A personalized test question recommendation method and system based on a question bank

Abstract

The present invention discloses a personalized test question recommendation method and system based on a question bank, relating to the technical field of test question recommendation. A personalized test question recommendation system based on a question bank includes: a user's test question recommendation ability analysis module, a test question data analysis module, a user's test question recommendation emotion analysis module, and a user test question recommendation prediction module. By obtaining the answering data and behavior data of a target user and combining with ability analysis and emotion analysis models, the present invention can achieve accurate personalized recommendation for users, and can recommend the most suitable test questions according to the ability growth and emotion fluctuations of users, thereby improving learning efficiency; by converting test question data into analysis test question vectors and using a personalized test question analysis model to analyze them, the mastery of users in each knowledge point can be comprehensively evaluated, not only paying attention to the answering correctness rate of users, but also considering the specific performance of users during the answering process, thereby providing a more comprehensive ability evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of question recommendation, and particularly to a personalized question recommendation method and system based on a question bank. Background Art

[0002] Question recommendation usually analyzes students' learning behaviors, historical performances, and knowledge point mastery to recommend questions suitable for their individual learning needs and ability levels. This process requires precise educational measurement of students' cognitive levels. Traditional educational measurement methods mainly reflect students' mastery of knowledge points through exam scores, but this method has limitations. For example, even students with the same exam scores may have different degrees of mastery of knowledge points. Only relying on exam scores cannot accurately reflect students' true ability levels or distinguish differences in knowledge point mastery among different students. In addition, if a student has a weak grasp of a certain knowledge point, it may affect their understanding and construction of the entire knowledge system. Whether a student can make up for learning deficiencies and improve their grades depends to a large extent on whether the subsequent practice questions can effectively help them consolidate and improve. In this process, personalized question recommendation plays a crucial role. Summary of the Invention

[0003] The present invention aims to provide a personalized question recommendation method and system based on a question bank to recommend questions that better suit the current learning stage for users.

[0004] A personalized question recommendation method based on a question bank includes the following steps:

[0005] Step S1: Obtain the stage answering data of the target user; the stage answering data of the target user includes N pieces of answered question data T n and the answering option data P n of the target user, where n = 1, 2,..., N; N is the total number of questions answered by the target user in the current stage; based on the answered question data T n of the target user, the answering option data P n of the target user, and the user question recommendation ability analysis model, obtain the target user ability growth factor Z n ; the user question recommendation ability analysis model includes a score judgment layer, an ability increment calculation layer, and an ability factor output layer, and is used to analyze the ability growth of the target user according to the specific characteristic performances of the answered questions;

[0006] The specific steps for obtaining the answered question data T n of the target user are as follows:

[0007] For any question, obtain the question data, and convert the question data into an analysis question vector X, X = [X 1 ,X2 , …, X i , …, X I , X i represents the specific information of the i-th test question feature in the analysis test question vector X, where I is the total number of test question features in the test question data; the analysis test question vector is input into the personalized test question analysis model for analysis to obtain the test question analysis ability vector Y, Y = [Y 1 , Y 2 , …, Y i , …, Y I , Y i is the test question ability analysis data of the i-th test question feature corresponding to X i ; the analysis test question vector X corresponding to the test questions already answered by the target user and the test question analysis ability vector Y are used as the test question data T already answered by the target user n ; the personalized test question analysis model includes a feature recognition layer, I feature analysis layers C i and a feature result output layer, which are used to perform specific and accurate feature analysis on the test questions;

[0008] Step S2: Obtain the stage answering behavior data of the target user. The stage answering behavior data of the target user includes the answering stay duration S n of the target user and the answering interaction data H n of the target user; based on the stage answering behavior data of the target user and the user recommended test question emotion analysis model, obtain the target user emotion fluctuation factor E n ; the user recommended test question emotion analysis model includes a duration analysis layer, an interaction data analysis layer, and an emotion fluctuation factor output layer, which are used to numerically analyze the emotion of the user during test question answering using the emotion fluctuation factor function, and use the improved optimization algorithm to determine the emotion fluctuation factor function;

[0009] Step S3: Analyze according to the target user ability growth factor Z n , the target user emotion fluctuation factor E n and the user test question recommendation prediction model to obtain the target user test question recommendation prediction test question set; recommend corresponding test questions for the target user in the question bank in the next stage based on the target user test question recommendation prediction test question set; the user test question recommendation prediction model includes an ability increment matching layer, a comprehensive ability analysis layer, and a test question recommendation layer, which are used to perform comprehensive ability analysis on the target user and match personalized test questions with corresponding abilities.

[0010] As a preferred technical solution of the present invention, the personalized test question analysis model in step S1 includes a feature recognition layer, I feature analysis layers C i and a feature result output layer;

[0011] The feature recognition layer is used to process all X in the analysis test question vector X iPerform feature recognition to obtain feature label B i ; According to feature label B i Send X i to the corresponding feature analysis layer C i ;

[0012] Feature analysis layer C i is used to perform feature analysis on X i to obtain Y i ;

[0013] The feature result output layer is used to combine all Y i to obtain the test question analysis ability vector Y, Y = [Y 1 , Y 2 , …, Y i , …, Y I ;

[0014] The specific steps for training the feature analysis layer C i include:

[0015] According to the set feature label B i Collect several groups of test question feature training samples corresponding to the test question features; each group of test question feature training samples contains specific information corresponding to a group of test question features and test question ability analysis data; combine the several groups of test question feature training samples to obtain a test question feature training set;

[0016] According to the test question feature training set, perform model training on the feature analysis layer C i with the test question ability analysis data as the target to obtain the initial feature analysis layer C i '; Perform model evaluation on the initial feature analysis layer C i ' to obtain the model evaluation result of the initial feature analysis layer C i '; If the model evaluation result of the initial feature analysis layer C i ' is passed, then use the initial feature analysis layer C i ' as the feature analysis layer C i , and deploy it to the personalized test question analysis model; otherwise, continue with model training;

[0017] Traverse and train all feature analysis layers C i until the model training is completed.

[0018] As a preferred technical solution of the present invention, the user recommended test question ability analysis model in step S1 includes a score judgment layer, an ability increment calculation layer, and an ability factor output layer;

[0019] The score judgment layer is used to determine according to the target user's answer option data P n and the target user's answered test question data T nOptimize the correlation calculation for the analysis test question vector X in it to obtain the ability growth parameter vector α, α = [α 1 , α 2 , …, α i , …, α I ;

[0020] The ability increment calculation layer is used to calculate the target user ability growth factor Z by using the formula Z n = αY; n Y is determined by the test question analysis ability vector Y in the test question data T n answered by the target user;

[0021] The ability factor output layer is used to output the target user ability growth factor Z n .

[0022] As a preferred technical solution of the present invention, the specific steps for optimizing the correlation calculation include:

[0023] For any X i perform the optimized correlation calculation:

[0024] Extract features from the target user's answer option data P n to obtain the target user's answer option data feature P n ';

[0025] According to the target user's answer option data feature P n ' and X i perform correlation calculation to obtain the target user's answer option data correlation Q i ;

[0026] Use the formula to calculate α i ; MM min represents the minimum value among all Q i , MM max represents the maximum value among all Q i ; β represents the adjustment parameter;

[0027] Traverse all X i to obtain the ability growth parameter vector α, α = [α 1 , α 2 , …, α i , …, α I .

[0028] As a preferred technical solution of the present invention, the user recommended test question emotion analysis model in step S2 includes a duration analysis layer, an interaction data analysis layer, and an emotion fluctuation factor output layer;

[0029] The duration analysis layer is used to, according to the answering stay duration S of the target usern Calculate with the set threshold time to obtain the target user duration emotion parameter U n ;

[0030] The interaction data analysis layer is used to analyze based on the target user's answer interaction data H n to obtain the target user emotion prediction label V n ; According to the target user emotion prediction label V n match in the emotion parameter library to obtain the target user emotion prediction label factor V n ';

[0031] The emotion fluctuation factor output layer is used to perform emotion fluctuation factor function calculation based on the target user duration emotion parameter U n and the target user emotion prediction label factor V n ' to obtain the target user emotion fluctuation factor E n ; The emotion fluctuation factor function is determined by prior data and an optimization algorithm;

[0032] The specific steps for training the interaction data analysis layer include:

[0033] Collect several groups of emotion label training samples; each group of emotion label training samples contains user answer interaction data and annotated emotion labels; combine several groups of emotion label training samples to obtain an emotion label training set;

[0034] Train the interaction data analysis layer with the emotion label training set aiming at the annotated emotion labels to obtain an initial interaction data analysis layer; perform model evaluation on the initial interaction data analysis layer to obtain the initial interaction data analysis layer model evaluation result; if the initial interaction data analysis layer model evaluation result is passed, then use the initial interaction data analysis layer as the interaction data analysis layer; otherwise, continue with model training.

[0035] As a preferred technical solution of the present invention, the specific steps for determining the emotion fluctuation factor function include:

[0036] Collect several groups of emotion fluctuation verification samples; in each group of emotion fluctuation verification samples, set the independent variables as the user duration emotion parameter and the user emotion prediction label factor, and the dependent variable as the user emotion fluctuation factor; all emotion fluctuation verification samples meet the subsequent analysis; combine several groups of emotion fluctuation verification samples to obtain an emotion fluctuation verification set;

[0037] Construct K function optimization individuals G k , k = 1, 2,..., K; each function optimization individual G k contains a set of solutions for constructing the emotion fluctuation factor function; the K function optimization individuals G kCombine to obtain the function optimization iteration population; set the number of iterations j, where j = 1, 2, …, J; set the iteration balance coefficient R t , R t =D*((J - j) / J) 3 , where D is the iteration balance weight;

[0038] When performing iteration, for the function optimization individual G in the function optimization iteration population k perform simulation calculations to obtain the function optimization fitness W k ; determine whether the iteration balance coefficient R t at this time is less than the preset stage update threshold. If the iteration balance coefficient R t is greater than the preset stage update threshold, then perform Gaussian perturbation mutation on the function optimization iteration population to obtain a new function optimization iteration population and perform the next iteration; if the iteration balance coefficient R t is less than the preset stage update threshold, then perform Cauchy perturbation mutation on the function optimization iteration population to obtain a new function optimization iteration population and perform the next iteration;

[0039] The specific steps of the simulation calculation include:

[0040] Calculate the independent variables in the emotion fluctuation verification set according to the function optimization individual G k to obtain the simulated emotion fluctuation factor; calculate the Euclidean distance between the simulated emotion fluctuation factor and the user emotion fluctuation factor to obtain the simulated Euclidean distance; take the reciprocal of the simulated Euclidean distance as the function optimization fitness W k of the function optimization individual G k ;

[0041] When the number of iterations j reaches the maximum value, output the function optimization individual G k corresponding to the maximum function optimization fitness W k , which is the optimal function optimization individual; take the solution corresponding to the constructed emotion fluctuation factor function in the optimal function optimization individual as the emotion fluctuation factor function.

[0042] As a preferred technical solution of the present invention, the user test question recommendation prediction model in step S3 includes an ability increment matching layer, a comprehensive ability analysis layer, and a test question recommendation layer;

[0043] The ability increment matching layer is used to calculate according to the target user ability growth factor Z n and the target user emotion fluctuation factor E n to obtain the target user ability increment Z n ';

[0044] The comprehensive ability analysis layer is used to calculate according to all the target user ability increments Z nPerform feature fusion to obtain the incremental ability of the target user at the current stage;

[0045] The test question recommendation layer is used to recommend test questions based on the incremental ability of the target user at the current stage, and obtain a pretest question set of test question recommendations for the target user.

[0046] A personalized test question recommendation system based on a question bank, including:

[0047] The user test question recommendation ability analysis module, which includes a user test question acquisition unit and a user test question analysis unit;

[0048] The user test question acquisition unit is used to obtain the answering data of the target user at the current stage; the answering data of the target user at the current stage includes N pieces of answered test question data T n and the answering option data P of the target user n , n = 1, 2,..., N; N is the total number of test questions answered by the target user in the current stage;

[0049] The user test question analysis unit is used to obtain the target user ability growth factor Z based on the answered test question data T n , the answering option data P of the target user n and the user test question recommendation ability analysis model; the user test question recommendation ability analysis model includes a score judgment layer, an ability increment calculation layer, and an ability factor output layer, and is used to analyze the ability growth of the target user according to the specific feature performance of the answered test questions; n ;

[0050] The test question data analysis module, which includes a test question feature acquisition unit and a test question feature analysis unit;

[0051] The test question feature acquisition unit is used to obtain test question data for any test question, and convert the test question data into an analysis test question vector X, X = [X 1 , X 2 , …, X i , …, X I , X i represents the specific information of the i-th test question feature in the analysis test question vector X, and I is the total number of test question features in the test question data;

[0052] The test question feature analysis unit is used to input the analysis test question vector into the personalized test question analysis model for analysis, and obtain a test question analysis ability vector Y, Y = [Y 1 , Y 2 , …, Y i , …, Y I , Y i is X iThe test item ability analysis data corresponding to the i-th test item; the analysis test vector X and the test item analysis ability vector Y corresponding to the test questions answered by the target user are used as the test question data T answered by the target user n ; The personalized test item analysis model includes a feature recognition layer and I feature analysis layers C i and a feature result output layer for performing specific and accurate feature analysis on test items;

[0053] The user recommended test question emotion analysis module, which includes a user emotion acquisition unit and a user emotion analysis unit;

[0054] The user emotion acquisition unit is used to obtain the stage answering behavior data of the target user. The stage answering behavior data of the target user includes the answering stay duration S of the target user n and the answering interaction data H of the target user n ;

[0055] The user emotion analysis unit is used to obtain the target user emotion fluctuation factor E based on the stage answering behavior data of the target user and the user recommended test question emotion analysis model; n The user recommended test question emotion analysis model includes a duration analysis layer, an interaction data analysis layer, and an emotion fluctuation factor output layer, which are used to numerically analyze the emotion of the user when answering test questions using the emotion fluctuation factor function, and use the improved optimization algorithm to determine the emotion fluctuation factor function;

[0056] The user test question recommendation prediction module, which includes a test question recommendation analysis unit;

[0057] The test question recommendation analysis unit is used to analyze according to the target user ability growth factor Z n 、the target user emotion fluctuation factor E n and the user test question recommendation prediction model to obtain the target user test question recommendation prediction test question set; based on the target user test question recommendation prediction test question set, corresponding test questions are recommended for the target user in the question bank in the next stage; the user test question recommendation prediction model includes an ability increment matching layer, a comprehensive ability analysis layer, and a test question recommendation layer, which are used to perform comprehensive ability analysis on the target user and match personalized test questions with corresponding abilities.

[0058] The present invention has the following advantages:

[0059] 1. The present invention can achieve precise personalized recommendation for users by obtaining the answering data and behavioral data of target users and combining the ability analysis and emotion analysis models. It can recommend the most suitable test questions according to the ability growth and emotion fluctuations of users, thereby improving learning efficiency. By converting the test question data into analysis test question vectors and using a personalized test question analysis model to analyze them, it can comprehensively evaluate the user's mastery of each knowledge point, not only paying attention to the answering accuracy rate of the user, but also considering the specific performance of the user during the answering process, thus providing a more comprehensive ability assessment.

[0060] 2. The present invention can effectively identify the emotion fluctuations of users during the answering process by monitoring the answering stay duration and interaction data of users and combining the emotion analysis model, which helps to timely detect the learning fatigue or anxiety state of users. Thus, according to the real-time emotion to judge the ability increment, and according to the ability growth factor and emotion fluctuation factor of the target user, it can dynamically adjust the recommended test questions, making the recommended test questions more in line with the current state of the user, neither too simple nor too difficult, thereby maintaining the learning motivation and interest of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a structural schematic diagram of a personalized test question recommendation system based on a question bank adopted in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] In order to enable those skilled in the art of the present technology to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention.

[0063] Embodiment 1, a personalized test question recommendation method based on a question bank, includes the following steps:

[0064] Step S1: Obtain the answering data in the target stage; the answering data of the target user in the target stage includes N pieces of answered test question data T n and the answering option data P n of the target user, where n = 1, 2,..., N; N is the total number of test questions answered by the target user in the current stage; based on the answered test question data T n of the target user, the answering option data P n of the target user, and the user recommended test question ability analysis model, obtain the ability growth factor Z n of the target user; the user recommended test question ability analysis model includes a score judgment layer, an ability increment calculation layer, and an ability factor output layer, and is used to analyze the ability growth of the target user according to the specific characteristic performance of the answered test questions.

[0065] The specific steps to obtain the answered test question data T n of the target user:

[0066] For any test question, obtain the test question data, and convert the test question data into an analysis test question vector X, X = [X 1 , X 2 , …, X i , …, X I , where X i represents the specific information of the i-th test question feature in the analysis test question vector X, and I is the total number of test question features in the test question data; input the analysis test question vector into the personalized test question analysis model for analysis to obtain the test question analysis ability vector Y, Y = [Y 1 , Y 2 , …, Y i , …, Y I , where Y i is the test question ability analysis data of the i-th test question feature corresponding to X i ; use the analysis test question vector X and the test question analysis ability vector Y corresponding to the test questions already answered by the target user as the test question data T n already answered by the target user; the personalized test question analysis model includes a feature recognition layer, I feature analysis layers C i and a feature result output layer, which are used to perform specific and accurate feature analysis on the test questions;

[0067] The number and specific content of the test question features are set by professional and technical personnel according to the actual situation; for example, for test question ①, the stem contains knowledge points I, II, and III; the relationships between each option O1, O2, O3, and O4 and the knowledge points are as follows: O1: correct option, involving knowledge points I, II, and III; O2: wrong option, involving knowledge points II and III; O3: wrong option, involving knowledge points I and III; O4: wrong option, involving knowledge point III; analyze test question ①, and the specific information is information such as the stem, options, and knowledge points. Perform feature analysis on these specific information to obtain the test question analysis ability vector, which includes the knowledge points and ability bases after feature analysis;

[0068] The personalized test question analysis model in step S1 includes a feature recognition layer, I feature analysis layers C i and a feature result output layer;

[0069] The feature recognition layer is used to perform feature recognition on all X i in the analysis test question vector X to obtain the feature label B i ; according to the feature label B i , send X i to the corresponding feature analysis layer C i ;

[0070] The feature analysis layer C i is used to perform analysis on X iPerform feature analysis to obtain Y i ;

[0071] The feature result output layer is used to combine all Y i to obtain the test question analysis ability vector Y, Y = [Y 1 , Y 2 , …, Y i , …, Y I ;

[0072] The specific steps for training the feature analysis layer C i include:

[0073] Collect several groups of test question feature training samples corresponding to the set feature label B i ; Each group of test question feature training samples contains a set of specific information corresponding to the test question feature and test question ability analysis data; Combine several groups of test question feature training samples to obtain the test question feature training set;

[0074] Perform model training on the feature analysis layer C i using the test question ability analysis data as the target to obtain the initial feature analysis layer C i '; Evaluate the initial feature analysis layer C i ' to obtain the model evaluation result of the initial feature analysis layer C i '; If the model evaluation result of the initial feature analysis layer C i ' is passed, then use the initial feature analysis layer C i ' as the feature analysis layer C i , and deploy it to the personalized test question analysis model; otherwise, continue model training;

[0075] Traverse and train all feature analysis layers C i until the model training is completed;

[0076] By converting the test question data into an analysis test question vector and using the feature recognition layer for feature recognition, various features of the test questions can be accurately analyzed. This method ensures a comprehensive understanding of the test questions, thereby improving the accuracy and effectiveness of test question analysis. The feature analysis layer conducts specialized analysis for each feature to ensure that each feature can be fully processed. This method improves the efficiency of feature analysis, enabling the system to quickly analyze a large number of test questions. Through the feature recognition layer and the feature analysis layer, personalized ability assessment can be carried out according to the specific features of each test question. This method enables the test question analysis ability vector to reflect the true difficulty and knowledge point coverage of the test questions, thus providing a reliable basis for subsequent analysis of user ability growth. Through accurate test question analysis, the most suitable test questions for each student can be recommended, thereby realizing a personalized learning path. This method helps to stimulate students' learning interest and improve learning efficiency;

[0077] The user recommended test question ability analysis model in step S1 includes a score judgment layer, an ability increment calculation layer, and an ability factor output layer;

[0078] The score judgment layer is used to perform optimized correlation calculation based on the target user's answer option data P n and the analyzed test question vector X in the target user's answered test question data T n to obtain the ability growth parameter vector α, α = [α 1 ,α 2 ,…,α i ,…,α I ;

[0079] The ability increment calculation layer is used to calculate the target user's ability growth factor Z n using the formula Z n = αY; Y is determined by the test question analysis ability vector Y in the target user's answered test question data T n ;

[0080] The ability factor output layer is used to output the target user's ability growth factor Z n ;

[0081] The specific steps for performing optimized correlation calculation include:

[0082] For any X i perform optimized correlation calculation:

[0083] Extract features from the target user's answer option data P n to obtain the target user's answer option data feature P n ';

[0084] According to the target user's answer option data feature P n ' and Xi Correlation calculation is performed to obtain the relevance Q of the target user's answer option data i ;

[0085] Using the formula α is calculated i ; MM min represents the minimum value among all Q i , MM max represents the maximum value among all Q i ; β represents the adjustment parameter; the specific value of the adjustment parameter is set by professionals according to the actual situation;

[0086] All X are traversed i to obtain the ability growth parameter vector α, α = [α 1 , α 2 , …, α i , …, α I ;

[0087] By optimizing the correlation calculation, the system can accurately evaluate the ability growth of the target user in each question characteristic. This method ensures the accuracy and reliability of the ability evaluation and provides a solid foundation for subsequent personalized recommendations; by adjusting the parameter β, the ability growth parameter vector α can be adjusted according to the actual situation, which can adapt to the different needs of different users and improve the flexibility and adaptability of the recommendation; by extracting the characteristics of the target user's answer option data and calculating its relevance Q i with the question characteristics, the performance of the user in different characteristics can be objectively evaluated. This method reduces the bias caused by subjective judgment and improves the objectivity of the evaluation; by continuously calculating the ability growth factor Z n on each question characteristic, the ability growth of the user can be continuously evaluated. This method helps to timely discover problems and take corresponding intervention measures to improve the learning effect;

[0088] Step S2: Obtain the target user's stage answering behavior data, which includes the target user's answering stay duration S n and the target user's answering interaction data H n ; Based on the target user's stage answering behavior data and the user recommended question emotion analysis model, the target user's emotion fluctuation factor E n is obtained; the user recommended question emotion analysis model includes a duration analysis layer, an interaction data analysis layer, and an emotion fluctuation factor output layer, which are used to numerically represent the emotion of the user when answering questions using the emotion fluctuation factor function and determine the emotion fluctuation factor function using the improved optimization algorithm;

[0089] The user recommendation test question emotion analysis model in step S2 includes a duration analysis layer, an interaction data analysis layer, and an emotion fluctuation factor output layer;

[0090] The duration analysis layer is used to calculate based on the target user's answer question staying duration S n and the set threshold time to obtain the target user's duration emotion parameter U n ; The set threshold time is set by the big data average duration;

[0091] The interaction data analysis layer is used to analyze based on the target user's answer question interaction data H n to obtain the target user's emotion prediction label V n ; According to the target user's emotion prediction label V n match in the emotion parameter library to obtain the target user's emotion prediction label factor V n '; The emotion parameter library is set based on prior knowledge and contains several standard emotion labels and corresponding influence factors;

[0092] The emotion fluctuation factor output layer is used to perform emotion fluctuation factor function calculation based on the target user's duration emotion parameter U n and the target user's emotion prediction label factor V n ' to obtain the target user's emotion fluctuation factor E n ; The emotion fluctuation factor function is determined by prior data and an optimization algorithm;

[0093] The specific steps for training the interaction data analysis layer include:

[0094] Collect several groups of emotion label training samples; Each group of emotion label training samples includes user answer question interaction data and labeled emotion labels; Combine several groups of emotion label training samples to obtain an emotion label training set;

[0095] Train the interaction data analysis layer with the labeled emotion labels as the goal according to the emotion label training set to obtain an initial interaction data analysis layer; Perform model evaluation on the initial interaction data analysis layer to obtain the initial interaction data analysis layer model evaluation result; If the initial interaction data analysis layer model evaluation result is passed, use the initial interaction data analysis layer as the interaction data analysis layer; Otherwise, continue with model training;

[0096] By analyzing the answering stay duration and answering interaction data of the target users, the emotional fluctuations of the users can be accurately monitored. This method ensures the real-time monitoring of the users' emotional states, helps to timely discover and solve the emotional problems of the users during the learning process; through the comprehensive evaluation of the duration analysis layer and the interaction data analysis layer, the emotional states of the users can be comprehensively analyzed from multiple dimensions. This method improves the comprehensiveness and accuracy of the emotional evaluation; by analyzing the users' answering interaction data and combining with the matching of emotional tags, the emotional states of the users can be accurately predicted. This method improves the accuracy of the emotional prediction and helps to better understand the behavioral motivations of the users; through the calculation of the emotional fluctuation factor function, the emotional fluctuations of the users can be numerically quantified, thus facilitating subsequent analysis and application. This method makes the evaluation of the emotional fluctuations more objective and quantitative;

[0097] The specific steps for determining the emotional fluctuation factor function include:

[0098] Collect several groups of emotional fluctuation verification samples; in each group of emotional fluctuation verification samples, set the independent variables as the user duration emotional parameter and the user emotional prediction label factor, and the dependent variable as the user emotional fluctuation factor; all emotional fluctuation verification samples meet the subsequent analysis; combine several groups of emotional fluctuation verification samples to obtain the emotional fluctuation verification set;

[0099] Construct K function optimization individuals G k , k = 1, 2,..., K; each function optimization individual G k contains a set of solutions for constructing the emotional fluctuation factor function; combine the K function optimization individuals G k to obtain the function optimization iteration population; set the number of iterations j, j = 1, 2,..., J; set the iteration balance coefficient R t , R t = D * ((J - j) / J) 3 , where D is the iteration balance weight;

[0100] The iteration balance coefficient changes rapidly in the early stage of the iteration, which can improve the global search ability of the optimal individual and prevent falling into the local optimum; in the later stage of the iteration, the iteration balance coefficient changes slowly, which is conducive to the function optimization individual to explore the optimal solution and improve the local search ability and search accuracy of the algorithm;

[0101] During the iteration, perform simulation calculations on the function optimization individual G k in the function optimization iteration population to obtain the function optimization fitness W k ; judge whether the iteration balance coefficient R t is less than the preset stage update threshold. If the iteration balance coefficient R tIf it is greater than the preset stage update threshold, perform Gaussian perturbation mutation on the function optimization iteration population to obtain a new function optimization iteration population and proceed to the next iteration; if the iteration balance coefficient R t is less than the preset stage update threshold, perform Cauchy perturbation mutation on the function optimization iteration population to obtain a new function optimization iteration population and proceed to the next iteration; the preset stage update threshold is set by professional technicians according to the actual situation;

[0102] The optimization algorithm conducts a large - scale search in the early iteration stage, gradually narrowing the target position range, and conducts a small - scale search in the later iteration stage to find the exact position of the optimal individual; as the population iterates, some inferior solutions will appear and cannot be eliminated, easily leading the algorithm to fall into a local optimum. Therefore, two different mutation mechanisms are introduced to help the iteration population jump out of the local optimum;

[0103] The specific steps for simulation calculation include:

[0104] Calculate the independent variables in the emotion fluctuation verification set according to the function optimization individual G k to obtain the simulated emotion fluctuation factor; calculate the Euclidean distance between the simulated emotion fluctuation factor and the user emotion fluctuation factor to obtain the simulated Euclidean distance; take the reciprocal of the simulated Euclidean distance as the function optimization fitness W k of the function optimization individual G k ;

[0105] When the iteration number j reaches the maximum value, output the function optimization individual G k corresponding to the maximum function optimization fitness W k , which is the optimal function optimization individual; take the solution corresponding to the constructed emotion fluctuation factor function in the optimal function optimization individual as the emotion fluctuation factor function;

[0106] By collecting emotional fluctuation verification samples and performing iterative calculations of the optimization algorithm, the system can determine the most suitable function to describe the user's emotional fluctuation factor, improving the accuracy of the emotional fluctuation factor function and making the assessment of emotional fluctuations more accurate. By setting an iterative balance coefficient and using Gaussian perturbation mutation in the early stage of iteration and Cauchy perturbation mutation in the later stage, local search can be gradually carried out on the basis of global search to avoid falling into local optimal solutions. This method improves the search ability and search accuracy of the algorithm. The dynamic adjustment of the iterative balance coefficient enables the algorithm to adopt different search strategies at different stages. In the early stage, the algorithm conducts a large-scale search to gradually narrow the range of the target position. In the later stage, the algorithm conducts a small-scale search to find the exact position of the optimal individual. This method enables the algorithm to more flexibly adapt to the requirements of different stages. By calculating the independent variables in the emotional fluctuation verification set and comparing them with the actual emotional fluctuation factors, the system can be optimized based on data. This method makes the optimization process more objective and reliable, reducing the deviation caused by subjective judgment.

[0107] Step S3: Analyze according to the target user's ability growth factor Z n , the target user's emotional fluctuation factor E n and the user test question recommendation prediction model to obtain the target user test question recommendation prediction test question set; Based on the target user test question recommendation prediction test question set, corresponding test questions are recommended for the target user in the question bank in the next stage; The user test question recommendation prediction model includes an ability increment matching layer, a comprehensive ability analysis layer, and a test question recommendation layer, which are used to conduct a comprehensive ability analysis of the target user and match personalized test questions corresponding to the ability.

[0108] The user test question recommendation prediction model in Step S3 includes an ability increment matching layer, a comprehensive ability analysis layer, and a test question recommendation layer;

[0109] The ability increment matching layer is used to calculate according to the target user's ability growth factor Z n and the target user's emotional fluctuation factor E n to obtain the target user's ability increment Z n ';

[0110] The comprehensive ability analysis layer is used to perform feature fusion according to all target user ability increments Z n ' in the current stage to obtain the target user's stage ability increment;

[0111] The test question recommendation layer is used to recommend test questions according to the target user's stage ability increment to obtain the target user test question recommendation prediction test question set;

[0112] By comprehensively considering the ability growth factor and emotional fluctuation factor of the target user, the most suitable test questions can be recommended for each user. This method ensures that the recommended test questions not only match the user's current ability level but also take into account the user's emotional state, thereby improving the learning effect. Through the ability increment matching layer and the comprehensive ability analysis layer, the ability growth of the user can be comprehensively analyzed. This method not only focuses on the user's answering accuracy rate but also considers the user's specific performance during the answering process, thus providing a more comprehensive ability analysis. According to the user's ability increment Z n ′ and the emotional fluctuation factor E n ,the recommended test questions can be dynamically adjusted. This method makes the recommended test questions more in line with the user's current state, neither too simple nor too difficult, thus maintaining the user's learning motivation.

[0113] Example 2, a personalized test question recommendation system based on a question bank, as shown in Figure 1 shown, includes:

[0114] User recommended test question ability analysis module. The user recommended test question ability analysis module includes a user test question acquisition unit and a user test question analysis unit;

[0115] The user test question acquisition unit is used to obtain the target user's stage answering data. The target user's stage answering data includes N pieces of target user's answered test question data T n and the target user's answering option data P n , n = 1, 2,..., N; N is the total number of test questions answered by the target user in the current stage;

[0116] The user test question analysis unit is used to obtain the target user's ability growth factor Z n based on the target user's answered test question data T n , the target user's answering option data P n and the user recommended test question ability analysis model. The user recommended test question ability analysis model includes a score judgment layer, an ability increment calculation layer, and an ability factor output layer, which are used to analyze the target user's ability growth according to the specific characteristic performance of the answered test questions;

[0117] Test question data analysis module. The test question data analysis module includes a test question feature acquisition unit and a test question feature analysis unit;

[0118] The test question feature acquisition unit is used to obtain the test question data for any test question and convert the test question data into an analysis test question vector X, X = [X 1 , X 2 , …, X i , …, X I , X iIt represents the specific information for analyzing the i-th item of test question features in the test question vector X, where I is the total number of test question features in the test question data;

[0119] The test question feature analysis unit is used to input the analyzed test question vector into the personalized test question analysis model for analysis, obtaining the test question analysis ability vector Y, Y = [Y 1 , Y 2 , …, Y i , …, Y I , where Y i is the test question ability analysis data for the i-th item of test question features corresponding to X i ; The analyzed test question vector X and the test question analysis ability vector Y corresponding to the test questions already answered by the target user are used as the test question data T n already answered by the target user; The personalized test question analysis model includes a feature recognition layer, I feature analysis layers C i and a feature result output layer, which is used to perform specific and accurate feature analysis on the test questions;

[0120] The user recommended test question emotion analysis module, which includes a user emotion acquisition unit and a user emotion analysis unit;

[0121] The user emotion acquisition unit is used to obtain the stage answering behavior data of the target user, and the stage answering behavior data of the target user includes the answering stay duration S n of the target user and the answering interaction data H n of the target user;

[0122] The user emotion analysis unit is used to obtain the target user emotion fluctuation factor E n based on the stage answering behavior data of the target user and the user recommended test question emotion analysis model; The user recommended test question emotion analysis model includes a duration analysis layer, an interaction data analysis layer, and an emotion fluctuation factor output layer, which are used to numerically analyze the emotion of the user during test question answering using an emotion fluctuation factor function, and use an improved optimization algorithm to determine the emotion fluctuation factor function;

[0123] The user test question recommendation prediction module, which includes a test question recommendation analysis unit;

[0124] The test question recommendation analysis unit is used to analyze according to the target user ability growth factor Z n , the target user emotion fluctuation factor E n and the user test question recommendation prediction model, obtaining the target user test question recommendation prediction test question set; Based on the target user test question recommendation prediction test question set, corresponding test questions are recommended for the target user in the question bank in the next stage; The user test question recommendation prediction model includes an ability increment matching layer, a comprehensive ability analysis layer, and a test question recommendation layer, which are used to perform comprehensive ability analysis on the target user and match personalized test questions with corresponding abilities.

[0125] It should be understood that those of ordinary skill in the art can make improvements or modifications based on the above description, and all such improvements and modifications shall fall within the protection scope of the appended claims of the present invention. The parts not described in detail in this specification belong to the prior art well-known to those of ordinary skill in the art.

Claims

1. A personalized test question recommendation method based on a question bank, characterized in that: The following steps are involved: Step S1: Obtaining the target user's stage answer data; The target user stage answer data contains N pieces of target user answered test data T n and the target user answer option data P n , n=1,2,…,N; N is the total number of test questions that the target user has answered in the current stage; Based on the target user's answered test data T n , Target user answer option data P n And the user recommendation test question ability analysis model, get the target user ability growth factor Z n The user recommendation test question ability analysis model includes a score judgment layer, an ability increment calculation layer, and an ability factor output layer, which is used to analyze the target user's ability growth based on the specific characteristics of the answered test questions; Get the target user's answered test data T n Specific steps: For any test question, obtain the test question data and convert the test question data into an analysis test question vector X, X=[X1, X2, …, X i , …, X I ], X i Represents the specific information of the i-th test feature in the test vector X, where I is the total number of test features in the test data; Input the analysis question vector into the personalized question analysis model for analysis, and obtain the question analysis ability vector Y, Y=[Y1, Y2, …, Y i , …, Y I ],Y i For X i The question ability analysis data corresponding to the i-th question feature; the analysis question vector X and the question analysis ability vector Y corresponding to the question answered by the target user are used as the question data T of the target user answered n ; The personalized test question analysis model includes a feature recognition layer, a feature analysis layer C i and the feature result output layer, which is used to conduct specific and accurate feature analysis of the test questions; Step S2: Obtain the target user's stage answering behavior data, which includes the target user's stay time S for answering questions. n Interaction data H with target users n ; Based on the target user's stage answering behavior data and the user recommended test question sentiment analysis model, the target user's sentiment fluctuation factor E is obtained n ; The user recommendation test question sentiment analysis model includes a duration analysis layer, an interaction data analysis layer, and a sentiment fluctuation factor output layer, which is used to quantify the user's sentiment when answering the test questions using the sentiment fluctuation factor function, and determine the sentiment fluctuation factor function using the improved optimization algorithm; Step S3: According to the target user capability growth factor Z n , Target user emotion fluctuation factor E n The user test question recommendation prediction model is analyzed to obtain a target user test question recommendation pre-test question set; based on the target user test question recommendation pre-test question set, corresponding test questions are recommended for the target user in the question bank in the next stage; the user test question recommendation prediction model includes an ability increment matching layer, a comprehensive ability analysis layer and a test question recommendation layer, which are used to perform comprehensive ability analysis on the target user and match personalized test questions with corresponding abilities.

2. A personalized test question recommendation method based on a question bank according to claim 1, characterized in that: The personalized test question analysis model in step S1 includes a feature recognition layer, a feature analysis layer C i And feature result output layer; The feature recognition layer is used to analyze all X in the question vector X. i Perform feature recognition and obtain feature label B i ; According to feature label B i X i Send to the corresponding feature analysis layer C i ; Feature Analysis Layer C i For X i Perform feature analysis and obtain Y i ; The feature result output layer is used to convert all Y i Combine them to get the question analysis ability vector Y, Y=[Y1, Y2,…, Y i , …, Y I ]; Training feature analysis layer C i The specific steps include: According to the setting feature label B i Collecting several groups of test question feature training samples corresponding to test question features; each group of test question feature training samples contains a group of specific information corresponding to test question features and test question ability analysis data; combining several groups of test question feature training samples to obtain a test question feature training set; According to the test feature training set, the feature analysis layer C i Model training is performed with the test ability analysis data as the target to obtain the initial feature analysis layer C i '; Initial feature analysis layer C i 'Evaluate the model and get the initial feature analysis layer C i 'Model evaluation results; if the initial feature analysis layer C i 'If the model evaluation result is passed, the initial feature analysis layer C i 'As feature analysis layer C i , deployed to the personalized test question analysis model, otherwise, continue model training; Traverse and train all feature analysis layers C i , until the model training is completed.

3. A personalized test question recommendation method based on a question bank according to claim 2, characterized in that: The user recommended test question ability analysis model in step S1 includes a score judgment layer, an ability increment calculation layer and an ability factor output layer; The scoring judgment layer is used to judge the target user's answer options data P n and the target user's answered test data T n The analysis question vector X in the optimization correlation calculation is used to obtain the ability growth parameter vector α, α=[α1, α2, …, α i , …, α I ]; The capacity increment calculation layer is used to utilize the formula Calculate the target user capability growth factor Z n ; Y is composed of the test data T that the target user has answered n The test question analysis ability vector Y is determined; The capability factor output layer is used to output the target user capability growth factor Z n .

4. A personalized test question recommendation method based on a question bank according to claim 3, characterized in that: The specific steps for optimizing correlation calculation include: For any X i Perform optimized correlation calculation: For the target user's answer option data P n Perform feature extraction to obtain the target user's answer option data feature P n '; According to the target user's answer option data characteristics P n ' and X i Correlation calculation to obtain the data correlation Q of the target user's answer options i ; Using the formula Calculate α i ;MM min Indicates all Q i The minimum value in MM max Indicates all Q i The maximum value in; β represents the adjustment parameter; Iterate over all X i , we get the capability growth parameter vector α, α=[α1, α2, …, α i , …, α I ].

5. A personalized test question recommendation method based on a question bank according to claim 4, characterized in that: The user recommendation test question sentiment analysis model in step S2 includes a duration analysis layer, an interaction data analysis layer, and a sentiment fluctuation factor output layer; The duration analysis layer is used to calculate the target user's answer time S n Calculate with the set threshold time to obtain the target user's duration emotion parameter U n ; The interactive data analysis layer is used to analyze the interactive data H of target users’ answers. n Analyze and get the target user emotion prediction label V n ; Predict label V based on target user sentiment n Match in the emotion parameter library to obtain the target user emotion prediction label factor V n '; The emotion fluctuation factor output layer is used to calculate the target user's emotion parameter U according to the target user's duration. n , target user emotion prediction label factor V n 'Calculate the emotion fluctuation factor function to obtain the target user's emotion fluctuation factor E n ; The emotional fluctuation factor function is determined by prior data and optimization algorithms; The specific steps for training the interactive data analysis layer include: Collect several groups of emotion label training samples; each group of emotion label training samples contains user answering interaction data and annotated emotion labels; combine several groups of emotion label training samples to obtain an emotion label training set; According to the emotion label training set, the interaction data analysis layer is trained with the goal of labeling emotion labels to obtain an initial interaction data analysis layer; a model evaluation is performed on the initial interaction data analysis layer to obtain an initial interaction data analysis layer model evaluation result; if the initial interaction data analysis layer model evaluation result is passed, the initial interaction data analysis layer is used as the interaction data analysis layer; otherwise, the model training continues.

6. A personalized test question recommendation method based on a question bank according to claim 5, characterized in that: The specific steps to determine the emotional fluctuation factor function include: Collect several groups of emotion fluctuation verification samples; in each group of emotion fluctuation verification samples, set the independent variables as user duration emotion parameters and user emotion prediction label factors, and the dependent variable as user emotion fluctuation factors; all emotion fluctuation verification samples are suitable for subsequent analysis; combine several groups of emotion fluctuation verification samples to obtain an emotion fluctuation verification set; Construct K functions to optimize individual G k , k=1, 2, ..., K; each function optimizes individual G k contains a set of solutions for constructing the emotional fluctuation factor function; K functions optimize individual G k Combine to obtain the function optimization iteration population; set the number of iterations j, j = 1, 2, ..., J; set the iteration balance coefficient R t , R t =D*((Jj) / J) 3 , D is the iterative balance weight; During iteration, the function optimization individual G in the function optimization iterative population is k Perform simulation calculation to obtain the function optimization fitness W k ; Determine the iterative balance coefficient R at this time t Is it less than the preset stage update threshold? If the iteration balance coefficient R t If the iterative balance coefficient R is greater than the preset stage update threshold, the function optimization iterative population is subjected to Gaussian perturbation mutation to obtain a new function optimization iterative population for the next iteration. t If it is less than the preset stage update threshold, the function optimization iterative population is subjected to Cauchy perturbation mutation to obtain a new function optimization iterative population for the next iteration; The specific steps for simulation calculation include: Optimize individual G according to the function k Calculate the independent variables in the emotion fluctuation validation set to obtain the simulated emotion fluctuation factor; calculate the Euclidean distance between the simulated emotion fluctuation factor and the user emotion fluctuation factor to obtain the simulated Euclidean distance; use the inverse of the simulated Euclidean distance as a function to optimize the individual G k The function optimizes the fitness W k ; When the number of iterations j reaches the maximum value, the output function optimizes the fitness W k The maximum corresponding function optimizes the individual G k , that is, the optimal function optimization individual; the solution of the corresponding emotional fluctuation factor function constructed in the optimal function optimization individual is taken as the emotional fluctuation factor function.

7. A personalized test question recommendation method based on a question bank according to claim 6, characterized in that: The user test question recommendation prediction model in step S3 includes an ability increment matching layer, a comprehensive ability analysis layer, and a test question recommendation layer; The capability increment matching layer is used to increase the target user's capability factor Z. n and target user emotion fluctuation factor E n Calculate and get the target user capability increment Z n '; The comprehensive capability analysis layer is used to calculate the capability increment Z of all target users in the current stage. n 'Perform feature fusion to obtain the target user's stage capability increment; The question recommendation layer is used to recommend questions based on the target user's stage capability increments, and obtain a set of pre-test questions recommended for the target user.

8. A personalized test question recommendation system based on a question bank, characterized in that: The system applies a personalized test question recommendation method based on a question bank as described in any one of claims 1 to 7, including: A user recommended test question ability analysis module, which includes a user test question acquisition unit and a user test question analysis unit; The user test question acquisition unit is used to acquire the target user's stage answer data; the target user's stage answer data contains N pieces of target user's answered test question data T n and the target user answer option data P n , n=1, 2, …, N; N is the total number of questions answered by the target user in the current stage; The user test question analysis unit is used to analyze the test questions answered by the target user based on the test question data T n , Target user answer option data P n And the user recommendation test question ability analysis model, get the target user ability growth factor Z n The user recommendation test question ability analysis model includes a score judgment layer, an ability increment calculation layer, and an ability factor output layer, which is used to analyze the target user's ability growth based on the specific characteristics of the answered test questions; A test question data analysis module, which includes a test question feature acquisition unit and a test question feature analysis unit; The test feature acquisition unit is used to acquire test data for any test question and convert the test data into an analysis test vector X, where X = [X1, X2, ..., X i , …, X I ], X i Represents the specific information of the i-th test feature in the test vector X, where I is the total number of test features in the test data; The question feature analysis unit is used to input the question analysis vector into the personalized question analysis model for analysis, and obtain the question analysis ability vector Y, Y = [Y1, Y2, ..., Y i , …, Y I ],Y i For X i The question ability analysis data corresponding to the i-th question feature; the analysis question vector X and the question analysis ability vector Y corresponding to the question answered by the target user are used as the question data T of the target user answered n ; The personalized test question analysis model includes a feature recognition layer, a feature analysis layer C i and the feature result output layer, which is used to conduct specific and accurate feature analysis of the test questions; A user-recommended test question sentiment analysis module, which includes a user sentiment acquisition unit and a user sentiment analysis unit; The user emotion acquisition unit is used to obtain the target user's stage answering behavior data. The target user's stage answering behavior data contains the target user's answering time S n Interaction data H with target users n ; The user emotion analysis unit is used to obtain the target user's emotion fluctuation factor E based on the target user's stage answering behavior data and the user recommended test question emotion analysis model. n The user recommendation test question sentiment analysis model includes a duration analysis layer, an interaction data analysis layer, and a sentiment fluctuation factor output layer, which is used to quantify the user's sentiment when answering the test questions using the sentiment fluctuation factor function, and determine the sentiment fluctuation factor function using the improved optimization algorithm; A user test question recommendation prediction module, which includes a test question recommendation analysis unit; The question recommendation analysis unit is used to increase the ability factor Z of the target user. n , Target user emotion fluctuation factor E n The user test question recommendation prediction model is analyzed to obtain a target user test question recommendation pre-test question set; based on the target user test question recommendation pre-test question set, corresponding test questions are recommended for the target user in the question bank in the next stage; the user test question recommendation prediction model includes an ability increment matching layer, a comprehensive ability analysis layer and a test question recommendation layer, which are used to perform comprehensive ability analysis on the target user and match personalized test questions with corresponding abilities.

Images