Self-adaptive question setting method and system based on retrieval enhancement algorithm

Abstract

The invention relates to a self-adaptive question setting method and system based on a retrieval enhancement algorithm, and the method comprises the steps: collecting the answer record data of a user through a data collection module, and obtaining a user state vector and a feedback label; a test question generation strategy is adjusted according to the user state vector through a reinforcement learning unit, and learning experience of other users is migrated to adjustment of the test question generation strategy of a new user through a migration learning unit; performing retrieval in the knowledge base through the knowledge graph by adopting a retrieval enhancement algorithm, calculating the similarity between the user state and the nodes in the knowledge graph, and selecting the node with the highest similarity as a retrieval result; and generating test questions by using a graph-based retrieval enhancement generation algorithm and a large language model, and pushing the test questions to the user. Compared with the prior art, the method has the advantages of high individuation degree, real-time matching, diversification and the like.

Description

Technical Field

[0001] The present invention relates to the field of intelligent education technology, and in particular to an adaptive question generation method and system based on a retrieval enhancement algorithm. Background Art

[0002] With the rapid development of information technology, the digital transformation of the education industry is gradually advancing. Traditional teaching models often rely on teachers to design test questions and set questions according to a one-size-fits-all standard, making it difficult to make personalized adjustments according to each student's learning progress and knowledge mastery. At present, some intelligent education platforms have adopted data analysis and machine learning technologies for personalized teaching, but they are still limited to static knowledge point recommendations, question generation, or the push of review content. Existing automatic question generation technologies rely on pre-set rules or templates to generate questions, lacking flexible and intelligent control over the question generation process, making it difficult to simulate the thinking process and question-setting strategies of teachers, resulting in the generated test questions being inaccurate and diverse enough in practical applications. In addition, the question-setting system is difficult to effectively simulate the creative thinking of teachers during the question-setting process. When setting questions, teachers not only consider the learning situation of students but also flexibly adjust the type, difficulty, and knowledge coverage of questions according to teaching objectives, the difficulty of knowledge points, and the learning background of students. The deficiencies of existing automated question-setting systems lead to the lack of innovation and pertinence in the generated questions. At the same time, the learning state of students is dynamically changing. A single static question bank and fixed question-setting rules only generate a fixed set of test questions based on the historical data of students or the results of a one-time assessment, lacking the ability to adjust the test question content in real time. This static generation method cannot timely track the weak points of students' knowledge and learning progress, resulting in poor performance in personalized teaching. In recent years, retrieval enhancement algorithms have made remarkable progress in the field of natural language processing. The retrieval enhancement algorithm model combines two technical means of information retrieval and text generation, by retrieving relevant information from a large-scale external database and combining it with a generation model to generate specific content. However, the application of retrieval enhancement algorithms in the education industry is still in its initial stage. There is still a lack of mature technical solutions and implementation methods for combining retrieval enhancement algorithms with the historical learning data of students to dynamically generate test questions that meet the personalized needs of students.

[0003] Chinese Patent Application CN118861240A discloses a method and device for generating subject test questions based on large language models and retrieval enhancement. The method for generating subject test questions based on large language models and retrieval enhancement converts them into test questions in JSON format through a format parser based on large language models, and then flattens them into text-form test questions through rules; uses the flattened test questions to retrieve relevant texts in textbooks; inputs the flattened test questions, question types, knowledge points, and retrieved relevant texts into a question generator based on large language models to generate test questions. However, this application has the deficiency of not being dynamically adjusted according to user feedback. When generating test questions with retrieval enhancement, it mainly relies on knowledge points in textbooks and lacks personalized design. Therefore, how to automatically generate test questions suitable for the individual characteristics of users according to the user's learning progress, knowledge mastery, and weak links is a technical problem to be solved. Summary of the Invention

[0004] The purpose of the present invention is to provide an adaptive question generation method based on a retrieval enhancement algorithm. By generating question generation measurements through reinforcement learning, optimizing data through transfer learning, performing retrieval through a retrieval enhancement algorithm, and generating test questions based on a graph-based retrieval enhancement generation algorithm and large language models, it solves the problems of insufficient accuracy in personalized question generation and weak dynamic adjustment ability in the prior art, and realizes the real-time matching of test question generation and students' learning status.

[0005] The purpose of the present invention can be achieved through the following technical solutions: According to one aspect of the present invention, an adaptive question generation method based on a retrieval enhancement algorithm is provided, and the specific steps include: S1. The data acquisition module collects the user's answer record data, performs outlier filtering and data preprocessing, obtains the user state vector and feedback label, and inputs them into the optimization and continuous learning module; S2. The optimization and continuous learning module adjusts the test question generation strategy according to the user state vector through the reinforcement learning unit, and transfers the learning experience of other users to the adjustment of the test question generation strategy of new users through the transfer learning unit; S3. According to the user state vector and feedback label, use a retrieval enhancement algorithm to perform retrieval in the knowledge base through a knowledge graph, calculate the similarity between the user state and the nodes in the knowledge graph, and select the node with the highest similarity as the retrieval result; S4. The test question generation module generates test questions according to the user state vector, test question generation strategy, and retrieval result, using a graph-based retrieval enhancement generation algorithm and large language models, and pushes them to the user and stores them in the knowledge base.

[0006] Further, the answer record data in S1 includes user ID, answer, answer correctness, answering duration, current learning progress mark, and subjective feedback text; feedback keywords are extracted from the subjective feedback text and converted into structured feedback tags, where the feedback tags include feedback question difficulty and corresponding feedback knowledge point names; the answer record data is preprocessed to obtain the user's answering correct rate, answer error type code, and quantified learning progress.

[0007] Further, the state space of the reinforcement learning unit in S2 is the user state vector, including answering correct rate, answer error type code, answering duration, and quantified learning progress; the action space of the reinforcement learning unit includes adjusting question difficulty weight and adjusting knowledge point coverage.

[0008] In the reinforcement learning unit, a reward function is set according to the user state vector to drive the adjustment of the question generation strategy, and the reward function has the following expression: , where , , and are reward weights; is the answering correct rate; is the error type code; is the total number of error types; is the answering duration; is the quantified learning progress; is the label of the current user state vector; The adjustment of the question generation strategy is carried out through the value function, and the expression is: , where is the current strategy; is the next moment strategy parameter; is the step size amplitude parameter used to control the adjustment of the question generation strategy; is the reward function; is the user state vector value function.

[0009] Further, the transfer learning in S2 uses a long short-term memory network to predict the user's current knowledge weak points based on the user's historical answer record data, and feeds them back to the reinforcement learning unit based on the knowledge weak points.

[0010] Cluster according to the subjects selected by the user. When a user with insufficient historical answering record data enters, calculate the cosine similarity between the current user's state vector and the state vectors of users in each cluster based on the existing answering record data, and select the most similar cluster for migration. The judgment basis for insufficient historical answering record data is that the number of operations of this user is lower than the first threshold. After the number of times of using transfer learning data accumulates to the first threshold, reduce the transfer learning weight according to a preset step size and transition to pure reinforcement learning.

[0011] Further, in S3, the nodes in the knowledge graph include the knowledge point name and the difficulty of the question, and the edge attributes include the relationship type and the similarity score between nodes. In the knowledge graph, the relationship type is established by comparing the similarity score between nodes with a second threshold. The relationship types include belonging to knowledge points, associated wrong questions, easily confused knowledge points, prerequisite knowledge points, and extended knowledge points.

[0012] Calculate the user similarity between the user state vector and the nodes, and expand the similarity of the nodes corresponding to the feedback labels by a preset ratio. Sort according to the obtained user similarity, and select a preset number of nodes with the largest similarity to form a retrieval set as the retrieval result, and calculate the user similarity The expression of , where is the current user state vector, is the embedded representation of the nodes in the knowledge graph; is the node set The element in.

[0013] Further, the generated questions in S4 include the question surface, the answer, the difficulty level, and the corresponding knowledge points. The generated questions also need to pass a difficulty verification, and the verification is that the difficulty level number needs to be lower than the answering correct rate in the user state vector multiplied by a preset multiple.

[0014] According to another aspect of the present invention, a system for adaptive question generation based on a retrieval enhancement algorithm is provided. The system includes a data collection module, an optimization and continuous learning module, a retrieval enhancement module, and a question generation module; The data collection module collects the answering record data of the user, performs outlier filtering and data preprocessing, and obtains the user state vector and the feedback label and inputs them into the optimization and continuous learning module; The optimization and continuous learning module adjusts the question generation strategy according to the user state vector through the reinforcement learning unit, and transfers the learning experience of other users to the adjustment of the question generation strategy of the new user through the transfer learning unit; The retrieval enhancement algorithm module retrieves through the knowledge graph in the knowledge base using the retrieval enhancement algorithm based on the user status vector and feedback tags, calculates the similarity between the user status and the nodes in the knowledge graph, and selects the node with the highest similarity as the retrieval result; The test question generation module generates candidate test questions using a graph-based retrieval enhancement generation algorithm and a large language model based on the user status vector, test question generation strategy, and retrieval result, and pushes them to the user and stores them in the knowledge base.

[0015] Compared with the prior art, the present invention has the following beneficial effects: (1) Improve the accuracy of personalized question generation: By integrating reinforcement learning and transfer learning technologies, a dynamically adjustable personalized question generation mechanism is constructed. The reinforcement learning module takes the user's real-time answering data as the core input, and drives policy iteration optimization through a reward function to ensure that the question difficulty and knowledge point distribution are accurately matched with the user's current ability. The transfer learning module uses a pre-trained long short-term memory network to quickly inherit the learning experience of similar groups when new user data is insufficient, solving the cold start problem. This technical collaboration enables the system to more accurately capture the user's real-time learning status and dynamically generate personalized and adaptable questions.

[0016] (2) Achieve efficient and diverse question generation: The system significantly improves the question generation efficiency and diversity through the knowledge graph and retrieval enhancement algorithm, combined with the generation ability of the large language model. The knowledge graph is constructed based on the knowledge base and the user's wrong questions. The nodes cover knowledge points, questions, and reference materials, and the edge relationships support semantic depth retrieval. In the retrieval stage, a graph-based retrieval enhancement generation algorithm and a large language model are used to preferentially return questions highly relevant to the user's weak points, covering the learning needs at different cognitive levels.

[0017] (3) Support dynamic learning tracking and closed-loop optimization of the question generation strategy: The system can implement a closed-loop process of data collection, strategy update, question generation, and feedback verification to achieve continuous tracking and adaptive optimization of the user's learning progress. The data collection module synchronizes the user's answering behavior in real time, filters out outliers, and converts unstructured feedback into quantitative indicators. The optimization and continuous learning module dynamically adjusts the question generation strategy based on real-time data. In the retrieval enhancement algorithm module, the knowledge graph dynamically retrieves according to the user's current situation, and the subsequent retrieval pertinence can be improved through different edge attribute relationship types. In addition, the difficulty verification mechanism requires that the difficulty level of the generated questions does not exceed a preset multiple of the user's correct rate. The entire test question production process of the system forms a closed-loop optimization, which is conducive to generating high-quality test questions that are more in line with the user's personalized needs and improving the user experience. Description of the Drawings

[0018] Figure 1 It is a flowchart of an adaptive question generation method based on a retrieval enhancement algorithm; Figure 2 It is a structural diagram of an adaptive question generation system based on a retrieval enhancement algorithm. Specific implementation manners

[0019] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented on the premise of the technical solution of the present invention, and gives detailed implementation manners and specific operation processes, but the protection scope of the present invention is not limited to the following embodiments.

[0020] Embodiment 1 This embodiment is an adaptive question generation method based on a retrieval enhancement algorithm. The specific steps include: S1. The data acquisition module collects the user's answer record data, filters out outliers and preprocesses the data to obtain a user status vector and a feedback label, and inputs them into the optimization and continuous learning module; S2. The optimization and continuous learning module adjusts the question generation strategy according to the user status vector through the reinforcement learning unit, and transfers the learning experience of other users to the adjustment of the question generation strategy of new users through the transfer learning unit; S3. According to the user status vector and the feedback label, use the retrieval enhancement algorithm to retrieve through the knowledge graph in the knowledge base, calculate the similarity between the user status and the nodes in the knowledge graph, and select the node with the highest similarity as the retrieval result; S4. The question generation module uses the graph-based retrieval enhancement generation algorithm and the large language model to generate questions according to the user status vector, the question generation strategy and the retrieval result, and pushes them to the user and stores them in the knowledge base.

[0021] The answer record data includes the user ID, the answer, the answer correctness, the answering duration, the current learning progress mark, and the subjective feedback text. Extract feedback keywords from the subjective feedback text and convert them into structured feedback labels, including the feedback question difficulty and the corresponding feedback knowledge point name. Preprocess the answer record data to obtain the user's answer correct rate, the answer error type code, and the quantified learning progress. The answer error type code is sorted from difficult to easy and from large to small according to the expert judgment of the correction difficulty of the wrong answer. The quantified learning progress is the percentage of the current learning progress mark in the total learning task.

[0022] In the reinforcement learning unit of the optimization and continuous learning module, its state space is the user status vector, including the answer correct rate, the answer error type code, the answering duration, and the quantified learning progress; its action space includes adjusting the question difficulty weight and adjusting the knowledge point coverage range. Continuously adjust the question generation strategy based on the user's answer record data, and use the student's performance feedback to optimize the difficulty and type of questions.

[0023] In the reinforcement learning unit, the reward function is set according to the user state vector to drive the adjustment of the question generation strategy. The reward function has the following expression: , where , , and are reward weights; is the answering accuracy rate; is the error type code; is the total number of error types; is the answering duration; is the quantified learning progress; is the label of the current user state vector. The reward function is calculated based on data from multiple dimensions shown by the user during the answering process, used to measure the user's performance on specific questions, and provide a basis for subsequent personalized question generation strategies. By comprehensively analyzing the user's performance, the difficulty and type of questions are dynamically adjusted according to the learning state to improve the effect of personalized teaching.

[0024] The adjustment of the question generation strategy is carried out through the value function, and the expression is: , where is the current strategy; is the strategy parameter at the next moment; is the step size amplitude parameter used to control the adjustment of the question generation strategy; is the reward function; is the user state vector value function.

[0025] In S2, transfer learning predicts the current knowledge weaknesses of users based on their historical answering record data through a long short-term memory network, and feeds the knowledge weaknesses back to the reinforcement learning unit. Clustering is performed according to the subjects selected by the users. When users with insufficient historical answering record data enter, the cosine similarity of the user state vectors between the current user and each cluster is calculated based on the existing answering record data, and the most similar cluster is selected for transfer; the judgment basis for insufficient historical answering record data is that the number of operations of this user is lower than the first threshold. When the number of times of using transfer learning data accumulates to the first threshold, the transfer learning weight is reduced according to the preset step length, and it transitions to pure reinforcement learning. Transfer learning can transfer the learning experience of other users to new users, helping the system to adapt to the learning progress and weak links of new users faster. In this process, the incremental update mechanism plays a key role. It converts the users' answering record data into the basis for system updates, and adjusts the personalized learning paths of students through the updated data to ensure continuous optimization and adaptation to the changing needs of users during long-term operation, improving the user experience.

[0026] In S3, the nodes in the knowledge graph include the knowledge point names and the difficulty levels of the questions, and the edge attributes include the relationship type and the similarity score between the nodes. In the knowledge graph, the relationship type is established by comparing the similarity score between the nodes with the second threshold. The relationship types include belonging to knowledge points, associated wrong questions, easily confused knowledge points, prerequisite knowledge points, and extended knowledge points. The construction of the knowledge graph is based on textbooks, question banks, and reference materials in the knowledge base, and is obtained through natural language processing and relationship extraction.

[0027] Calculate the user similarity between the user state vector and the nodes, and expand the similarity of the nodes corresponding to the feedback labels by a preset ratio. Sort according to the obtained user similarity, and select a preset number of nodes with the maximum similarity to form a retrieval set as the retrieval result. Calculate the user similarity The expression of , where is the current user state vector, is the embedded representation of the nodes in the knowledge graph; is the set of nodes in. The higher the similarity, the more relevant the node is to the current learning state of the user, and questions related to these nodes are recommended preferentially.

[0028] The test questions generated in S4 include the question stem, answers, difficulty levels, and corresponding knowledge points. The generated test questions also need to undergo a difficulty verification, and the verified difficulty level number needs to be lower than the preset multiple multiplied by the user's answering correct rate in the user status vector. The generated test questions will, according to the user's personalized needs, ensure that each user receives an appropriate challenge in the knowledge points they have mastered and promote their improvement in weak areas. Through this test question generation method based on user data, feedback, and knowledge graphs, this embodiment can provide precise and personalized educational services, improve the learning effect of users, while reducing the burden of teachers in creating test questions and promoting the implementation of personalized teaching.

[0029] Embodiment 2 This embodiment provides a system for adaptive test question generation based on a retrieval enhancement algorithm. The system includes a data collection module, an optimization and continuous learning module, a retrieval enhancement module, and a test question generation module.

[0030] The data collection module collects the user's answering record data, filters out outliers, and performs data preprocessing to obtain the user status vector and feedback tags, and inputs them into the optimization and continuous learning module. These data are used to evaluate the student's mastery of the questions, common error types, and problem-solving speed, etc., so as to provide a basis for personalized test question generation. The collected data will be cleaned and preprocessed to ensure its consistency and accuracy, so as to provide high-quality data support for the subsequent test question generation module. All the collected data are uniformly stored in the learning database to support efficient retrieval and management, providing data support for the system and ensuring that the subsequent modules can generate personalized test questions through precise data analysis.

[0031] The optimization and continuous learning module includes a reinforcement learning unit and a transfer learning unit, which are responsible for continuously optimizing the question generation strategy by analyzing the user's answer record data, and improving the accuracy and adaptability of personalized question generation. Based on machine learning algorithms, this module can continuously learn during the system operation, gradually adapt to the personalized needs of different students, ensure the continuous optimization of the question generation process, and thus improve the educational effect. Through the reinforcement learning unit, the question generation strategy is adjusted according to the user state vector, and through the transfer learning unit, the learning experience of other users is transferred to the adjustment of the question generation strategy for new users, realizing the dynamic adjustment of the user's personalized learning state, thereby driving the optimization of subsequent question generation and ensuring the accuracy and adaptability of question generation. Reinforcement learning technology enables the system to automatically adjust the question difficulty and knowledge point coverage according to the user's performance, while transfer learning enables the system to quickly adapt to the learning progress and weak links of new users, reducing the dependence on a large amount of data. Through periodic training and evaluation, the system continuously optimizes the question generation strategy, avoiding the limitations of traditional static question generation systems and being able to always adapt to the personalized needs of each student. The incremental update mechanism provides the system with the ability of continuous learning based on real-time feedback, making the question generation process always in an optimized state, thereby improving the accuracy of personalized teaching and the educational effect. Through the efficient retrieval of the retrieval enhancement algorithm module and the dynamic combination with the optimization and continuous learning module, it provides the question content support that fits the user's personalized learning needs.

[0032] The retrieval enhancement algorithm module uses the retrieval enhancement algorithm to retrieve through the knowledge graph in the knowledge base according to the user state vector and feedback tags, calculates the similarity between the user state and the nodes in the knowledge graph, and selects the node with the highest similarity as the retrieval result. The retrieval enhancement algorithm module deeply correlates relevant knowledge points through the relationships of the knowledge graph, thereby improving the diversity and accuracy of the retrieval results. According to the user's learning situation and practice needs, the retrieval enhancement module quickly retrieves the most relevant questions or learning resources from the knowledge base. These retrieval results are not just simple questions or resources, but related text fragments, questions, knowledge point descriptions, etc. enhanced by the graph, and this information can help the system accurately understand the user's learning progress and weak links. The retrieval process of the retrieval enhancement algorithm module is dynamic, and it adjusts the retrieval strategy in real time according to the user's learning behavior and feedback. For example, the system will timely identify the user's weak links in specific fields or knowledge points according to the user's answer correct rate and error types, and select relevant content from the knowledge base for feedback. By combining the user's performance feedback, the system continuously adjusts and optimizes the retrieval strategy to ensure that the content retrieved each time can help the user progress to the greatest extent.

[0033] The question generation module generates candidate questions using a graph-based retrieval augmented generation algorithm and a large language model based on the user status vector, question generation strategy, and retrieval results, and pushes them to the user and stores them in the knowledge base.

[0034] The system performance of this embodiment was comprehensively evaluated through the feedback and testing of actual users. The experimental results are shown in Table 1. According to the subjective evaluations of power industry experts and learners, the system in this embodiment performs excellently in several key aspects. First, regarding the question quality, the average score of experts is 4.7, the average score of learners is 4.5, and the overall average score is 4.6, indicating that the questions generated by the system are widely recognized in terms of quality and can effectively meet the needs of different users. Second, in terms of difficulty alignment, the average score of experts is 4.6, that of learners is 4.3, and the overall score is 4.45, showing that the difficulty of the questions generated by the system is highly aligned with the actual level of users, avoiding overly simple or complex questions, thus enhancing the learning experience of users. In addition, the acceptance of the system has been highly recognized by experts and learners. The average score of experts is 4.8, the score of learners is 4.6, and the overall score is 4.7, reflecting the wide recognition and high usage satisfaction of the system among the user group.

[0035] Table 1 Subjective evaluations of users of the adaptive question generation system The differences in the scores of experts and learners in each item are not significant, indicating that the system in this embodiment can better meet the needs of different user groups in terms of question quality, difficulty adjustment, and acceptance, and has received unanimous praise from users. The system in this embodiment can generate high-quality questions automatically and is precise and effective in question design, capable of providing high-quality content that meets user expectations. In addition, the system in this embodiment performs excellently in intelligent difficulty adjustment, capable of automatically adjusting the difficulty of questions according to the learning progress of different users to promote more effective learning, making the system not only have wide applicability but also be highly accepted among different groups, enhancing the pertinence and efficiency of learning. At the same time, the automatic generation of questions reduces the cost of manual question making and improves the efficiency of training and learning.

[0036] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

Claims

1. An adaptive question setting method based on a retrieval enhancement algorithm, characterized in that: The specific steps include: S1. The data collection module collects the user's answer record data, performs outlier filtering and data preprocessing, obtains the user state vector and feedback label and inputs them into the optimization and continuous learning module; S2, the optimization and continuous learning module adjusts the test question generation strategy according to the user state vector through the reinforcement learning unit, and transfers the learning experience of other users to the adjustment of the test question generation strategy for the new user through the transfer learning unit; S3. Based on the user state vector and feedback label, a search enhancement algorithm is used to search the knowledge base through the knowledge graph, calculate the similarity between the user state and the nodes in the knowledge graph, and select the node with the highest similarity as the search result; S4. The test question generation module generates test questions according to the user state vector, test question generation strategy and retrieval results using a graph-based retrieval enhancement generation algorithm and a large language model, pushes them to the user and stores them in the knowledge base.

2. The method for self-adapting questions based on a search enhancement algorithm according to claim 1, characterized in that: The answer record data in S1 includes user ID, answer, answer correctness, answer time, current learning progress mark and subjective feedback text; feedback keywords are extracted from the subjective feedback text and converted into structured feedback tags, and the feedback tags include the difficulty of the feedback test question and the corresponding feedback knowledge point name; the answer record data is preprocessed to obtain the user's answer accuracy, answer error type code and quantified learning progress.

3. The adaptive question setting method based on retrieval enhancement algorithm according to claim 1 is characterized in that: The state space of the reinforcement learning unit in S2 is a user state vector, including the correctness of answering questions, the coding of the wrong answer type, the duration of answering questions, and the quantified learning progress; The action space of the reinforcement learning unit includes adjusting the difficulty weight of test questions and adjusting the coverage of knowledge points.

4. The method for self-adapting questions based on a search enhancement algorithm according to claim 3, characterized in that: The reinforcement learning unit sets a reward function according to the user state vector to drive the adjustment of the test question generation strategy. The expression is: ， in, , , and is the reward weight; is the correct answer rate; Encode the error type; is the total number of error types; The duration of answering questions; To quantify learning progress; is the label of the current user state vector; The adjustment of the test question generation strategy is performed through the value function, and the expression is: ， in, For the current strategy; is the strategy parameter for the next moment; The step size parameter used to control the adjustment of the test generation strategy; is the reward function; is the user state vector The value function of .

5. The method for self-adapting questions based on retrieval enhancement algorithm according to claim 1, characterized in that: The transfer learning in S2 predicts the user's current knowledge weaknesses based on the user's historical answer record data through a long short-term memory network, and feeds back to the reinforcement learning unit based on the knowledge weaknesses.

6. The method for self-adapting questions based on retrieval enhancement algorithm according to claim 5, characterized in that: Clustering is performed according to the subject selected by the user. When a user with insufficient historical answer record data enters, the cosine similarity of the user state vector between the current user and each cluster is calculated based on the existing answer record data, and the most similar cluster is selected for migration. The judgment basis for insufficient historical answer record data is that the number of operations of the user is lower than a first threshold. When the number of times the transfer learning data is used accumulates to the first threshold, the transfer learning weight is reduced according to the preset step size, and transition is made to pure reinforcement learning.

7. The method for self-adapting questions based on a search enhancement algorithm according to claim 1, characterized in that: In S3, the nodes in the knowledge graph include knowledge point names and test question difficulties, and the edge attributes include relationship types and similarity scores between nodes. The relationship types in the knowledge graph are established by comparing the similarity scores between nodes with a second threshold. The relationship types include knowledge points, related wrong questions, easily confused knowledge points, prerequisite knowledge points, and extended knowledge points.

8. The method for self-adapting questions based on retrieval enhancement algorithm according to claim 7, characterized in that: Calculate the user similarity between the user state vector and the node, and increase the similarity of the node corresponding to the feedback label according to a preset ratio, sort according to the obtained user similarity, select a preset number of nodes with the maximum similarity to form a search set as the search result, and calculate the user similarity The expression is: ， in, is the current user state vector, It is the embedded representation of nodes in the knowledge graph; For a node collection The elements in .

9. The method for self-adapting questions based on a search enhancement algorithm according to claim 1, characterized in that: The test questions generated in S4 include question surface, answers, difficulty levels and corresponding knowledge points. The generated test questions also need to undergo difficulty verification, and the verification is that the difficulty level must be lower than the correct answer rate in the user state vector multiplied by a preset multiple.

10. A system for the adaptive question setting method based on retrieval enhancement algorithm according to any one of claims 1 to 9, characterized in that: The system includes a data acquisition module, an optimization and continuous learning module, a retrieval enhancement module and a test question generation module; The data collection module collects the user's answer record data, performs outlier filtering and data preprocessing, obtains the user state vector and feedback label and inputs them into the optimization and continuous learning module; The optimization and continuous learning module adjusts the test question generation strategy according to the user state vector through the reinforcement learning unit, and transfers the learning experience of other users to the adjustment of the test question generation strategy of the new user through the transfer learning unit; The retrieval enhancement algorithm module uses a retrieval enhancement algorithm to search the knowledge base through the knowledge graph according to the user state vector and the feedback label, calculates the similarity between the user state and the nodes in the knowledge graph, and selects the node with the highest similarity as the retrieval result; The test question generation module generates candidate test questions based on the user state vector, test question generation strategy and retrieval results using a graph-based retrieval enhancement generation algorithm and a large language model, pushes them to the user and stores them in the knowledge base.

Images