided in the present application can be exemplarily applied to the system for intelligently generating teaching materials based on a question chain.

[0069] like Figure 1 As shown, the question chain-based teaching material intelligent generation system includes an input module 110, a processing module 120 and an output module 130, wherein the processing module 120 is communicatively connected with the input module 110 and the output module 130 respectively.

[0070] The input module 110 is used to obtain user input information and send the user input information to the processing module 120 .

[0071] The processing module 120 is used to execute the intelligent generation method of teaching materials based on question chains provided in an embodiment of the present application based on user input information, including: obtaining teaching task information, wherein the teaching task information includes the course content and teaching objectives of the target course; calling a pre-trained large language model to generate a question chain for the target course based on the teaching task information, and generating a teaching design for the target course based on the question chain; wherein the question chain includes multiple related questions for guiding students to learn the course content and achieve the teaching objectives.

[0072] As for the specific content of the intelligent generation method of teaching materials based on question chains, it will be explained in subsequent embodiments. Please refer to the content of the subsequent embodiments and will not be described in detail here.

[0073] After generating the teaching materials, the server 120 sends the generated teaching materials to the output module 130, and the output module 130 outputs the teaching materials of the target course, wherein the teaching materials include the teaching design. Optionally, the teaching materials may also include the question chain.

[0074] Optionally, the input module 110 and the output module 130 are both arranged on the client, which can be various terminal devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers and desktop computers, etc., and can also be applications running on the terminal device, such as a web browser, desktop application, mobile application, etc., which is not limited in this application.

[0075] Optionally, the processing module 120 may be an independent physical server, or a server cluster consisting of multiple physical servers, or a cloud server or a virtual machine providing cloud computing services, which is not limited in the present application.

[0076] Optionally, the communication network may be any form of wireless communication network or wired communication network, or any combination thereof, which is not limited in the present application.

[0077] Exemplary Methods

[0078] Figure 2 The following is a flow chart of a method for intelligently generating teaching materials based on a question chain provided in an embodiment of the present application. Figure 2 As shown, the intelligent generation method of teaching materials based on question chain can be applied to Figure 1 The method comprises steps S201-S202:

[0079] S201. Acquire teaching task information, where the teaching task information includes the course content and teaching objectives of the target course.

[0080] The target course can be understood as a specific course for which teaching materials (including teaching design) need to be generated, and is the object of teaching material generation.

[0081] The course content can be understood as the specific knowledge, skills or concepts that need to be imparted to students in the target course. It is the basis of teaching activities and determines the scope of knowledge that students need to master.

[0082] The teaching objectives can be understood as the effects or standards that one hopes to achieve through teaching activities, which clarify the direction of teaching and expected outcomes.

[0083] The teaching task information can be understood as a collection of relevant information required to complete a certain teaching activity, and is the basis for generating teaching materials.

[0084] Teaching task information includes the teaching objectives and course content of the target courses for which teaching activities need to be carried out, and may also include other data that is helpful for question chain or teaching generation, such as learning information, teaching strategies, teaching resource requirements, situational information, and teaching design-related requirements, etc. This application does not limit this. This will be explained in the subsequent content and will not be elaborated again.

[0085] The teaching task information can be obtained through various channels.

[0086] Optionally, the teaching task information can be directly obtained from the demand information input by the user through the input module. For example, the user can directly enter the name of the target course, the course content overview, specific teaching objectives and other key information in the input module of the system.

[0087] Optionally, the teaching task information can be retrieved, intelligently analyzed or obtained through a recommendation algorithm based on the demand information input by the user. For example, the system can retrieve the course content and course objectives of the target course in a preset database based on the course identifier input by the user (the demand information input by the user is "Please help me make a classroom teaching design for the sixth section of the eighth unit of the compulsory high school mathematics course 1''"). For example, the system can automatically match relevant teaching strategies, teaching resources or teaching style suggestions based on the course content and teaching objectives input by the user, thereby enriching and improving the teaching task information.

[0088] Optionally, teaching task information can be obtained based on relevant files uploaded by users. For example, users can upload course outlines, teaching plans, textbook chapters and other files. The system can automatically parse these files, extract key information such as course content and teaching objectives, and form teaching task information.

[0089] The demand information input by the user can be understood as the user's specific requirements and descriptions of the teaching materials that are expected to be generated. This information helps the system understand the user's intentions and needs, so as to more accurately generate teaching materials that meet the user's expectations. The teaching material generation demand information may include, but is not limited to, one or more combinations of the following information: target course name, course content overview, specific teaching objectives, teaching key points, expected teaching style, teaching time, student background description, available teaching resources, expected teaching interaction methods, evaluation methods, etc.

[0090] The demand information may be information actively input by the user, or information input by the user through multiple rounds of dialogues. The multiple rounds of dialogues are designed with the goal of guiding the user to input more complete teaching materials to generate demand information.

[0091] It should be noted that the user may input the demand information by text input or voice input, and this application does not limit this.

[0092] S202. Calling a pre-trained large language model to generate a question chain for the target course based on the teaching task information, and generating a teaching design for the target course based on the question chain; wherein the question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives.

[0093] The question chain can be understood as a series of logically interrelated questions, which aims to gradually guide students to study the course content in depth and ultimately achieve the teaching objectives.

[0094] Optionally, the question chain includes at least one core question, and each core question includes at least one sub-question. Furthermore, the sub-questions are developed around the core question to explore in depth various aspects of the core question, or to provide necessary support and preparation for the resolution of the core question. A clear hierarchical and logically rigorous structure is formed between the core question and the sub-questions, which helps students to systematically understand and master knowledge. Furthermore, some or all of the sub-questions include at least one sub-question unit, and the relationship between sub-questions and sub-question units is the same as the relationship between core questions and sub-questions, which will not be elaborated here. Furthermore, the sub-question unit can also be split into smaller units in order to explore a certain detail or difficulty in more depth and form a more sophisticated question structure, which can be based on the complexity of the course content, the students' learning needs or teaching strategies.

[0095] The teaching design can be understood as a specific implementation plan generated based on the teaching task information and the question chain.

[0096] The teaching design includes a teaching process, the teaching process includes multiple teaching links, and each teaching link includes a specific implementation plan for the link.

[0097] Optionally, the teaching design may also include one or more of the following contents: teaching objectives, teaching key points and difficulties, student abilities, learning situation analysis, content positioning, teaching evaluation, etc.

[0098] The large language model (LLM) refers to a generative deep neural network model based on a Transformer structure, which has a powerful natural language processing capability. It should be noted that any large language model can be used in the embodiments of the present application.

[0099] As an optional implementation, a single prompt is used to comprehensively indicate the generation of a question chain and a teaching design. In this implementation, a pre-trained large language model is called to generate a question chain for the target course based on the teaching task information, and a teaching design for the target course is generated based on the question chain, including: generating a first task instruction based on the teaching task information and the first task description information, the first task instruction is used to trigger the large language model to perform the first task, the first task is used to generate a question chain for the target course based on the teaching task information, and after the question chain is generated, the teaching design for the target course is continued to be generated in combination with the question chain; the first task instruction is input into the pre-trained large language model, the large language model performs the first task, and outputs the teaching design for the target course.

[0100] As an optional implementation, hierarchical prompts are used to generate question chains and teaching designs step by step. In this implementation, a pre-trained large language model is called to generate a question chain for the target course based on the teaching task information, and a teaching design for the target course is generated based on the question chain, including: generating a second task instruction according to the teaching task information and the second task description information, the second task instruction is used to trigger the large language model to perform the second task, and the second task is used to generate a question chain for the target course according to the teaching task information; inputting the second task instruction into the pre-trained large language model, and the large language model performs the second task and outputs the question chain for the target course; then generating a third task instruction according to the teaching task information, the question chain and the third task description information, the third task instruction is used to trigger the large language model to perform the third task, and the third task is used to generate the teaching design for the target course in combination with the question chain; inputting the third task instruction into the pre-trained large language model, and the large language model performs the third task and outputs the teaching design for the target course.

[0101] In the embodiment of the present application, a large language model is pre-trained.

[0102] As an optional implementation, the large language model is trained based on a combination of unsupervised training and supervised training.

[0103] First, unsupervised training is performed on any type of large language model in the prior art using unlabeled training data in the field of education, so that the large language model can learn relevant knowledge in the field of education, thereby obtaining a first large language model.

[0104] We use a large amount of text data in the field of education, which comes from various educational resource libraries, online courses, textbooks, and supplementary teaching materials. We use this data to train language modeling so that the model can capture the language rules and knowledge characteristics in the field of education. During the training process, we use advanced deep learning algorithms and model architectures, such as Transformer, to improve the learning ability and generalization performance of the model.

[0105] Optionally, the unlabeled training data may include textbooks, supplementary teaching materials, academic papers, classroom records, etc. of a specified subject. These data cover a wide range of content in the specified subject, such as mathematical concepts, physical laws, chemical experiments, historical events, etc. Through unsupervised training, the large language model can learn and understand these subject knowledge, form a preliminary knowledge system, and have the ability to generate relevant texts.

[0106] Let's take mathematics as an example. We collected a large amount of data covering a wide range of mathematics, including mathematics textbooks, supplementary teaching materials, academic papers, and classroom records, to train the large language model, so that the large language model can gradually learn the knowledge characteristics, logical structure, mathematical thinking, and mathematical ability in the field of mathematics. In addition, because mathematical knowledge itself has multiple logical reasoning methods, such as induction, deduction, etc., the large language model can learn the reasoning and explanation methods suitable for different mathematical knowledge.

[0107] After obtaining the first large language model, supervised training for a specified task is performed on the first large language model using labeled training data, so that the first large language model has the ability to perform the specified task, and a pre-trained large language model is obtained. The specified task includes the second task, the third task, and / or the first task. In order to ensure that the large language model can effectively learn and perform the specified task, the training samples need to cover a variety of teaching content and scenarios.

[0108] Optionally, a first training sample is used to perform first task training on the large language model. The first training sample includes sample teaching task information, first task description information, and label information (annotated teaching design). The first training is to enable the large language model to generate a question chain based on the sample teaching task information in the first training sample, and to generate a teaching design based on the question chain, and to ensure that the loss function determined by the teaching design output by the large language model and the annotated teaching design meets the preset requirements.

[0109] Optionally, a second training sample is used to perform a second task training on the large language model. The first training sample includes sample teaching task information, second task description information, and label information (labeled question chain), and the second training is to enable the large language model to generate a question chain according to the sample teaching task information in the second training sample, and to ensure that the loss function determined by the question chain output by the large language model and the labeled question chain meets the preset requirements.

[0110] Optionally, a third training sample is used to perform a third task training on the large language model. The third training sample includes a sample question chain, a third task description information, and label information (annotated teaching design). Optionally, the third training sample also includes sample teaching task information. The third training is aimed at enabling the large language model to generate a course design according to the sample question chain in the third training sample and the loss function determined according to the teaching design output by the large language model and the annotated teaching design to meet the preset requirements.

[0111] The intelligent generation method of teaching materials based on the problem chain provided by the embodiment of the present application, on the one hand, utilizes the powerful language understanding and generation ability of the large language model, can deeply understand the course content and teaching objectives in the teaching task information, so as to ensure that the generated teaching design is closely centered on the teaching core, accurately reflects the teaching intention, and avoids the subjectivity and inconsistency of the traditional manual preparation of teaching design, and improves the professionalism and accuracy of the teaching design; on the other hand, introduces the problem chain of generating the target course according to the teaching task information, and then generates the teaching design based on the problem chain. The problem chain not only covers the core knowledge points of the course, but also includes a series of guiding questions with internal logical relationships, from shallow to deep, from easy to difficult, paving a clear problem-solving oriented learning path for students. In such a teaching design, students are guided to explore in depth step by step, which not only stimulates their interest in learning, but also promotes the systematic construction and in-depth understanding of knowledge. The orderliness and coherence of the teaching process are therefore significantly enhanced, which helps students form a stable and systematic knowledge framework, and then achieves a comprehensive improvement in learning effects.

[0112] As an optional implementation, the teaching task information also includes the learning situation information and / or teaching strategy of the target student, and the learning situation information includes the mastery degree of each knowledge point of the target course by the target student.

[0113] The learning information can be understood as information about the specific status of the target student when learning the target course, including the target student's mastery of each knowledge point of the target course. Optionally, the learning information can also include the target student's learning foundation, learning habits, learning progress, core literacy, existing doubts and difficulties, etc.

[0114] Optionally, learning information can reflect the students' mastery of each knowledge point. By understanding the target students' learning information, we can generate question chains and teaching designs for the corresponding levels of the target students, ensuring that the sequence and rhythm of teaching activities are more in line with the learning rhythm and learning ability of the target students, thereby achieving personalized teaching.

[0115] Optionally, learning information can reflect students' mastery of each knowledge point, thereby helping to accurately locate teaching difficulties. When generating question chains, more questions can be designed to target teaching difficulties, and through repeated training and guidance, help students overcome difficulties.

[0116] The teaching strategy can be understood as a series of specific teaching methods and means used to achieve teaching objectives, including one or more of the selection of teaching content, application of teaching methods, organization of teaching activities, etc. When generating question chains or teaching designs, reasonable teaching strategies can significantly improve teaching results.

[0117] Optionally, by choosing appropriate teaching strategies, the question chain and teaching process can be designed more specifically to ensure that teaching activities are closely centered around teaching objectives, thereby improving the pertinence and effectiveness of teaching.

[0118] Optionally, the rational use of teaching methods and strategies (such as reading for self-study, listening carefully, independent thinking, independent exploration, questioning, communication and expression, hands-on practice, group cooperation, etc.) can design more diverse teaching activities to stimulate students' interest and enthusiasm in learning.

[0119] Optionally, by using appropriate teaching strategies, such as case teaching and situational teaching, students can better understand and apply the knowledge they have learned, and promote the transfer and application of knowledge.

[0120] As an optional implementation method, calling a pre-trained large language model to generate a question chain of the target course based on the teaching task information includes:

[0121] Call the pre-trained large language model to perform the following processing:

[0122] A1. According to the dependency relationship between the knowledge points in the course content and the teaching objectives, generate at least one core question of the target course and determine the order of solving the core questions. Each core question corresponds to at least one knowledge point.

[0123] Optionally, the large language model analyzes each knowledge point in the course content of the target course and understands the dependencies between the knowledge points.

[0124] Optionally, by searching in a pre-established database (which stores the knowledge graphs of each target course), the knowledge graph of the target course can be obtained, and then the dependency relationship between the knowledge points in the course content can be determined.

[0125] The dependency relationship may include sequence, cause and effect, hierarchical relationship, etc.

[0126] The teaching objectives represent the knowledge mastery and ability level that students should achieve after learning the course content. The teaching objectives will guide the large language model when generating core questions to ensure that the generated core questions can achieve the requirements of the teaching objectives after being solved.

[0127] Specifically, based on the dependencies between knowledge points and teaching objectives, the big language model will generate at least one core question. Each core question corresponds to one or more key knowledge points in the course content, aiming to guide students to think deeply and explore. In addition, the big language model will determine the order of solving each core question based on the dependencies between knowledge points and the thinking and logic of the corresponding subjects it possesses. Optionally, the order of solving each core question conforms to the students' cognitive laws and learning habits, and gradually guides students to build a complete knowledge system from simple to complex, from basic to advanced.

[0128] Furthermore, after generating at least one core question of the target course according to the dependency relationship between the knowledge points in the course content and the teaching objectives, the method also includes: determining a final core question among multiple core questions, and the target student's mastery of the knowledge points corresponding to the final core question meets a preset level threshold.

[0129] This implementation method is to further select the core questions that are most suitable for the target students based on the multiple core questions generated in step A1 according to the target students' academic information, as the core questions that need to be solved in the end, i.e., the final core questions.

[0130] The preset degree threshold can be understood as a standard or limit for measuring the target student's mastery of the knowledge points corresponding to the core questions. This threshold is used to determine whether the student's mastery of a certain knowledge point has reached the teaching requirements or expectations.

[0131] Optionally, the preset degree threshold is determined based on the zone of proximal development learning theory. The zone of proximal development learning theory believes that there are two levels of student development, one is the student's current level, which refers to the level of problem solving that can be achieved when working independently, and the other is the student's possible development level, that is, the potential obtained through teaching. The difference between the two is the zone of proximal development. Therefore, when setting the preset degree threshold, the student's zone of proximal development can be considered, and a level that is both challenging and achievable through hard work can be set to stimulate students' learning potential and enthusiasm.

[0132] Optionally, the preset degree threshold can be determined based on a combination of factors such as teaching objectives, course difficulty, and student foundation.

[0133] By reasonably setting the preset degree threshold, the core problems that are most suitable for the target students can be screened out as the core problems that need to be solved in the end, that is, the final core problems, which will help improve teaching effectiveness and students' learning experience and make teaching more in line with students' actual needs and learning characteristics.

[0134] Furthermore, determining the order of solving the core problems includes: determining the order of solving the core problems according to the dependency relationship between the knowledge points in the course content and the learning information of the target students.

[0135] According to the above content, the dependency relationship of each knowledge point in the course content (such as sequence, cause and effect, hierarchical relationship, etc.) determines the learning order and logical relationship between knowledge points. The learning information reflects the students' mastery of each knowledge point. By comprehensively analyzing the dependency relationship of knowledge points and the students' learning information, the order of solving each core problem is determined, which is consistent with the logical relationship of knowledge points and the students' cognitive laws, learning habits and learning levels.

[0136] In addition, the theory of the zone of proximal development can be combined to achieve a more optimized determination of the order in which core problems are solved.

[0137] A2. Generate at least one sub-question of the core question based on the core question and the dependency relationship between the knowledge points corresponding to the core question, and determine the order of solving the sub-questions. The sub-questions are used to guide students to correctly answer the core question.

[0138] The implementation logic of step A2 is similar to that of step A1. You may refer to the implementation logic of step A1 and will not elaborate on it here.

[0139] As an optional implementation, at least one sub-question of the core question is generated according to the core question and the dependency relationship between the knowledge points corresponding to the core question, including:

[0140] At least one sub-problem corresponding to the core problem is generated according to the core problem, the dependency relationship between the knowledge points corresponding to the core problem, and the optimal problem chain construction mode corresponding to the core problem.

[0141] The optimal question chain construction model can be understood as a method based on specific rules or algorithms to generate a question chain with the best logical order and hierarchical structure (such as induction, deduction, construction, mixing, etc.), aiming to construct a question chain that can maximize students' learning effects.

[0142] Optionally, the optimal question chain construction mode corresponding to the core question is determined based on attribute information of the core question and / or learning information of the target students.

[0143] The attribute information may be understood as the type, difficulty, and knowledge points involved of the core question.

[0144] The learning information helps to understand the actual situation of the students, so as to adjust the difficulty and sequence of the question chain to better meet the needs of the students.

[0145] Optionally, the optimal question chain construction mode corresponding to the core question can also be determined based on the teaching objectives. The teaching objectives and course requirements stipulate the knowledge mastery and ability level that students should achieve after learning the course content. These factors can guide the determination of the optimal question chain construction mode to ensure that the generated question chain can meet the teaching requirements.

[0146] As an optional implementation manner, the teaching task information also includes at least one teaching strategy.

[0147] The teaching strategy can be understood as the overall principles or programs that guide teaching activities and methods, which determine how to effectively achieve teaching goals.

[0148] In this implementation, calling a pre-trained large language model to generate a teaching design for the target course based on the question chain includes:

[0149] Call the pre-trained large language model to perform the following processing:

[0150] B1. Determine the teaching links according to the question chain, wherein each teaching link corresponds to a question in the question chain, and the teaching order of each teaching link matches the logical relationship between the questions in the question chain.

[0151] The pre-trained large language model will determine the teaching link based on the generated question chain. Each question in the question chain is regarded as a teaching node or focus, and the logical relationship between them (such as sequence, cause and effect, etc.) constitutes the teaching process or path.

[0152] For example, the large language model will identify each question in the question chain and understand the teaching focus or difficulty they each represent. Then, based on the nature and logical relationship of the questions, the question chain will be divided into different teaching links. Each link revolves around a question and aims to achieve specific teaching goals by solving the problem. Finally, based on the logical relationship between the questions in the question chain, the order of the teaching links is determined to ensure the coherence and logic of the teaching process, so that students can gradually deepen their learning and understand the course content along the established path.

[0153] B2. Determine the teaching activities corresponding to each teaching link based on the teaching strategy.

[0154] The big language model designs corresponding teaching activities for each teaching link based on the teaching strategies corresponding to the target courses.

[0155] For example, the large language model will design specific teaching activities based on the teaching strategies corresponding to the target course, and ensure that the designed teaching activities match the objectives of the teaching session, that is, the designed teaching activities should be able to help students solve problems in the current session, thereby achieving the teaching objectives.

[0156] B3. Generate the teaching design content corresponding to each teaching link based on the corresponding teaching activities and course content of each teaching link.

[0157] In this step, the model will synthesize the results of the previous two steps, integrate the course content and teaching activities, ensure that the teaching activities can be closely centered around the teaching content, and then generate the final teaching design content.

[0158] As an optional implementation, Figure 3 As shown, the course material generation method provided in this embodiment further includes step S301 after generating the teaching design based on the question chain:

[0159] The pre-trained large language model is called to generate the courseware of the target course according to the teaching design of the target course.

[0160] Specifically, after the teaching design of the target course is generated, a fourth task instruction is generated according to the teaching design and the description information of the fourth task, and the fourth task instruction is used to trigger the pre-trained large language model to perform the fourth task, and the fourth task is used to generate the courseware of the target course according to the teaching design of the target course. The fourth task instruction is input into the pre-trained large language model, and the large language model performs the fourth task to generate the courseware of the target course.

[0161] In this implementation, the large language model needs to be trained for the fourth task so that it has the ability to perform the fourth task. The specific training method can refer to the training method for other tasks in the aforementioned embodiments, and the concept is similar.

[0162] As an optional implementation, the teaching task information further includes context information, and the context information includes at least one of the target student's environment information and the teacher's preference;

[0163] The pre-trained large language model is called to generate the courseware of the target course according to the teaching design of the target course, including:

[0164] Call the pre-trained large language model to perform the following processing:

[0165] C1. Generate a courseware outline for the target course according to the teaching sequence of each teaching link in the teaching design.

[0166] The big language model first analyzes the teaching design and clarifies the teaching order of each teaching link. Then, based on the teaching order of each teaching link, the courseware outline of the target course is generated. The courseware outline can be understood as the skeleton of the courseware, which defines the overall structure of the courseware and the order of each part, and plays an important guiding role in the subsequent content filling and resource integration.

[0167] C2. Determine the teaching resources corresponding to the teaching design content of each teaching link according to the teaching design content corresponding to each teaching link and the context information, wherein the teaching resources involve at least one modality.

[0168] The Big Language Model deeply considers the specific content and contextual information of each teaching link. Contextual information includes the environment of the target students (such as region, cultural background, learning conditions, etc.) and the teacher's preferences (such as teaching style, favorite resource types, etc.). Based on this information, the Big Language Model will select the most appropriate teaching resources for each teaching link.

[0169] The teaching resources may include multiple modalities such as text, pictures, videos, audio, etc., aiming to present teaching content in the most intuitive and effective way.

[0170] Optionally, the big language model will search for matching resources in the resource library based on the content and objectives in the teaching design. These resources should be able to accurately explain or demonstrate the teaching content while being consistent with the students' cognitive level and interests.

[0171] For example, if the target students are in rural areas, they may be more inclined to use examples and pictures related to rural life; if the teacher prefers to use video resources, the model will give priority to recommending relevant teaching videos.

[0172] C3. Generate the courseware of the target course according to the courseware outline and the teaching resources of each teaching link.

[0173] The big language model will integrate the courseware outline and the teaching resources of each teaching link to generate the final target courseware. This process usually involves inserting resources into the corresponding position of the courseware, adjusting the layout and style of the resources, and adding necessary explanatory text or annotations.

[0174] As an optional implementation, Figure 4 As shown, after calling the large language model to generate the question chain of the target course based on the teaching task information, and before calling the large language model to generate the teaching design of the target course based on the question chain, the method further includes steps S401-S402:

[0175] S401. Obtaining problem chain adjustment feedback information, where the problem chain adjustment feedback information is used to adjust problems in the problem chain.

[0176] After calling the large language model to generate the question chain of the target course based on the teaching task information, in order to ensure the quality and applicability of the question chain, the question chain adjustment feedback information can be further collected. The purpose of this step is to obtain feedback and suggestions on the initially generated question chain from teachers, teaching experts or other relevant stakeholders.

[0177] Optionally, after the large language model generates the question chain of the target course, the system's output module will output it and display it to teachers, teaching experts or other relevant stakeholders for review. In this process, the system may provide a user-friendly interface so that reviewers can easily browse the question chain and evaluate the questions one by one. The evaluation method can be various, such as using a rating system, filling out a questionnaire, or writing comments and suggestions through a human-computer interaction window.

[0178] For example, a teacher may review a question chain and find that a question is too complex for students to understand. He or she can write a suggestion next to the question, such as "Simplify the statement and use more understandable language." Alternatively, a teaching expert may think that a question is too difficult and beyond the ability of the target students, so he or she may suggest that the difficulty of the question be reduced.

[0179] S402: Call the large language model to adjust feedback information based on the question chain, update the question chain, and obtain an updated question chain.

[0180] Optionally, the question chain update includes adjusting the order of questions, modifying the way questions are expressed, adding or deleting questions, adjusting the difficulty of questions, etc.

[0181] When the question chain adjustment feedback information is obtained, the large language model is called to parse the question chain adjustment feedback information, and the initially generated question chain is updated and optimized based on the question chain adjustment feedback information. After updating and optimization, the large language model will generate an updated question chain that is more in line with teaching needs and closer to students' actual learning situation.

[0182] Exemplary Devices

[0183] Corresponding to the above-mentioned method for intelligently generating teaching materials based on question chains, an embodiment of the present application also provides a device for intelligently generating teaching materials based on question chains. Figure 5 is a structural diagram of a teaching material intelligent generation device based on question chain provided in an embodiment of the present application, such as Figure 5 As shown, the teaching material intelligent generation device based on question chain provided in the embodiment of the present application includes:

[0184] The first unit 501 is used to obtain teaching task information, where the teaching task information includes the course content and teaching objectives of the target course;

[0185] The second unit 502 is used to call a pre-trained large language model to generate a question chain of the target course based on the teaching task information, and generate a teaching design of the target course based on the question chain;

[0186] The question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives.

[0187] The intelligent generation device of teaching materials based on question chain provided by the embodiment of the present application, on the one hand, utilizes the powerful language understanding and generation ability of the large language model, can deeply understand the course content and teaching objectives in the teaching task information, so as to ensure that the generated teaching design is closely centered on the teaching core, accurately reflects the teaching intention, and avoids the subjectivity and inconsistency of the traditional manual preparation of teaching design, and improves the professionalism and accuracy of the teaching design; on the other hand, introduces the strategy of generating the question chain of the target course according to the teaching task information, and then generating the teaching design based on the question chain, the question chain not only covers the core knowledge points of the course, but also includes a series of guiding questions with internal logical relationships, from shallow to deep, from easy to difficult, paving a clear problem-solving oriented learning path for students, in such a teaching design, students are guided to gradually explore in depth, which not only stimulates their interest in learning, but also promotes the systematic construction and in-depth understanding of knowledge. The orderliness and coherence of the teaching process are therefore significantly enhanced, which helps students to form a stable and systematic knowledge framework, and then achieves a comprehensive improvement in learning effects.

[0188] Optionally, the teaching task information also includes learning information of the target students and / or teaching strategies, and the learning information includes the target students' mastery of each knowledge point of the target course.

[0189] Optionally, the second unit 502 may be specifically used for:

[0190] Call the pre-trained large language model to perform the following processing:

[0191] According to the dependency relationship between the knowledge points in the course content and the teaching objectives, at least one core question of the target course is generated, and the order of solving the core questions is determined, and each core question corresponds to at least one knowledge point;

[0192] According to the core question and the dependency relationship between the knowledge points corresponding to the core question, at least one sub-question of the core question is generated, and the order of solving the sub-questions is determined. The sub-questions are used to guide students to correctly answer the core question.

[0193] Optionally, the teaching task information further includes learning information of the target student, and the learning information includes the mastery degree of each knowledge point of the target course by the target student; the second unit 502 can be specifically used for:

[0194] At least one sub-problem corresponding to the core problem is generated based on the core problem, the dependency relationship between the knowledge points corresponding to the core problem, and the optimal problem chain construction mode corresponding to the core problem. The optimal problem chain construction mode is determined based on the attribute information of the core problem and / or the learning situation information of the target student.

[0195] Optionally, the teaching task information further includes learning information of the target student, and the learning information includes the mastery degree of each knowledge point of the target course by the target student;

[0196] The second unit can be specifically used for:

[0197] After generating at least one core question of the target course according to the dependency relationship between the knowledge points in the course content and the teaching objective, a final core question is determined from the multiple core questions, and the mastery degree of the knowledge point corresponding to the final core question by the target student meets a preset degree threshold;

[0198] and / or,

[0199] The order of solving the core problems is determined based on the dependency relationship between the knowledge points in the course content and the learning information of the target students.

[0200] Optionally, the teaching task information also includes a teaching strategy; the second unit 502 can be specifically used for:

[0201] Call the pre-trained large language model to perform the following processing:

[0202] Determine the teaching links according to the question chain, wherein each teaching link corresponds to a question in the question chain, and the teaching order of each teaching link matches the logical relationship between the questions in the question chain;

[0203] Determine the teaching activities corresponding to each teaching link according to the teaching strategy;

[0204] According to the teaching activities corresponding to each teaching link and the course content corresponding to each teaching link, the teaching design content corresponding to each teaching link is generated.

[0205] Optionally, the device further comprises:

[0206] The third unit is used to call the pre-trained large language model to generate the courseware of the target course according to the teaching design of the target course.

[0207] Optionally, the teaching task information further includes context information, and the context information includes at least one of the target student's environment information and the teacher's preference; the third unit can be specifically used for:

[0208] Call the pre-trained large language model to perform the following processing:

[0209] Generate a courseware outline for the target course according to the teaching sequence of each teaching link in the teaching design;

[0210] Determine, according to the teaching design content corresponding to each teaching link and the context information, the teaching resources corresponding to the teaching design content of each teaching link, wherein the teaching resources involve at least one modality;

[0211] The courseware of the target course is generated according to the courseware outline and the teaching resources corresponding to the teaching design content of each teaching link.

[0212] Optionally, the device further comprises:

[0213] The fourth unit is used to obtain question chain adjustment feedback information after calling the large language model to generate the question chain of the target course based on the teaching task information and before calling the large language model to generate the teaching design of the target course based on the question chain, wherein the question chain adjustment feedback information is used to adjust the questions in the question chain; and call the large language model to update the question chain based on the question chain adjustment feedback information to obtain an updated question chain.

[0214] The intelligent generation device of teaching materials based on question chains provided in this embodiment belongs to the same application concept as the intelligent generation method of teaching materials based on question chains provided in the above embodiments of this application, and can execute the intelligent generation method of teaching materials based on question chains provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the intelligent generation method of teaching materials based on question chains. For technical details not fully described in this embodiment, please refer to the specific processing content of the intelligent generation method of teaching materials based on question chains provided in the above embodiments of this application, which will not be repeated here.

[0215] The functions implemented by the above first unit 501 and the second unit 502 may be implemented by the same or different processors, respectively, and the embodiment of the present application is not limited thereto.

[0216] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by the configuration file, so as to realize the functions of some or all of the above units. All units of the above devices can be implemented in the form of a processor calling software, or in the form of hardware circuits, or in part by a processor calling software, and the remaining part is implemented in the form of hardware circuits.

[0217] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0218] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0219] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0220] Exemplary Electronic Devices

[0221] Another embodiment of the present application also provides an electronic device, see Figure 6 As shown, the device includes:

[0222] Memory 200 and processor 210;

[0223] The memory 200 is connected to the processor 210 and is used to store programs;

[0224] The processor 210 is used to implement the intelligent generation method of teaching materials based on question chains disclosed in any of the above embodiments by running the program stored in the memory 200.

[0225] Specifically, the electronic device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0226] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.

[0227] A bus may include a pathway that transfers information between components of a computer system.

[0228] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0229] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0230] The memory 200 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0231] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0232] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0233] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0234] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of any one of the question chain-based teaching material intelligent generation methods provided in the above embodiments of the present application.

[0235] An embodiment of the present application also proposes a chip, which includes a processor and a data interface. The processor reads and runs the program stored in the memory through the data interface to execute the intelligent generation method of teaching materials based on question chains introduced in any of the above embodiments. The specific processing process and its beneficial effects can be found in the introduction to the embodiment of the intelligent generation method of teaching materials based on question chains.

[0236] Exemplary computer program products and storage media

[0237] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method for intelligently generating teaching materials based on question chains according to various embodiments of the present application described in any of the above embodiments of this specification.

[0238] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0239] In addition, an embodiment of the present application may also be a storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the method for intelligently generating teaching materials based on question chains according to various embodiments of the present application described in any of the above embodiments of this specification.

[0240] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0241] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0242] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0243] The modules and sub-modules in the devices and terminals of the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0244] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0245] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0246] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0247] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0248] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0249] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0250] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligently generating teaching materials based on question chains, characterized in that: include: Acquiring teaching task information, wherein the teaching task information includes course content and teaching objectives of a target course; Calling a pre-trained large language model to generate a question chain for the target course based on the teaching task information, and generating a teaching design for the target course based on the question chain; The question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives.

2. The method according to claim 1, characterized in that The teaching task information also includes the target student's learning information and / or teaching strategy. The learning information includes the target student's mastery of each knowledge point of the target course.

3. The method according to claim 1, characterized in that Calling a pre-trained large language model to generate a question chain for the target course based on the teaching task information includes: Call the pre-trained large language model to perform the following processing: According to the dependency relationship between the knowledge points in the course content and the teaching objectives, at least one core question of the target course is generated, and the order of solving the core questions is determined, and each core question corresponds to at least one knowledge point; According to the core question and the dependency relationship between the knowledge points corresponding to the core question, at least one sub-question of the core question is generated, and the order of solving the sub-questions is determined. The sub-questions are used to guide students to correctly answer the core question.

4. The method according to claim 3, characterized in that The teaching task information also includes the learning information of the target students, and the learning information includes the mastery degree of each knowledge point of the target course by the target students; According to the core question and the dependency relationship between the knowledge points corresponding to the core question, at least one sub-question of the core question is generated, including: At least one sub-problem corresponding to the core problem is generated based on the core problem, the dependency relationship between the knowledge points corresponding to the core problem, and the optimal problem chain construction mode corresponding to the core problem. The optimal problem chain construction mode is determined based on the attribute information of the core problem and / or the learning situation information of the target student.

5. The method according to claim 3, characterized in that: The teaching task information also includes the learning information of the target students, and the learning information includes the mastery degree of each knowledge point of the target course by the target students; After generating at least one core question of the target course according to the dependency relationship of each knowledge point in the course content and the teaching objective, the method further comprises: determining a final core question from the multiple core questions, and the mastery degree of the knowledge point corresponding to the final core question by the target student meets a preset degree threshold; and / or, Determine the order in which the core issues should be addressed, including: The order of solving the core problems is determined based on the dependency relationship between the knowledge points in the course content and the learning information of the target students.

6. The method according to claim 1, characterized in that The teaching task information also includes teaching strategies; The pre-trained large language model is called to generate the teaching design of the target course based on the question chain, including: Call the pre-trained large language model to perform the following processing: Determine the teaching links according to the question chain, wherein each teaching link corresponds to a question in the question chain, and the teaching order of each teaching link matches the logical relationship between the questions in the question chain; Determine the teaching activities corresponding to each teaching link according to the teaching strategy; According to the teaching activities corresponding to each teaching link and the course content corresponding to each teaching link, the teaching design content corresponding to each teaching link is generated.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: The pre-trained large language model is called to generate the courseware of the target course according to the teaching design of the target course.

8. The method according to claim 7, characterized in that The teaching task information also includes context information, and the context information includes at least one of the target student's environment information and the teacher's preference; The pre-trained large language model is called to generate the courseware of the target course according to the teaching design of the target course, including: Call the pre-trained large language model to perform the following processing: Generate a courseware outline for the target course according to the teaching sequence of each teaching link in the teaching design; Determine, according to the teaching design content corresponding to each teaching link and the context information, the teaching resources corresponding to the teaching design content of each teaching link, wherein the teaching resources involve at least one modality; The courseware of the target course is generated according to the courseware outline and the teaching resources corresponding to the teaching design content of each teaching link.

9. The method according to any one of claims 1 to 6, characterized in that: After calling the large language model to generate a question chain for the target course based on the teaching task information, and before calling the large language model to generate a teaching design for the target course based on the question chain, the method further includes: Acquiring question chain adjustment feedback information, wherein the question chain adjustment feedback information is used to adjust the questions in the question chain; The large language model is called to adjust the feedback information based on the question chain, and the question chain is updated to obtain an updated question chain.

10. A device for intelligently generating teaching materials based on question chains, characterized in that: include: The first unit is used to obtain teaching task information, wherein the teaching task information includes the course content and teaching objectives of the target course; The second unit is used to call a pre-trained large language model to generate a question chain of the target course based on the teaching task information, and generate a teaching design of the target course based on the question chain; The question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives.

11. An electronic device, characterized in that: including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the method for intelligently generating teaching materials based on question chains as described in any one of claims 1 to 9 by running the program in the memory.

12. A computer program product, characterized in that The method comprises computer program instructions, which, when executed by a processor, enable the processor to implement the method for intelligently generating teaching materials based on question chains as described in any one of claims 1 to 9.

13. A system for intelligently generating teaching materials based on question chains, characterized in that: include: An input module, a processing module and an output module, wherein the processing module is communicatively connected with the input module and the output module respectively; The input module is used to obtain user input information and send the user input information to the processing module; The processing module is used to obtain teaching task information, wherein the teaching task information includes the course content and teaching objectives of the target course; call the pre-trained large language model to generate a question chain of the target course based on the teaching task information, and generate a teaching design of the target course based on the question chain; wherein the question chain includes a plurality of related questions for guiding students to learn the course content and achieve the teaching objectives; The output module is used to output the teaching materials of the target course, and the teaching materials include the teaching design.

Images