An auxiliary learning method, device, electronic equipment and storage medium

Abstract

The application provides a learning assisting method and device, electronic equipment and storage medium, wherein the method comprises: obtaining attribute information of a target question, the attribute information comprising at least one of question content, knowledge points and target cognitive levels, the target question comprising a question answered incorrectly by a user, and the target cognitive level representing a cognitive level required by the target question to be reached by an answerer; determining an answering step corresponding to the target question according to the attribute information of the target question; and guiding the user to sequentially perform an answering process corresponding to each answering step. The application determines an answering step corresponding to a target question according to attribute information of the target question, can generate an answering step corresponding to different questions, thereby meeting the differentiated needs of different questions for answering steps, providing personalized learning experience for the user, enabling the user to more targetedly learn and master the target question, and improving the learning effect of the user.

Description

Technical Field

[0001] This application relates to the field of natural language processing technology, specifically to an auxiliary learning method, device, electronic device, and storage medium. Background Technology

[0002] Heuristic learning is a problem-solving-centered learning method that promotes learning and knowledge construction by guiding students to think actively, explore independently, and solve problems. It aims to stimulate students' thinking, innovation, and problem-solving abilities. A heuristic learning system is an educational technology system designed and implemented based on heuristic learning principles. It typically achieves heuristic learning by setting multiple online knowledge learning tasks of varying difficulty.

[0003] Existing heuristic learning systems typically require pre-set, fixed answering steps, which students must follow during the learning process. In practice, due to the vastness of the knowledge system, students need to learn a large number of questions and knowledge points, and different questions involve different knowledge points and target cognitive levels. Fixed answering steps often cannot comprehensively cover all questions, cannot meet the differentiated needs of different questions for answering steps, and thus affect students' learning outcomes. Summary of the Invention

[0004] In view of this, this application provides an auxiliary learning method, device, electronic device, and storage medium that can meet the differentiated needs of different questions for answering steps, provide users with a personalized learning experience, and improve users' learning effectiveness.

[0005] According to a first aspect of the embodiments of this application, an assisted learning method is provided, comprising:

[0006] Obtain the attribute information of the target question, the attribute information including at least one of question content, knowledge points to be tested, and target cognitive level, the target question including questions that users answered incorrectly, and the target cognitive level representing the cognitive level that the target question requires the respondent to reach;

[0007] Based on the attribute information of the target question, determine the corresponding answer steps for the target question;

[0008] Guide users to follow the answer process for each step in sequence.

[0009] Optionally, determining the answering steps corresponding to the target question based on the attribute information of the target question, and guiding the user to sequentially execute the answering process corresponding to each answering step, includes:

[0010] The attribute information of the target question is input into a pre-trained large language model, so that the large language model can determine the answer steps corresponding to the target question based on the attribute information of the target question, and guide the user to execute the answer process corresponding to each answer step in sequence.

[0011] Optionally, determining the answering steps corresponding to the target question based on the attribute information of the target question includes:

[0012] Based on the attribute information of the target question and the preset question bank, determine the answering steps corresponding to the target question;

[0013] The preset question bank contains the answer steps and attribute information for each question.

[0014] Optionally, guiding the user to sequentially execute the answering process corresponding to each answering step includes:

[0015] Generate a prompt question to guide the user to correctly complete the first step of answering the question;

[0016] If the user correctly answers the first prompt question, a second prompt question is generated to guide the user to correctly complete the second answering step;

[0017] The second answering step is the next answering step after the first answering step.

[0018] Optionally, the method further includes:

[0019] If the user fails to answer the first prompt question correctly, at least based on the knowledge points the user has mastered and the first answering steps, a first guiding question is generated to guide the user to answer the first prompt question correctly.

[0020] If the user correctly answers both the first guiding question and the first prompt question, a second prompt question is generated to guide the user to correctly complete the second answering step.

[0021] Optionally, the user's knowledge point information is determined through the following processing:

[0022] Obtain the user's historical learning data, which includes first data of the user's historical answers to questions, including at least one of the following: question content, user's answer result, question difficulty, and the knowledge point being tested.

[0023] Based on the historical learning data, it is determined whether the user has mastered the knowledge points.

[0024] Optionally, the method further includes:

[0025] During the process of guiding the user to sequentially execute the answering process corresponding to each answering step, the user's intention is determined based on the content input by the user into the large language model; when the user's intention is to guide the large language model to output the answer to the target question, a prompt message is generated, indicating that the large language model cannot output the answer to the target question before the user sequentially executes the answering process corresponding to each answering step;

[0026] And / or,

[0027] After guiding the user through the answering process of each step and correctly answering the target question, exercises related to the target question are pushed to the user.

[0028] According to a second aspect of the embodiments of this application, an auxiliary learning device is provided, comprising:

[0029] The first unit is used to obtain the attribute information of the target question. The attribute information includes at least one of the question content, the knowledge points being tested, and the target cognitive level. The target question includes questions that the user answered incorrectly. The target cognitive level represents the cognitive level that the respondent is required to reach by the target question.

[0030] The second unit is used to determine the answering steps corresponding to the target question based on the attribute information of the target question, and guide the user to execute the answering process corresponding to each answering step in sequence.

[0031] According to a third aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor;

[0032] The memory is connected to the processor and is used to store programs;

[0033] The processor is used to implement the assisted learning method as described in any one of the first aspects of the embodiments of this application by running the program in the memory.

[0034] According to a fourth aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the computer program is run by a processor, it implements the assisted learning method as described in any one of the first aspects of the present application.

[0035] The technical solution proposed in this application first obtains the attribute information of the target question. The attribute information includes at least one of the question content, the knowledge points being tested, and the target cognitive level. The target question includes questions that the user answered incorrectly. The target cognitive level represents the cognitive level that the respondent is required to reach by the target question. Then, based on the attribute information of the target question, the answering steps corresponding to the target question are determined. Finally, the user is guided to sequentially execute the answering process corresponding to each answering step.

[0036] Compared to a solution that uses the same answer steps for all questions, the technical solution proposed in this application determines the answer steps corresponding to the target question based on the attribute information of the target question. This allows for the generation of answer steps for different questions, thereby meeting the differentiated needs of different questions for answer steps, providing users with a personalized learning experience, enabling users to learn and master the target questions more effectively, and improving their learning outcomes. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating the first assisted learning method provided in the embodiments of this application.

[0039] Figure 2 This is a schematic diagram illustrating the process of guiding users to sequentially execute each answering step, as provided in the embodiments of this application.

[0040] Figure 3 This is a flowchart illustrating the second assisted learning method provided in the embodiments of this application.

[0041] Figure 4 This is a flowchart illustrating the third auxiliary learning method provided in the embodiments of this application.

[0042] Figure 5 This is a schematic diagram of the structure of an auxiliary learning device provided in an embodiment of this application.

[0043] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0044] The technical solutions provided in this application are applicable to various scenarios requiring assisted learning, such as learning platforms, self-learning systems, and exam preparation. By employing the technical solutions provided in this application, the differentiated needs of different questions for answering steps can be met, providing users with a personalized learning experience and improving their learning outcomes.

[0045] The technical solutions provided in this application can be applied, by way of example, to hardware devices such as processors, electronic devices, and servers (including cloud servers), or packaged into software programs for execution. When the hardware device executes the processing procedure of the technical solutions in this application, or when the aforementioned software program is run, the target task can be automatically split and the application programming interfaces required by the task can be automatically invoked to achieve the purpose of the target task. This application only provides illustrative descriptions of the specific processing procedure of the technical solutions in this application and does not limit the specific implementation form of the technical solutions in this application. Any technical implementation form that can execute the processing procedure of the technical solutions in this application can be adopted by this application.

[0046] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0047] Before introducing the solution proposed in this application, the relevant technologies will first be introduced:

[0048] Heuristic learning is a problem-solving-centered learning method that promotes learning and knowledge construction by guiding students to think actively, explore independently, and solve problems. It aims to stimulate students' thinking, innovation, and problem-solving abilities. A heuristic learning system is an educational technology system designed and implemented based on heuristic learning principles. It typically achieves heuristic learning by setting multiple online knowledge learning tasks of varying difficulty.

[0049] Existing heuristic learning systems typically require pre-set, fixed answering steps, which students must follow during the learning process. In practical applications, due to the complexity of the knowledge system, students need to learn a large number of questions and knowledge points, and different questions and knowledge points involve different levels of cognitive objectives. Fixed answering steps often cannot comprehensively cover all questions and knowledge points, failing to meet the differentiated needs of different knowledge points for answering steps, thus affecting students' learning outcomes.

[0050] In view of this, this application provides an auxiliary learning method, device, electronic device, and storage medium that can meet the differentiated needs of different questions for answering steps, provide users with a personalized learning experience, and improve users' learning effectiveness. These will be described in detail in the following embodiments.

[0051] Exemplary methods

[0052] Figure 1 A flowchart illustrating the first assisted learning method provided in this application embodiment. (See attached flowchart.) Figure 1 As shown, the assisted learning method provided in this embodiment includes steps S101-S103:

[0053] S101. Obtain the attribute information of the target question. The attribute information includes at least one of the question content, the knowledge points being tested, and the target cognitive level. The target question includes questions that the user answered incorrectly. The target cognitive level represents the cognitive level that the respondent is required to reach by the target question.

[0054] The target questions can be understood as questions that require guidance for users in their learning.

[0055] The target questions include those that the user answered incorrectly. Optionally, after the user answers a question, the user's answer result is obtained, and when the user's answer result indicates that the user answered the question incorrectly, the question is identified as a target question.

[0056] Optionally, target questions may also include questions where the user's answer does not meet the preset answer requirements. Each question has pre-set answer requirements, specifying the required level of completion for the user's answer. The user's answer to a question is compared with the preset answer requirements for that question. If the user's answer does not meet the preset answer requirements, that question is designated as the target question.

[0057] The content of the question can be understood as the specific information contained in the target question, including at least the question stem, and if the target question is a multiple-choice question, it may also include the options.

[0058] The knowledge points mentioned in the assessment can be understood as the knowledge points that need to be involved in answering the target questions.

[0059] The target cognitive level can be understood as the cognitive level that the target question requires the respondent to reach.

[0060] The attribute information can be any one or more combinations of question content, assessment knowledge points, and target cognitive level. When necessary in actual situations, it can also include other attribute information, such as question difficulty, etc. This application does not limit this.

[0061] Optionally, each question can be pre-set with assessment knowledge points and target cognitive levels. Once the target question is determined, the corresponding assessment knowledge points and target cognitive levels can be determined.

[0062] Optionally, the content of the question can reflect the knowledge points and target cognitive levels that the question is testing. After determining the target question, the content of the target question can be analyzed to obtain the knowledge points and target cognitive levels that the target question is testing.

[0063] S102. Based on the attribute information of the target question, determine the answering steps corresponding to the target question.

[0064] The answering steps can be understood as the thinking steps for the target question designed to guide users in mastering the target question, which can help users use heuristic learning thinking to master the target question.

[0065] A question may include multiple steps to answer it, and there are logical relationships and execution order relationships between these steps.

[0066] For example, when the target question is a multiple-choice question, there are four steps to answering the question: analyze the knowledge points being tested, analyze each option, analyze the incorrect options, and provide the correct option.

[0067] Specifically, after obtaining the attribute information of the target question, analyzing the attribute information of the target question can determine the answering steps of the target question.

[0068] As an optional implementation method, the attribute information of the target question is analyzed to determine the answering steps of the target question, including: determining the answering steps corresponding to the target question based on the attribute information of the target question and a preset question bank, wherein the preset question bank records the answering steps and attribute information of each question.

[0069] Before implementing the assisted learning method provided in this application embodiment, a question bank is pre-established. The question bank records the answer steps and attribute information for each question, that is, it records the correspondence between attribute information and answer steps. The question bank is pre-stored on the controller or server side.

[0070] Specifically, after obtaining the attribute information of the target question, the system calls the preset question bank, searches for the answer steps corresponding to the attribute information of the target question in the preset question bank, and determines the answer steps corresponding to the target question.

[0071] As an optional implementation, analyzing the attribute information of the target question to determine the corresponding answer steps can be implemented based on the processing concept of a large language model. This will be discussed in detail later and will not be elaborated upon here.

[0072] S103. Guide the user to execute the answering process corresponding to each answering step in sequence.

[0073] The answering process corresponding to the answering steps can be understood as the user's process of answering the questions at those steps.

[0074] Each step in the answering process corresponds to the user's answering process. By guiding the user to execute the answering process corresponding to each step, the user can complete the learning task for that step.

[0075] There is an execution order relationship between the various answering steps of the target question. By guiding users to execute the answering process corresponding to each answering step in sequence according to this execution order relationship, users can complete the learning task of each answering step in sequence and thus master the target question.

[0076] As an optional implementation method, such as Figure 2 As shown, the system guides the user through the answering process for each step, including steps S201-S202:

[0077] S201. Generate a first prompt question to guide the user to correctly complete the first step of answering the question.

[0078] The first step in answering a question can be understood as any step in answering the question, except for the last step.

[0079] Correctly completing the first step of the question can be understood as completing the learning task of the first step of the question, or it can be understood as correctly answering the first prompt question.

[0080] The first prompt question in the first answering step can be understood as a guiding question generated for the first answering step. It can provide users with prompts to think about, analyze, and execute the answering process corresponding to the first answering step, guiding users to complete the first answering step correctly.

[0081] Optionally, the attribute information of the target question can be analyzed to generate a first hint question.

[0082] Optionally, a first prompt question can be generated based on the knowledge points and cognitive level assessed in the target question. After obtaining the attribute information of the target question, the first prompt question corresponding to the first answering step can be generated by analyzing the knowledge points and cognitive level assessed in the target question.

[0083] Optionally, before generating the first prompt question corresponding to the first answer step based on the knowledge points and cognitive level of the target question, it is also necessary to determine the position of the first answer step in the execution order of each answer step.

[0084] S202. If the user correctly answers the first prompt question, generate a second prompt question to guide the user to correctly complete the second answer step; wherein the second answer step is the next answer step after the first answer step.

[0085] When a user correctly answers the first prompt question, it means that the user has completed the learning task of the first answering step. In this case, it is necessary to guide the user to execute the answering process corresponding to the next answering step of the first answering step according to the execution order of the answering steps of the target question, that is, guide the user to execute the answering process corresponding to the second answering step.

[0086] Specifically, after generating the first prompt question, in response to the user's answer to the first prompt question, the system obtains the user's answer result and determines whether the user has correctly answered the first prompt question. If the user has correctly answered the first prompt question, the system generates a second prompt question to guide the user to correctly complete the second answering step, and then uses the second prompt question to guide the user to perform the answering process corresponding to the second answering step.

[0087] Repeat steps S201 and S202 until the user correctly answers the prompts for each of the answer steps, that is, until the user completes the answer process for each of the answer steps.

[0088] Optionally, guiding users to sequentially execute the answering process corresponding to each answering step can also be implemented based on the processing concept of a large language model, which will be elaborated in detail in subsequent embodiments and will not be described in detail here.

[0089] The technical solution proposed in this application first obtains the attribute information of the target question. The attribute information includes at least one of the question content, the knowledge points being tested, and the target cognitive level. The target question includes questions that the user answered incorrectly. The target cognitive level represents the cognitive level that the respondent is required to reach by the target question. Then, based on the attribute information of the target question, the answering steps corresponding to the target question are determined. Finally, the user is guided to sequentially execute the answering process corresponding to each answering step.

[0090] Compared to a solution that uses the same answer steps for all questions, the technical solution proposed in this application determines the answer steps corresponding to the target question based on the attribute information of the target question. This allows for the generation of answer steps for different questions, thereby meeting the differentiated needs of different questions for answer steps, providing users with a personalized learning experience, enabling users to learn and master the target questions more effectively, and improving their learning outcomes.

[0091] When guiding users to sequentially execute the answering process for each step, there may be instances where users fail to answer the first prompt question correctly. As an optional implementation, step S103, "guiding users to sequentially execute the answering process for each step," also includes steps S203-S204:

[0092] S203. If the user fails to answer the first prompt question correctly, at least based on the knowledge points the user has mastered and the first answering steps, generate a first guiding question to guide the user to answer the first prompt question correctly.

[0093] In practical applications, users need to learn multiple knowledge points, including the knowledge points tested in the target question. The knowledge point information that users have mastered can be understood as the relevant information of the knowledge points that users have already mastered before learning the target question.

[0094] Optionally, the user's mastery of knowledge points can be represented by the user's level of knowledge point mastery. The user's level of knowledge point mastery can be understood as the user's level of understanding of existing knowledge points. For example, different levels of knowledge point mastery can be represented according to Bloom's six levels of cognitive domain objectives.

[0095] Optionally, before executing the assisted learning method provided in this embodiment, it is pre-determined that the user has already mastered the knowledge point information. Optionally, before executing step S203, it is determined that the user has already mastered the knowledge point information.

[0096] The method for determining the knowledge points that the user has mastered will be explained in subsequent embodiments and will not be detailed here.

[0097] If a user fails to answer the first prompt question correctly, it means that the user has not completed the learning task of the first solution step and has not mastered the knowledge corresponding to the first solution step.

[0098] The first guiding question can be understood as a prompt question generated in response to the first prompt question, matching the user's existing knowledge. Because the first guiding question matches the user's level of knowledge and is generated specifically for the first prompt question, it provides a bridge between the user's existing knowledge and the knowledge corresponding to the first solution step, guiding the user to correctly answer the first prompt question.

[0099] If the user fails to answer the initial prompt question correctly, a guiding question needs to be generated to help the user answer the initial prompt question correctly. By guiding the user to think about and answer the guiding question, the user can be guided to answer the initial prompt question correctly.

[0100] Optionally, if the user fails to answer the first prompt question correctly, the system analyzes the knowledge points the user has already mastered and the first answer steps to generate a first guiding question.

[0101] The analysis of the first answering step can involve determining the corresponding knowledge and learning task, or determining its position within the execution order of all answering steps. Analyzing the user's existing knowledge points can involve identifying the knowledge points the user has already mastered, i.e., determining the user's level of understanding of the learned knowledge points. Based on the determined information, the first guiding question is generated.

[0102] Optionally, if the user fails to answer the first prompt question correctly, the system analyzes the user's existing knowledge, the first answer steps, the knowledge points tested in the target question, and the target cognitive level of the target question to generate a first guiding question.

[0103] S204. If the user correctly answers the first guidance question and the first prompt question, generate a second prompt question to guide the user to correctly complete the second answering step.

[0104] Specifically, after generating the first guiding question, in response to the user's answer to the first guiding question, the system obtains the user's answer result and determines whether the user has correctly answered the first guiding question. If the user has correctly answered the first guiding question, the system guides the user to answer the first prompt question again. After the user correctly answers the first prompt, the system generates a second prompt question to guide the user to correctly complete the second answering step. The second prompt question is then used to guide the user to perform the answering process corresponding to the second answering step.

[0105] As an optional implementation, steps S203 and S204 can be implemented based on the concept of processing large language models, which will be elaborated in detail in subsequent embodiments and will not be described in detail here.

[0106] Because each user's grasp of knowledge points varies, and their learning levels differ, some users may have lower learning levels and be unable to answer the initial prompt question correctly, thus affecting the effectiveness of assisted learning. This optional implementation generates a first guiding question when a user cannot answer the initial prompt question, based on the user's existing knowledge. This first guiding question acts as a bridge between the user's existing knowledge and the knowledge corresponding to the first solution step, guiding the user to answer the prompt question correctly. This, in turn, smoothly guides the user through each step of the answering process. This optional implementation considers the differences in initial learning levels among users, allowing for flexible adjustments and personalized guidance based on the user's actual situation. This enhances user learning interest, improves learning effectiveness, and achieves a personalized, heuristic learning experience.

[0107] As an optional implementation method, the user's existing knowledge information is determined through steps A1-A2:

[0108] A1. Obtain the user's historical learning data, which includes first data of historical answers to questions, including at least one of question content, user's answer results, question difficulty, and the knowledge points being tested.

[0109] The first data may be any combination of one or more of the following: question content, user answer, question difficulty, and knowledge points being tested. The specific content of the first data is determined according to the actual situation, and this application does not limit it.

[0110] Optionally, the historical learning data may also include learning grades, test results, learning progress, historical Q&A records, etc., which are not limited in this application.

[0111] Optionally, the server's internal storage space stores historical learning data generated by the user on the assisted learning platform or service learning system. Optionally, the user's historical learning data can be retrieved from the cloud. Optionally, historical learning data can be retrieved in response to the user's input operation. It should be noted that retrieving the user's historical learning data can be implemented with reference to relevant existing technologies, and this application does not limit the specific implementation method of retrieving the user's historical learning data.

[0112] A2. Based on the historical learning data, determine the knowledge points that the user has mastered.

[0113] Optionally, feature analysis can be performed on the user's historical learning data, such as calculating the user's accuracy rate, average score, and answering time for different knowledge points; then, based on the feature analysis, significance testing can be applied to determine the knowledge points that the user has mastered.

[0114] Optionally, a cognitive diagnostic model can be used to determine the user's existing knowledge level. The user's historical learning data is input into the cognitive diagnostic model, which analyzes the historical learning data and outputs information on the knowledge points the user has mastered.

[0115] For example, the DINA (Deterministic Inputs, Noisy “And” gate model) cognitive diagnostic model is used. The user’s historical learning data is input into the DINA model, and the DINA model outputs the user’s level of knowledge mastery.

[0116] The DINA model is a probabilistic graphical model-based method used to infer a user's mastery level of different knowledge points. The formulas involved in determining a user's existing knowledge point mastery level using the DINA model are as follows:

[0117] Formula 1:

[0118]

[0119] Formula 2:

[0120]

[0121] Where, η ij η represents the potential response of user i to question j. ij =1 indicates that user i answered question j correctly, and user i has mastered all the knowledge points contained in question j. η ij =0 indicates that user i answered question j incorrectly, meaning user i did not master at least one of the knowledge points contained in question j; X ij X represents user i's response to question j. ij =0 indicates an incorrect answer, X ij =1 indicates a correct answer; α i α represents user i's mastery of knowledge points. i ={α i1 ,α i2 ,···α ik} represents the knowledge point vector possessed by user i, K represents the number of all relevant attributes, and α ik α represents user i's mastery of knowledge point k. ik =1 indicates that user i has mastered knowledge point k, α ik =0 indicates that user i has not mastered knowledge point k; In the process of analyzing historical learning data, the DINA model needs to construct a j-row, k-column Q matrix, which represents the knowledge point examination matrix for all questions. jkLet q be the element in the j-th row and k-th column of matrix Q, representing the test question j's examination of knowledge point k. jk =1 indicates that question j tests knowledge point k, q jk =0 indicates that question j does not test knowledge point k.

[0122] P j (α i α represents the knowledge level of user i. i Under the given conditions, the probability of answering question j correctly is s j g represents the probability that a user will make a mistake if they have mastered all the knowledge points tested in question j. j This represents the probability that a user guesses correctly without fully understanding all the knowledge points tested in question j.

[0123] As an optional implementation, this application embodiment provides another assisted learning method. In the assisted learning method provided in this embodiment, steps S102 and S103 are implemented based on the processing concept of a large language model. The step of determining the answering steps corresponding to the target question according to the attribute information of the target question and guiding the user to execute the answering process corresponding to each answering step in sequence includes: inputting the attribute information of the target question into a pre-trained large language model so that the large language model determines the answering steps corresponding to the target question according to the attribute information of the target question, and guiding the user to execute the answering process corresponding to each answering step in sequence.

[0124] like Figure 3 As shown, in this optional implementation, the assisted learning method provided in this embodiment includes steps S301-S302:

[0125] S301. Obtain the attribute information of the target question. The attribute information includes at least one of the following: question content, knowledge points to be tested, and target cognitive level. The target question includes questions that the user answered incorrectly. The target cognitive level represents the cognitive level that the respondent is required to reach by the target question.

[0126] Step S301 corresponds to step S101 in the aforementioned embodiment. The specific content of step S301 can be found in the content of step S101, and will not be repeated here.

[0127] S302. Input the attribute information of the target question into the pre-trained large language model, so that the large language model can determine the answering steps corresponding to the target question based on the attribute information of the target question, and guide the user to execute the answering process corresponding to each answering step in sequence.

[0128] Large language models (LLMs) refer to generative deep neural network models based on the Transformer architecture, which possess powerful natural language processing capabilities. It should be noted that any type of large language model can be used, and this application makes no limitation on it.

[0129] This application requires pre-training a large language model. Optionally, multiple sample questions are obtained through various means, the sample attribute information of the sample questions and the sample answer steps corresponding to the sample questions are determined, and the dataset composed of the sample attribute information and sample answer steps of multiple sets of sample questions is used as training samples to pre-train any of the existing large language models. This enables the pre-trained large language model to determine the answer steps corresponding to the target question based on the attribute information of the input target question, and to guide the user to execute the answer process corresponding to each answer step in sequence.

[0130] Specifically, after obtaining the attribute information of the target question, the attribute information of the target question is input into the pre-trained large language model. The large language model can then determine the answer steps corresponding to the target question based on the attribute information of the target question, and guide the user to execute the answer process corresponding to each answer step in sequence.

[0131] As an optional implementation, a pre-trained large language model guides the user to sequentially execute the answering process corresponding to each step, including:

[0132] The large language model generates a first prompt question based on the attribute information of the input target question to guide the user to correctly complete the first step of answering the question;

[0133] After the user inputs their answer to the first prompt question into the large language model, the large language model determines whether the user has correctly answered the first prompt question based on the answer. If the user has correctly answered the first prompt question, the large language model generates and outputs a second prompt question to guide the user to correctly complete the second answer step based on the attribute information of the target question. The second answer step is the next answer step after the first answer step.

[0134] Repeat the above process until the user correctly answers the prompts for each step of the question, that is, until the user completes the question-answering process for each step.

[0135] As an optional implementation, a pre-trained large language model guides the user to sequentially execute the answering process corresponding to each step, and also includes:

[0136] After the user inputs their answer to the first prompt question into the large language model, the large language model determines, based on the answer, that the user has not answered the first prompt question correctly. If the user has not answered correctly, the large language model inputs the knowledge points the user has mastered and the first answer steps into the large language model. Based on the knowledge points the user has mastered and the first answer steps, the large language model generates and outputs a first guiding question to guide the user to answer the first prompt question correctly. The first answer steps can be understood as the content of the first answer steps, or as the position of the first answer steps in the execution order of each answer step.

[0137] After the user inputs their answer to the first guiding question into the large language model, the large language model determines whether the user has correctly answered the first guiding question based on the answer. If it is determined that the user has correctly answered the first guiding question, the large language model outputs the first prompt question again.

[0138] After the user inputs their answer to the first prompt question into the large language model, the large language model determines whether the user has correctly answered the first prompt question based on the answer. If the user has correctly answered the first prompt question, the large language model generates and outputs a second prompt question to guide the user to correctly complete the second answering step based on the attribute information of the target question.

[0139] It should be noted that because the first guiding question can guide the user to correctly answer the first hint question, once the user answers the first guiding question correctly, they can generally answer the first hint question correctly as well. If the user answers the first guiding question correctly but still fails to answer the first hint question correctly, the user's existing knowledge and the first answer steps need to be input into the large language model again. The large language model will then generate another different first guiding question and guide the user to answer it. This process is repeated until the user answers the first hint question correctly or the number of iterations reaches a preset threshold.

[0140] This optional implementation relies on the excellent natural language processing capabilities of the pre-trained large language model, which can automatically guide users to execute the answering process corresponding to each answering step in sequence. For example, it can automatically generate guidance information to guide users to execute the answering process corresponding to each answering step in sequence, thereby improving guidance efficiency. At the same time, with the powerful capabilities of the large language model, the assisted learning method has greater universality.

[0141] Figure 4 The flowchart illustrates the third assisted learning method provided in this application embodiment. As an optional implementation, such as... Figure 4 As shown, the assisted learning method provided in this embodiment further includes step S401:

[0142] S401. During the process of guiding the user to sequentially execute the answering process corresponding to each answering step, the user's intention is determined based on the content input by the user into the large language model; when the user's intention is to guide the large language model to output the answer to the target question, a prompt message is generated, the prompt message indicating that the large language model cannot output the answer to the target question before the user sequentially executes the answering process corresponding to each answering step.

[0143] Specifically, during the process of guiding users to sequentially execute each step of the question-answering process using a pre-trained large language model, the content input by the user into the large language model is monitored in real time to determine the user's intent. Optionally, each time the user inputs content into the large language model, semantic understanding and intent recognition technologies are used to identify the intent behind the user's input and determine the corresponding user intent.

[0144] When the user's input to the large language model corresponds to the user's intent to guide the large language model to output the answer to the target question, a prompt message is generated to remind the user that the large language model cannot output the answer to the target question until the user has completed the answering process corresponding to each answering step in sequence, thereby guiding the user to continue to execute the answering process corresponding to the current answering step.

[0145] This application only requires the meaning of the prompt message and the function it performs, without limiting the specific content of the prompt message.

[0146] As an optional implementation, the auxiliary learning method provided in this embodiment further includes: pushing exercises related to the target question to the user after the user correctly answers the target question.

[0147] Optionally, after guiding the user to sequentially execute the answering process corresponding to each answering step and correctly answer the target question, push exercises related to the target question to the user.

[0148] Optionally, during the process of guiding the user to perform each answering step in sequence, if the user answers the target question correctly, the system will push exercises related to the target question to the user.

[0149] Exemplary device

[0150] Corresponding to the above-mentioned auxiliary learning methods, this application also provides an auxiliary learning device. Figure 5 This is a schematic diagram of the structure of an auxiliary learning device provided in an embodiment of this application, as shown below. Figure 5 As shown, the auxiliary learning device provided in this application embodiment includes:

[0151] The first unit 501 is used to obtain the attribute information of the target question. The attribute information includes at least one of the question content, the knowledge points to be tested, and the target cognitive level. The target question includes questions that the user answered incorrectly. The target cognitive level represents the cognitive level that the respondent is required to reach by the target question.

[0152] The second unit 502 is used to determine the answering steps corresponding to the target question based on the attribute information of the target question, and guide the user to execute the answering process corresponding to each answering step in sequence.

[0153] Compared to a solution that uses the same answer steps for all questions, the technical solution proposed in this application determines the answer steps corresponding to the target question based on the attribute information of the target question. This allows for the generation of answer steps for different questions, thereby meeting the differentiated needs of different questions and knowledge points for answer steps, providing users with a personalized learning experience, enabling users to learn and master target questions more effectively, and improving their learning outcomes.

[0154] Optionally, the second unit 502 can be specifically used for:

[0155] The attribute information of the target question is input into a pre-trained large language model, so that the large language model can determine the answer steps corresponding to the target question based on the attribute information of the target question, and guide the user to execute the answer process corresponding to each answer step in sequence.

[0156] Optionally, the second unit 502 can be specifically used for:

[0157] Based on the attribute information of the target question and the preset question bank, determine the answering steps corresponding to the target question;

[0158] The preset question bank contains the answer steps and attribute information for each question.

[0159] Optionally, the second unit 502 can be specifically used for:

[0160] Generate a prompt question to guide the user to correctly complete the first step of answering the question;

[0161] If the user correctly answers the first prompt question, a second prompt question is generated to guide the user to correctly complete the second answering step;

[0162] The second answering step is the next answering step after the first answering step.

[0163] Optionally, the second unit 502 can also be used for:

[0164] If the user fails to answer the first prompt question correctly, at least based on the knowledge points the user has mastered and the first answering steps, a first guiding question is generated to guide the user to answer the first prompt question correctly.

[0165] If the user correctly answers both the first guiding question and the first prompt question, a second prompt question is generated to guide the user to correctly complete the second answering step.

[0166] Optionally, the user's knowledge point information is determined through the following processing:

[0167] Obtain the user's historical learning data, which includes first data of the user's historical answers to questions, including at least one of the following: question content, user's answer result, question difficulty, and the knowledge point being tested.

[0168] Based on the historical learning data, it is determined whether the user has mastered the knowledge points.

[0169] Optionally, the device further includes:

[0170] The third unit is used to determine the user's intent based on the content input by the user into the large language model during the process of guiding the user to execute the answering process corresponding to each answering step in sequence; when the user's intent is to guide the large language model to output the answer to the target question, a prompt message is generated, the prompt message indicating that the large language model cannot output the answer to the target question before the user executes the answering process corresponding to each answering step in sequence;

[0171] And / or,

[0172] The fourth unit is used to push exercises related to the target question to the user after guiding the user to perform the answering process corresponding to each answering step in sequence and correctly answering the target question.

[0173] The auxiliary learning device provided in this embodiment belongs to the same concept as the auxiliary learning method provided in the above embodiments of this application. It can execute the auxiliary learning method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects for executing the auxiliary learning method. Technical details not described in detail in this embodiment can be found in the specific processing content of the auxiliary learning method provided in the above embodiments of this application, and will not be repeated here.

[0174] The functions implemented by the first unit 501 and the second unit 502 described above can be implemented by the same or different processors, and this application embodiment does not limit this.

[0175] It should be understood that the units in the above device can be implemented by a processor calling software. For example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit in the device. The processor can be a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. By designing the hardware circuits, some or all of the unit functions can be implemented. The hardware circuits 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 implemented by designing the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files to implement the functions of some or all of the above units. All units in the above device can be implemented entirely by a processor calling software, entirely by hardware circuits, or partially by a processor calling software with the remaining parts implemented by hardware circuits.

[0176] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or DSP. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.

[0177] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0178] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a System-on-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0179] Exemplary electronic devices

[0180] Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 6 As shown, the device includes:

[0181] Memory 200 and processor 210;

[0182] The memory 200 is connected to the processor 210 and is used to store programs;

[0183] The processor 210 is configured to implement the assisted learning method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0184] Specifically, the aforementioned electronic device may also include: a bus, a communication interface 220, an input device 230, and an output device 240.

[0185] The processor 210, memory 200, communication interface 220, input device 230, and output device 240 are interconnected via a bus. Among them:

[0186] A bus can include a pathway for transmitting information between various components of a computer system.

[0187] The processor 210 can 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 used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0188] Processor 210 may include a main processor, as well as a baseband chip, modem, etc.

[0189] The memory 200 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0190] Input device 230 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0191] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0192] The communication interface 220 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0193] 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 of the auxiliary learning methods provided in the above embodiments of this application.

[0194] This application also proposes a chip, which includes a processor and a data interface. The processor reads and runs a program stored in a memory through the data interface to execute the auxiliary learning method described in any of the above embodiments. For details of the processing and its beneficial effects, please refer to the above embodiments of the auxiliary learning method.

[0195] Exemplary computer program products and storage media

[0196] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the assisted learning methods according to various embodiments of this application as described in any of the above embodiments of this specification.

[0197] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0198] Furthermore, embodiments of this application may also be storage media storing a computer program, which is executed by a processor using the steps of the assisted learning methods according to various embodiments of this application described in any of the foregoing embodiments of this specification. Specifically, the following steps can be implemented:

[0199] S101. Obtain the attribute information of the target question. The attribute information includes at least one of the question content, the knowledge points being tested, and the target cognitive level. The target question includes questions that the user answered incorrectly. The target cognitive level represents the cognitive level that the respondent is required to reach by the target question.

[0200] S102. Based on the attribute information of the target question, determine the answering steps corresponding to the target question.

[0201] S103. Guide the user to execute the answering process corresponding to each answering step in sequence.

[0202] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0203] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0204] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.

[0205] The modules and sub-modules in the various embodiments of the present application's devices and terminals can be merged, divided, and deleted according to actual needs.

[0206] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0207] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.

[0208] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.

[0209] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0210] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0211] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0212] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily 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 this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An auxiliary learning method, characterized in that, include: Obtain the attribute information of the target question, the attribute information including at least one of question content, knowledge points to be tested, and target cognitive level, the target question including questions that users answered incorrectly, and the target cognitive level representing the cognitive level that the target question requires the respondent to reach; Based on the attribute information of the target question, determine the corresponding answer steps for the target question; Guide users to sequentially execute the answering process corresponding to each step of the question-answering process; The process of guiding the user to sequentially execute each answer step includes: Generate a prompt question to guide the user to correctly complete the first step of answering the question; If the user fails to answer the first prompt question correctly, at least based on the user's existing knowledge points and the first answering steps, a first guiding question is generated to guide the user to answer the first prompt question correctly. The user's existing knowledge points are determined through the following process: obtaining the user's historical learning data, which includes first data of historical answers, including at least one of question content, user answer results, question difficulty, and tested knowledge points; and determining the user's existing knowledge points based on the historical learning data. If the user correctly answers both the first guiding question and the first prompt question, a second prompt question is generated to guide the user to correctly complete the second answering step, wherein the second answering step is the next answering step after the first answering step.

2. The method according to claim 1, characterized in that, The step of determining the answering steps corresponding to the target question based on the attribute information of the target question, and guiding the user to sequentially execute the answering process corresponding to each answering step, includes: The attribute information of the target question is input into a pre-trained large language model, so that the large language model can determine the answer steps corresponding to the target question based on the attribute information of the target question, and guide the user to execute the answer process corresponding to each answer step in sequence.

3. The method according to claim 1 or 2, characterized in that, The step of determining the answering steps corresponding to the target question based on the attribute information of the target question includes: Based on the attribute information of the target question and the preset question bank, determine the answering steps corresponding to the target question; The preset question bank contains the answer steps and attribute information for each question.

4. The method according to claim 1 or 2, characterized in that, The method further includes: If the user correctly answers the first prompt question, a second prompt question is generated to guide the user to correctly complete the second answer step.

5. The method according to claim 2, characterized in that, The method further includes: During the process of guiding the user to sequentially execute the answering process corresponding to each answering step, the user's intention is determined based on the content input by the user into the large language model; when the user's intention is to guide the large language model to output the answer to the target question, a prompt message is generated, indicating that the large language model cannot output the answer to the target question before the user has sequentially completed the answering process corresponding to each answering step; And / or, After guiding the user through the answering process of each step and correctly answering the target question, exercises related to the target question are pushed to the user.

6. An auxiliary learning device, characterized in that, include: The first unit is used to obtain the attribute information of the target question. The attribute information includes at least one of the question content, the knowledge points being tested, and the target cognitive level. The target question includes questions that the user answered incorrectly. The target cognitive level represents the cognitive level that the respondent is required to reach by the target question. The second unit is used to determine the answering steps corresponding to the target question based on the attribute information of the target question, and guide the user to execute the answering process corresponding to each answering step in sequence; The process of guiding the user to sequentially execute each answer step includes: Generate a prompt question to guide the user to correctly complete the first step of answering the question; If the user fails to answer the first prompt question correctly, at least based on the user's existing knowledge points and the first answering steps, a first guiding question is generated to guide the user to answer the first prompt question correctly. The user's existing knowledge points are determined through the following process: obtaining the user's historical learning data, which includes first data of historical answers, including at least one of question content, user answer results, question difficulty, and tested knowledge points; and determining the user's existing knowledge points based on the historical learning data. If the user correctly answers both the first guiding question and the first prompt question, a second prompt question is generated to guide the user to correctly complete the second answering step, wherein the second answering step is the next answering step after the first answering step.

7. 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 assisted learning method as described in any one of claims 1-5 by running the program in the memory.

8. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the assisted learning method as described in any one of claims 1-5.

Images