Free test paper composition method and system based on test score

Abstract

The invention provides a free test paper composition method and system based on test scores, and relates to the technical field of data processing, and the method comprises the steps: obtaining a test score and a wrong question set when a user answers the last test paper; determining a suitable difficulty coefficient of the user according to a test score of the user answering the last test paper; determining to-be-mastered knowledge points of the user and the unfamiliarity of each to-be-mastered knowledge point according to the wrong question set of the last test paper answered by the user; obtaining the total number of preset test questions set by the user; determining a preset test question number of each to-be-mastered knowledge point according to a preset test question total number and the unfamiliar degree of each to-be-mastered knowledge point; taking all the to-be-mastered knowledge points as a precondition, taking the test paper difficulty coefficient close to a suitable difficulty coefficient and the test question number of each to-be-mastered knowledge point in the test paper close to a preset test question number as targets, extracting test questions from the question bank to perform free test paper group, and generating the test paper.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a free test paper composition method and system based on test scoring. Background Art

[0002] With the advancement of science and technology, especially the rapid development of information networks in recent years, more and more modern technologies are being applied to education and learning. In the process of students learning through test questions, the difficulty, knowledge point coverage and question types of the test questions can be automatically adjusted according to the completion of the test questions, and relevant test questions can be generated adaptively to provide personalized learning experience and effective learning support to help students quickly master knowledge points.

[0003] The current free test paper composition method mainly matches the similarity between each test question in the question bank and the wrong questions answered by the students, and pushes the test questions with high similarity to the students for re-practice, so that the students can quickly master the relevant knowledge points. However, the current free test paper composition method may cause students to repeatedly practice similar questions, and lack the exploration and learning of other knowledge points, which will limit the students' vision and may not be able to fully master the various knowledge points in the course, resulting in reduced accuracy of free test paper composition. At the same time, there is a lack of overall grasp of the students' mastery of knowledge points. Students may not have a solid foundation in a certain knowledge point. Pushing questions based only on similarity may keep pushing difficult questions with high similarity to students, resulting in students being unable to start with questions of lower difficulty and learn step by step. Students may fall into a dilemma that they cannot answer, resulting in frustration of their understanding ability and interest in learning the knowledge point, and reducing their learning efficiency. Summary of the invention

[0004] In order to solve the technical problems that the current free test paper composition method in the prior art may cause students to practice similar questions repeatedly, but lack the exploration and learning of other knowledge points, which will limit students' horizons and may not be able to fully grasp the various knowledge points in the course, resulting in reduced accuracy of free test paper composition, lack of overall grasp of students' mastery of knowledge points, students may not have a solid foundation in a certain knowledge point, and only push questions based on similarity may continue to push difficult questions with high similarity to students, resulting in students being unable to start from questions with lower difficulty and learn step by step, and students may fall into a dilemma that cannot be solved, resulting in students' comprehension ability and learning interest in the knowledge point being frustrated, and reducing students' learning efficiency, the present invention provides a free test paper composition method and system based on test scoring.

[0005] The technical solution provided by the embodiment of the present invention is as follows:

[0006] First aspect:

[0007] An embodiment of the present invention provides a free test paper composition method based on test scoring, comprising:

[0008] S1: Get the test score and wrong question set of the user's last test paper;

[0009] S2: Determine the appropriate difficulty coefficient for the user based on the test score of the previous test paper taken by the user;

[0010] S3: Determine the user's knowledge points to be mastered and the unfamiliarity of each knowledge point to be mastered based on the set of wrong questions answered by the user in the previous test paper;

[0011] S4: Obtain the total number of preset test questions set by the user;

[0012] S5: Determine the number of preset test questions for each knowledge point to be mastered according to the total number of preset test questions and the unfamiliarity of each knowledge point to be mastered;

[0013] S6: With the prerequisite of containing all the knowledge points to be mastered, and with the goal of the test paper difficulty coefficient being close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper being close to the preset number of test questions, test questions are extracted from the question bank for free composition to generate a test paper.

[0014] Second aspect:

[0015] An embodiment of the present invention provides a free test-taking system based on test scoring, comprising:

[0016] processor;

[0017] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the free test-paper-composing method based on test scoring as described in the first aspect is implemented.

[0018] The third aspect:

[0019] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the free test paper composition method based on test scoring as described in the first aspect is implemented.

[0020] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0021] (1) In the present invention, the appropriate difficulty coefficient of the user is determined according to the test score of the user's previous test paper, so as to comprehensively grasp the student's current mastery of knowledge points and push test questions of appropriate difficulty so that students can start with questions of lower difficulty and learn step by step, thus avoiding students from falling into a dilemma that they cannot solve, improving students' understanding ability of knowledge points and learning interest, and improving students' learning efficiency.

[0022] (2) In the present invention, based on the knowledge points to be mastered in the previous test paper of the students and the unfamiliarity of each knowledge point to be mastered, with the inclusion of all the knowledge points to be mastered as a prerequisite, and with the difficulty coefficient of the test paper being close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper being close to the preset number of test questions as the goal, a personalized test paper covering all the knowledge points to be mastered is generated for the students, avoiding pushing test questions based on similarity alone, improving students' ability to explore and learn other knowledge, improving the comprehensiveness of knowledge point coverage of the test questions, and improving the accuracy of free test paper composition.

[0023] (3) In the present invention, the test question allocation for each knowledge point to be mastered is determined based on the total number of preset test questions and the unfamiliarity of each knowledge point to be mastered. The system can accurately guide students to study and practice, avoiding students from blindly learning and wasting time on knowledge points that have already been mastered, thereby improving students' learning efficiency and the accuracy of free test papers. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A schematic diagram of a flow chart of a free test paper composition method based on test scoring provided by an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of the structure of a free test paper composition system based on test scoring provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0028] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0029] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0030] In the embodiments of the present invention, sometimes the subscripts such as W 1 It may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0031] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0032] Reference Manual Attached Figure 1 , showing a flow chart of a free test paper composition method based on test scoring provided by an embodiment of the present invention.

[0033] The embodiment of the present invention provides a method for free test composition based on test scoring, which can be implemented by a free test composition device based on test scoring, and the free test composition device based on test scoring can be a terminal or a server. The processing flow of the method for free test composition based on test scoring can include the following steps:

[0034] S1: Get the test score and wrong question set of the user's last test paper.

[0035] S2: Determine the appropriate difficulty coefficient for the user based on the test score of the previous test paper taken by the user.

[0036] In a possible implementation, the method for determining the appropriate difficulty coefficient specifically includes:

[0037] When the user's test score for the previous test satisfies s≤s 1 When the user's appropriate difficulty coefficient d is determined to be d a .

[0038] When the user answers the last test paper, the test score meets s 1 <s≤s 2 When the user's appropriate difficulty coefficient d is determined to be d b .

[0039] When the user answers the last test paper, the test score meets s 2 <s≤s 3 When the user's appropriate difficulty coefficient d is determined to be d c .

[0040] When the user answers the last test paper, the test score meets s 3 <s≤s 4 When the user's appropriate difficulty coefficient d is determined to be d e .

[0041] When the user's test score for the previous test satisfies s>s 4 When the user's appropriate difficulty coefficient is determined to be d f .

[0042] Among them, s represents the test score of the user's last test paper, s 1 represents the first scoring threshold, s 2 represents the second scoring threshold, s 3 represents the third scoring threshold, s 4 represents the fourth scoring threshold, d a Indicates the first level difficulty coefficient, d b Indicates the secondary difficulty coefficient, d c Indicates the level 3 difficulty coefficient, d e Indicates the difficulty coefficient of level 4, d f Indicates five levels of difficulty.

[0043] Among them, those skilled in the art can set the first scoring threshold s according to actual conditions. 1 , the second scoring threshold s 2 , the third scoring threshold s 3 and the fourth scoring threshold s 4 The present invention does not limit the size.

[0044] It should be noted that by dynamically determining the appropriate difficulty coefficient based on the user's test score, personalized learning support can be provided for each student. Students of different levels can obtain test questions that are suitable for their ability levels, avoiding the situation where students encounter test questions that are too simple or too difficult, resulting in a decrease in learning effect. At the same time, setting different difficulty coefficients according to different scoring thresholds can guide students' learning more accurately. For example, when a student's score is low, a lower difficulty coefficient can be set to provide relatively simple test questions to help students consolidate their foundation; when a student's score is high, the difficulty coefficient can be increased to challenge their learning ability.

[0045] In the present invention, the user's appropriate difficulty coefficient is determined according to the test score of the user's previous test paper, so as to grasp the student's current mastery of knowledge points as a whole, and then push test questions of appropriate difficulty so that students can start with questions of lower difficulty and study step by step, avoiding students from falling into difficulties that they cannot solve, improving students' understanding ability of knowledge points and learning interest, and improving students' learning efficiency.

[0046] S3: Determine the user's knowledge points to be mastered and the degree of unfamiliarity with each knowledge point to be mastered based on the set of wrong questions answered by the user in the previous test paper.

[0047] In a possible implementation manner, the unfamiliarity of each knowledge point to be mastered is determined in the following manner:

[0048] m j =tanh(t j )

[0049] Among them, m j represents the unfamiliarity of the jth knowledge point to be mastered, t j represents the number of wrong questions in the wrong questions set of the previous test paper that contain the jth knowledge point to be mastered. tanh() represents the hyperbolic tangent function, which is used to convert t j Convert to a value in the range [0,1].

[0050] The more wrong questions the user has in the wrong question set of the previous test paper that contain the j-th knowledge point to be mastered, the greater the unfamiliarity of the user to the j-th knowledge point to be mastered.

[0051] It should be noted that using the hyperbolic tangent function to convert the number of wrong questions into unfamiliarity values ​​in the range of [0,1] can accurately measure the unfamiliarity of each knowledge point. This measurement method enables the system to more accurately understand the students' familiarity with different knowledge points, which helps to provide more accurate guidance for subsequent learning.

[0052] In a possible implementation manner, the unfamiliarity of each knowledge point to be mastered is determined in the following manner:

[0053] m j =γt j

[0054] Among them, m j represents the unfamiliarity of the jth knowledge point to be mastered, t j It indicates the number of wrong questions in the set of wrong questions of the previous test paper taken by the user that contain the j-th knowledge point to be mastered. γ indicates the conversion coefficient, and γ>0.

[0055] The more wrong questions the user has in the wrong question set of the previous test paper that contain the j-th knowledge point to be mastered, the greater the unfamiliarity of the user to the j-th knowledge point to be mastered.

[0056] It should be noted that by adjusting the value of the conversion coefficient γ, the unfamiliarity can be adjusted individually according to the actual situation. For example, different conversion coefficients can be set according to the importance of the knowledge point or the learning ability level of the students to better meet the personalized learning needs.

[0057] It should be noted that directly using the number of wrong questions as a measure of unfamiliarity can intuitively reflect the students' mastery of each knowledge point. The more wrong questions there are, the lower the students' mastery of the knowledge point, and the higher the unfamiliarity, which helps teachers and students quickly understand the students' learning situation. Compared with using complex functions for conversion, directly multiplying the number of wrong questions by the conversion coefficient can simplify the calculation process, reduce the complexity of implementation, and be easier to implement.

[0058] In the present invention, the unfamiliarity is converted into a numerical form, which can quantify the student's learning progress for each knowledge point. Such quantification helps students and teachers to understand the student's learning situation on each knowledge point more clearly, and provides a basis for formulating more reasonable learning plans and teaching strategies. Targeted determination of the unfamiliarity of each knowledge point can help students to study in a targeted manner. Students can review and strengthen their focus according to their unfamiliarity with different knowledge points, thereby improving learning efficiency. Based on the quantitative data of unfamiliarity, the system can recommend learning resources and exercise questions that meet their learning level and unfamiliarity to students, and realize personalized learning recommendations. Such recommendations can better meet students' learning needs and improve learning effects.

[0059] S4: Obtain the total number of preset test questions set by the user.

[0060] Optionally, the total number of preset test questions can be 10, 20, 50, etc. The user can set the total number of preset test questions according to actual conditions.

[0061] S5: Determine the number of preset test questions for each knowledge point to be mastered according to the total number of preset test questions and the unfamiliarity of each knowledge point to be mastered.

[0062] In a possible implementation, S5 specifically includes: determining the number of preset test questions for each knowledge point to be mastered according to the following formula:

[0063]

[0064] Among them, a j represents the number of preset test questions for the jth knowledge point to be mastered, a represents the total number of preset test questions set by the user, and m j represents the unfamiliarity of the jth knowledge point to be mastered, and J represents the set of knowledge points to be mastered.

[0065] It should be noted that the question resources are allocated in a personalized manner according to the unfamiliarity of each knowledge point. For knowledge points with higher unfamiliarity, more questions are allocated so that students have more practice opportunities and strengthen their mastery of these knowledge points. By adjusting the question allocation according to unfamiliarity, teaching resources can be used more effectively. Allocating more questions to knowledge points with higher unfamiliarity can help students concentrate on targeted practice and improve learning efficiency.

[0066] In the present invention, the test question distribution of each knowledge point to be mastered is determined according to the total number of preset test questions and the unfamiliarity of each knowledge point to be mastered. The system can accurately guide students to study and practice, avoiding students from blindly learning and wasting time on knowledge points that have already been mastered, improving students' learning efficiency, and improving the accuracy of free test papers.

[0067] S6: With the prerequisite of containing all the knowledge points to be mastered, and with the goal of the test paper difficulty coefficient being close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper being close to the preset number of test questions, test questions are extracted from the question bank for free composition to generate the test paper.

[0068] In a possible implementation, S6 specifically includes sub-steps S601 to S603:

[0069] S601: With the premise of containing all the knowledge points to be mastered, set the constraint conditions of the free test-taking process.

[0070] Optionally, constraints include:

[0071] Knowledge point coverage constraints: The free test paper plan contains all the knowledge points to be mastered.

[0072] It should be noted that ensuring that the test paper covers all the knowledge points to be mastered can ensure that the knowledge points that students need to master in the test are fully examined, making the test paper more comprehensive and effective.

[0073] Total score constraints:

[0074]

[0075] Among them, sc i Represents the score of the i-th test question, and I represents the set of test questions formed by the free test paper composition plan.

[0076] It should be noted that by setting a total score constraint to ensure that the total score of each test paper is the same, this helps to ensure that the evaluation criteria are consistent, thereby improving the fairness and consistency of the test paper.

[0077] Total duration constraints:

[0078]

[0079] Among them, t i represents the estimated completion time of the ith test question, T min Indicates the minimum total duration, T max Indicates the maximum total duration.

[0080] It should be noted that by setting a total time constraint, the test time can be kept within a reasonable range to avoid the test time being too long or too short. Reasonable test time helps students better arrange their time and complete the test paper, and it is also conducive to the smooth progress of the test.

[0081] Discrimination Constraint:

[0082]

[0083] Among them, Q represents the test paper discrimination, q i represents the discrimination of the i-th test question, Q min Indicates the discrimination threshold.

[0084] Specifically, the discrimination can be expressed by the difference in scores between the high-scoring group and the low-scoring group.

[0085] It should be noted that by setting the discrimination constraint, the test paper is required to have a certain degree of discrimination, that is, the test questions can effectively distinguish the ability levels of students. This helps to improve the quality of the test questions, making the test paper more challenging, and also more accurately assessing the ability of students.

[0086] Exposure constraints:

[0087]

[0088] Among them, Q represents the exposure of the test paper, q i represents the exposure of the i-th question, B max Indicates the exposure threshold.

[0089] Specifically, exposure refers to the frequency of use of the test question in previous practice. The frequency of use of the test question can be evaluated by counting the number of times the test question has been used in previous exams or practices. The higher the frequency of use, the higher the exposure of the test question.

[0090] It should be noted that by setting exposure constraints, the exposure degree of the test questions can be controlled, that is, the frequency with which the test questions are used multiple times. Reasonable control of the exposure degree of the test questions can help prevent the test questions from becoming too familiar, maintain the novelty and fairness of the test paper, and also improve the credibility and effectiveness of the test paper.

[0091] S602: With the goal of making the test paper difficulty coefficient close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper close to the preset number of test questions, an objective function of the free test paper composition process is constructed.

[0092] Optionally, the objective function is specifically:

[0093]

[0094] Among them, F() represents the objective function, X represents the free test plan, min represents minimization, a represents the total number of preset test questions set by the user, and d i represents the difficulty coefficient of the i-th test question, I represents the test question set formed by the free test paper scheme, d represents the appropriate difficulty coefficient of the user, and λ 1 represents the weight coefficient of the difficulty coefficient deviation term, represents the actual number of test questions for the jth knowledge point to be mastered in the free test paper scheme, a j represents the number of preset test questions for the jth knowledge point to be mastered, J represents the set of knowledge points to be mastered, and λ 2 Represents the weight coefficient of the test question number deviation term.

[0095] Among them, those skilled in the art can set the weight coefficient λ of the difficulty coefficient deviation term according to actual conditions. 1 And the weight coefficient λ of the test number deviation term 2 The present invention does not limit the size.

[0096] It should be noted that the objective function takes into account the deviation between the overall difficulty of the test paper and the user's appropriate difficulty coefficient, as well as the deviation between the actual number of test questions and the preset number of test questions for each knowledge point to be mastered. This ensures that the overall difficulty of the generated test paper is consistent with the user's appropriate level and can cover the knowledge points that the user needs to master.

[0097] Furthermore, by minimizing the objective function, the generated test paper can achieve a good balance in terms of overall difficulty and knowledge point coverage. In this way, the generated test paper can not only meet the user's learning level and needs, but also ensure the quality and effectiveness of the test paper.

[0098] Optionally, the objective function is specifically:

[0099]

[0100] Among them, F() represents the objective function, X represents the free test plan, min represents minimization, a represents the total number of preset test questions set by the user, and d i represents the difficulty coefficient of the i-th test question, I represents the test question set formed by the free test paper scheme, d represents the appropriate difficulty coefficient of the user, and λ 1 represents the weight coefficient of the difficulty coefficient deviation term, represents the actual number of test questions for the jth knowledge point to be mastered in the free test paper scheme, a jrepresents the number of preset test questions for the jth knowledge point to be mastered, J represents the set of knowledge points to be mastered, and λ 2 represents the weight coefficient of the knowledge coverage deviation term, b i represents the exposure of the i-th question, b represents the system preset exposure, λ 3 Represents the weight coefficient of the exposure bias term, q i represents the discrimination of the i-th test question, q represents the system preset discrimination, and λ 4 Represents the weight coefficient of the discrimination bias term.

[0101] Among them, those skilled in the art can set the weight coefficient λ of the difficulty coefficient deviation term according to actual conditions. 1 , the weight coefficient of the test number deviation term λ 2 , the weight coefficient λ of the exposure bias term 3 And the weight coefficient λ of the discrimination deviation term 4 The present invention does not limit the size.

[0102] It should be noted that by minimizing the objective function, the generated test paper can achieve a good balance in terms of difficulty, knowledge point coverage, exposure and discrimination. The test paper generated in this way can not only adapt to the learning levels and needs of different students, but also ensure the quality and effectiveness of the test paper, and improve the practicality and applicability of the test paper.

[0103] S603: Under the constraints of the constraints, taking the objective function as the goal, through the genetic algorithm, test questions are extracted from the question bank for free composition to generate the test paper.

[0104] Among them, the genetic algorithm is an optimization algorithm based on biological evolution theory, which is often used to solve search and optimization problems. It simulates the process of biological evolution and gradually searches for the optimal solution or a better solution to the problem through operations such as inheritance, mutation, and selection of the group.

[0105] In traditional genetic algorithms, elite selection or roulette wheel selection is often used for selection, which is prone to premature convergence and fall into a local optimal solution. In order to solve this problem, the present invention provides an improved genetic algorithm, which is specifically:

[0106] The inverse of the objective function is used as the fitness function of the genetic algorithm.

[0107] It should be noted that the larger the reciprocal of the objective function, the smaller the value of the objective function, so maximizing the reciprocal of the objective function is equivalent to minimizing the objective function. This transformation makes the problem easier to handle because genetic algorithms are usually used to solve minimization problems.

[0108] Initialize the population Q 1, the population contains multiple individuals, each of which represents a feasible free test composition scheme.

[0109] Based on the Q-Learning algorithm, the individuals in the population are selected to form a population Q 2 .

[0110] The gene space constructed by the population is used as the action strategy space of the Q-Learning algorithm. The change in fitness value after performing a random selection action is used as the immediate reward for performing the selection action. The population is randomly selected and the Q matrix of the Q-Learning algorithm is updated. Then, the selection at the next iteration can be made based on the updated Q matrix:

[0111] Q(S t ,A t )=βQ(S t ,A t )+(1-β)(R t+1 +μmaxQ(S t+1 ,a)-Q(S t ,A t ))

[0112] Among them, S t represents the state at the tth iteration, A t represents the randomly selected action at the tth iteration, WQ(S t ,A t ) indicates that in state S t Execute randomly selected action A t Q value, β represents the learning rate, R t+1 Indicates that in state S t Execute randomly selected action A t The instant reward, μ represents the discount factor, maxQ(S t+1 ,a) represents the next state S t+1 The maximum Q value of the action a that can be selected in , also known as the long-term reward.

[0113] It should be noted that the use of the Q-Learning algorithm can make the selection operation more adaptive. By randomly selecting actions and updating the Q value based on the immediate reward, individuals in the population can gradually learn which gene combinations are more conducive to improving fitness and are more likely to be selected. The Q-Learning algorithm can help the population avoid falling into a local optimal solution. By introducing the discount factor μ, the algorithm can consider long-term rewards, thereby paying more attention to long-term benefits. This can reduce the situation where the population falls into a local optimal solution due to excessive pursuit of immediate rewards.

[0114] In the present invention, the gene space constructed by the population is used as the action strategy space of the Q-Learning algorithm, and by performing random selection actions and updating the Q matrix, the adaptability, search ability and learning speed of the population can be improved, thereby more effectively optimizing the fitness of the population.

[0115] For population Q 2 Perform a crossover operation, from population Q 2 Randomly select two individuals as parents, generate a random number, and compare the random number with the crossover probability P e Compare the size, if the random number is less than the crossover probability P e , then the parent is cross-operated to generate new individuals to form a population Q 3 , new individual y 1 ,y 2 The generation method is as follows:

[0116] y 1 =rand×x 1 +(1-rand)×x 2 y 2 =rand×x 2 +(1-rand)×x 1

[0117] Among them, x 1 、x 2 Represents the parent, and rand represents a random number between 0 and 1.

[0118] In the present invention, through the crossover operation, the genetic information of two different individuals can be combined to generate new individuals. In this way, more gene combinations can be introduced, the diversity of the population can be increased, and it is helpful to avoid the population from converging to the local optimal solution too early, thereby improving the global search ability. The crossover operation can promote the exchange and recombination of genetic information. The gene exchange between the parent individuals can cause the offspring individuals to have some common characteristics between the parent individuals, which helps to retain good genetic characteristics and is likely to create new excellent combinations.

[0119] Among them, the crossover probability P e Specifically:

[0120]

[0121] Among them, P e represents the crossover probability, P e,max represents the maximum crossover probability, P e,min represents the minimum crossover probability, δ represents the fitness value of the current individual, δ avg represents the average fitness value of the population, δ max Represents the maximum fitness value among individuals.

[0122] It should be noted that the crossover probability is dynamically adjusted as the fitness of the population changes, making the algorithm adaptive. When the overall fitness of the population is low, the crossover probability may increase to increase the diversity and search ability of the population; when the fitness of the population is high, the crossover probability may decrease to retain the characteristics of better individuals. By dynamically adjusting the crossover probability according to the individual fitness value, more diversity can be introduced into the population. When the individual fitness value is low, increasing the crossover probability helps to explore the search space more widely and improve the diversity of the population, which helps to jump out of the local optimal solution; when the individual fitness value is high, reducing the crossover probability can retain more characteristics of excellent individuals and avoid losing excellent solutions too early.

[0123] For population Q 3 Perform mutation operation, from population Q 3 Randomly select a parent x from 3 , generate a random number and compare the random number with the mutation probability P m Compare the size. If the random number is less than the mutation probability P, m , then for the parent x 3 Perform mutation operation to generate new individual y 3 Replace the original individuals to form a population Q 4 , new individual y 3 The generation method is as follows:

[0124]

[0125] Among them, x 3 Represents the parent, and rand represents a random number between 0 and 1.

[0126] It should be noted that randomly selecting individuals for mutation operations helps to introduce new individuals, thereby increasing the diversity of the population. These new individuals may explore new solution spaces, helping to avoid premature convergence to local optimal solutions. Mutation operations can increase the breadth of search by introducing a certain degree of randomness based on existing individuals. Newly generated individuals may have certain similarities with existing individuals, but due to the randomness of the mutation operation, they may produce characteristics different from the original individuals, thereby exploring new solution spaces.

[0127] Among them, the mutation probability P m Specifically:

[0128]

[0129] Among them, P m represents the mutation probability, P m,max represents the maximum mutation probability, P m,min represents the minimum mutation probability, δ represents the fitness value of the current individual, δavg represents the average fitness value of the population, δ max Represents the maximum fitness value among individuals.

[0130] It should be noted that the mutation probability is dynamically adjusted as the fitness of the population changes, making the algorithm adaptive. When the overall fitness of the population is low, the mutation probability may increase to increase the diversity and search ability of the population; when the fitness of the population is high, the mutation probability may decrease to retain the characteristics of better individuals. By dynamically adjusting the mutation probability according to the individual fitness value, more diversity can be introduced into the population. When the individual fitness value is low, increasing the mutation probability helps to explore the search space more widely and improve the diversity of the population, which helps to jump out of the local optimal solution; when the individual fitness value is high, reducing the mutation probability can retain more characteristics of excellent individuals and avoid losing excellent solutions too early.

[0131] Determine whether the number of iterations has reached the maximum number of iterations. If so, determine the individual with the highest fitness value as the best free test solution. Otherwise, return to the step of selecting individuals in the population and continue iterating.

[0132] In the present invention, through the optimization process of the genetic algorithm, the optimal combination of test questions can be selected under the premise of satisfying the constraints to maximize the quality of the test paper. This can ensure that the test paper has good knowledge point coverage, difficulty balance and differentiation, so as to more effectively evaluate students' abilities and understanding levels.

[0133] In a possible implementation, the free test-taking method based on test scoring further includes:

[0134] S6: Update the user's knowledge points to be mastered according to the test scores of the generated test paper.

[0135] In the present invention, based on the students' performance on the test paper, we can more accurately understand the knowledge points they have mastered and not mastered, and prepare for the next test paper generation. By updating the knowledge points to be mastered, we can provide students with more personalized learning guidance and strengthen the knowledge points that need to be improved in a targeted manner.

[0136] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0137] (1) In the present invention, the appropriate difficulty coefficient of the user is determined according to the test score of the user's previous test paper, so as to comprehensively grasp the student's current mastery of knowledge points and push test questions of appropriate difficulty so that students can start with questions of lower difficulty and learn step by step, thus avoiding students from falling into a dilemma that they cannot solve, improving students' understanding ability of knowledge points and learning interest, and improving students' learning efficiency.

[0138] (2) In the present invention, based on the knowledge points to be mastered in the previous test paper of the students and the unfamiliarity of each knowledge point to be mastered, with the inclusion of all the knowledge points to be mastered as a prerequisite, and with the difficulty coefficient of the test paper being close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper being close to the preset number of test questions as the goal, a personalized test paper covering all the knowledge points to be mastered is generated for the students, avoiding pushing test questions based on similarity alone, improving students' ability to explore and learn other knowledge, improving the comprehensiveness of knowledge point coverage of the test questions, and improving the accuracy of free test paper composition.

[0139] (3) In the present invention, the test question allocation for each knowledge point to be mastered is determined based on the total number of preset test questions and the unfamiliarity of each knowledge point to be mastered. The system can accurately guide students to study and practice, avoiding students from blindly learning and wasting time on knowledge points that have already been mastered, thereby improving students' learning efficiency and the accuracy of free test papers.

[0140] Reference Manual Attached Figure 2 , showing a schematic structural diagram of a free test paper composition system based on test scoring provided by the present invention.

[0141] The present invention further provides a free test paper composition system 20 based on test scoring, which is applied to the free test paper composition method based on test scoring, and comprises:

[0142] Processor 201;

[0143] The memory 202 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 201, the free test-paper-composing method based on test scoring as described in the method embodiment is implemented.

[0144] The free test paper composition system 20 based on test scoring provided by the present invention can execute the above-mentioned free test paper composition method based on test scoring and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0145] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0146] (1) In the present invention, the appropriate difficulty coefficient of the user is determined according to the test score of the user's previous test paper, so as to comprehensively grasp the student's current mastery of knowledge points and push test questions of appropriate difficulty so that students can start with questions of lower difficulty and learn step by step, thus avoiding students from falling into a dilemma that they cannot solve, improving students' understanding ability of knowledge points and learning interest, and improving students' learning efficiency.

[0147] (2) In the present invention, based on the knowledge points to be mastered in the previous test paper of the students and the unfamiliarity of each knowledge point to be mastered, with the inclusion of all the knowledge points to be mastered as a prerequisite, and with the difficulty coefficient of the test paper being close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper being close to the preset number of test questions as the goal, a personalized test paper covering all the knowledge points to be mastered is generated for the students, avoiding pushing test questions based on similarity alone, improving students' ability to explore and learn other knowledge, improving the comprehensiveness of knowledge point coverage of the test questions, and improving the accuracy of free test paper composition.

[0148] (3) In the present invention, the test question allocation for each knowledge point to be mastered is determined based on the total number of preset test questions and the unfamiliarity of each knowledge point to be mastered. The system can accurately guide students to study and practice, avoiding students from blindly learning and wasting time on knowledge points that have already been mastered, thereby improving students' learning efficiency and the accuracy of free test papers.

[0149] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0150] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0151] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0152] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0153] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0154] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0155] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0156] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0157] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0160] If the 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 can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0161] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the free test paper composition method based on test scoring as described in the method embodiment is implemented.

[0162] A computer-readable storage medium provided by the present invention can implement the steps and effects of the free test paper composition method based on test scoring in the above method embodiment. To avoid repetition, the present invention will not go into details.

[0163] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0164] (1) In the present invention, the appropriate difficulty coefficient of the user is determined according to the test score of the user's previous test paper, so as to comprehensively grasp the student's current mastery of knowledge points and push test questions of appropriate difficulty so that students can start with questions of lower difficulty and learn step by step, thus avoiding students from falling into a dilemma that they cannot solve, improving students' understanding ability of knowledge points and learning interest, and improving students' learning efficiency.

[0165] (2) In the present invention, based on the knowledge points to be mastered in the previous test paper of the students and the unfamiliarity of each knowledge point to be mastered, with the inclusion of all the knowledge points to be mastered as a prerequisite, and with the difficulty coefficient of the test paper being close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper being close to the preset number of test questions as the goal, a personalized test paper covering all the knowledge points to be mastered is generated for the students, avoiding pushing test questions based on similarity alone, improving students' ability to explore and learn other knowledge, improving the comprehensiveness of knowledge point coverage of the test questions, and improving the accuracy of free test paper composition.

[0166] (3) In the present invention, the test question allocation for each knowledge point to be mastered is determined based on the total number of preset test questions and the unfamiliarity of each knowledge point to be mastered. The system can accurately guide students to study and practice, avoiding students from blindly learning and wasting time on knowledge points that have already been mastered, thereby improving students' learning efficiency and the accuracy of free test papers.

[0167] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0168] There are a few points to note:

[0169] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0170] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0171] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0172] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A free test paper composition method based on test scoring, characterized in that: include: S1: Get the test score and wrong question set of the user's last test paper; S2: Determine the appropriate difficulty coefficient for the user based on the test score of the previous test paper taken by the user; S3: Determine the user's knowledge points to be mastered and the unfamiliarity of each knowledge point to be mastered based on the set of wrong questions answered by the user in the previous test paper; S4: Obtain the total number of preset test questions set by the user; S5: Determine the number of preset test questions for each knowledge point to be mastered according to the total number of preset test questions and the unfamiliarity of each knowledge point to be mastered; S6: With the prerequisite of containing all the knowledge points to be mastered, and with the goal of the test paper difficulty coefficient being close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper being close to the preset number of test questions, test questions are extracted from the question bank for free composition to generate a test paper.

2. The free test paper composition method based on test scoring according to claim 1 is characterized in that: The method for determining the appropriate difficulty coefficient specifically includes: When the test score of the user in the previous test satisfies s≤s1, the appropriate difficulty coefficient d for the user is determined to be d a ; When the test score of the user in the previous test satisfies s1<s≤s2, the appropriate difficulty coefficient d of the user is determined to be d b ; When the test score of the user in the previous test satisfies s2<s≤s3, the appropriate difficulty coefficient d of the user is determined to be d c ; When the test score of the user's answer to the previous test paper satisfies s3 < s ≤ s4, determine that the appropriate difficulty coefficient d of the user is d e ; When the test score of the user in the previous test satisfies s>s4, the appropriate difficulty coefficient of the user is determined to be d f ; Among them, s represents the test score of the user's previous test paper, s1 represents the first score threshold, s2 represents the second score threshold, s3 represents the third score threshold, s4 represents the fourth score threshold, and d a Indicates the first level difficulty coefficient, d b Indicates the secondary difficulty coefficient, d c Indicates the level 3 difficulty coefficient, d e Indicates the difficulty coefficient of level 4, d f Indicates five levels of difficulty.

3. The free test paper composition method based on test scoring according to claim 1 is characterized in that: The method for determining the unfamiliarity of each knowledge point to be mastered is specifically as follows: m j =tanh(t j ) Among them, m j represents the unfamiliarity of the jth knowledge point to be mastered, t j represents the number of wrong questions in the wrong question set of the previous test paper that contains the jth knowledge point to be mastered, and tanh() represents the hyperbolic tangent function, which is used to convert t j Convert to a value in the range [0, 1].

4. The free test paper composition method based on test scoring according to claim 1, characterized in that: The S5 is specifically: According to the following formula, determine the preset number of test questions for each knowledge point to be mastered: Among them, a j represents the number of preset test questions for the jth knowledge point to be mastered, a represents the total number of preset test questions set by the user, and m j represents the unfamiliarity of the jth knowledge point to be mastered, and J represents the set of knowledge points to be mastered.

5. The free test paper composition method based on test scoring according to claim 1, characterized in that: The S6 specifically includes: S601: setting constraints for the free test-taking process based on the premise that all the knowledge points to be mastered are included; S602: constructing an objective function of the free test paper composition process with the goal that the test paper difficulty coefficient is close to the appropriate difficulty coefficient and the number of test questions for each knowledge point to be mastered in the test paper is close to the preset number of test questions; S603: Under the constraints of the constraints, taking the objective function as the goal, using a genetic algorithm, extracting test questions from a question bank to freely compose a test paper, and generating a test paper.

6. The free test paper composition method based on test scoring according to claim 5 is characterized in that: The constraints include: Knowledge point coverage constraint: The free test paper scheme contains all the knowledge points to be mastered; Total score constraints: Among them, sc i represents the score of the i-th test question, and I represents the set of test questions formed by the free test paper scheme; Total duration constraints: Among them, t i represents the estimated completion time of the ith test question, T min Indicates the minimum total duration, T max Indicates the maximum total duration; Discrimination Constraint: Among them, Q represents the test paper discrimination, q i represents the discrimination of the i-th test question, Q min represents the discrimination threshold; Exposure constraints: Among them, Q represents the exposure of the test paper, q i represents the exposure of the i-th question, B max Indicates the exposure threshold.

7. The free test paper composition method based on test scoring according to claim 5 is characterized in that: The objective function is specifically: Where F( ) represents the objective function, X represents the free test paper scheme, min represents minimization, a represents the total number of preset test questions set by the user, and d represents the total number of preset test questions set by the user. i represents the difficulty coefficient of the i-th test question, I represents the test question set formed by the free test paper scheme, d represents the appropriate difficulty coefficient of the user, λ1 represents the weight coefficient of the difficulty coefficient deviation term, represents the actual number of test questions for the jth knowledge point to be mastered in the free test paper scheme, a j represents the preset number of test questions for the jth knowledge point to be mastered, J represents the set of knowledge points to be mastered, and λ2 represents the weight coefficient of the test question number deviation term.

8. The free test paper composition method based on test scoring according to claim 5, characterized in that: The objective function is specifically: Where F( ) represents the objective function, X represents the free test paper scheme, min represents minimization, a represents the total number of preset test questions set by the user, and d represents the total number of preset test questions set by the user. i represents the difficulty coefficient of the i-th test question, I represents the test question set formed by the free test paper scheme, d represents the appropriate difficulty coefficient of the user, λ1 represents the weight coefficient of the difficulty coefficient deviation term, represents the actual number of test questions for the jth knowledge point to be mastered in the free test paper scheme, a j represents the number of preset test questions for the th knowledge point to be mastered, J represents the set of knowledge points to be mastered, λ2 represents the weight coefficient of the knowledge coverage deviation term, b i represents the exposure of the ith question, b represents the system preset exposure, λ3 represents the weight coefficient of the exposure deviation term, q i represents the discrimination of the i-th test question, q represents the system preset discrimination, and λ4 represents the weight coefficient of the discrimination deviation term.

9. The free test paper composition method based on test scoring according to claim 1, characterized in that: Also includes: S6: Update the user's knowledge points to be mastered according to the test score of the generated test paper.

10. A free test-taking system based on test scoring, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the free test-paper-composing method based on test scoring as described in any one of claims 1 to 9 is implemented.

Images