A test question recommendation method and apparatus

Abstract

This application provides a test question recommendation method and apparatus, relating to the field of big data technology. When executing the method, the test question answers of a target individual are first collected. Then, based on the test question answer results and a cognitive diagnostic model, the probability of the target individual correctly answering unanswered questions is predicted. Next, the difficulty of unanswered questions in the question bank for the target individual is determined based on the probability. Finally, test questions are recommended to the target individual based on the difficulty. In this way, by directly predicting the probability of a target individual correctly answering unanswered questions based on the test question answer results and a cognitive diagnostic model, the target individual can be intuitively evaluated, thereby improving the rationality and effectiveness of test question recommendations.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to a test question recommendation method and apparatus. Background Technology

[0002] To meet the learning needs of employees regarding the various knowledge and skills required for their positions, many companies have built their own learning and training platforms. These platforms offer a wealth of learning resources for employees to choose from. However, employees often do not receive effective feedback during the learning process; they lack a clear understanding of their own knowledge level and are unable to select suitable practice questions from the vast amount of resources to improve their skills in a short period of time.

[0003] In existing technologies, target individuals are assessed based on cognitive diagnostic models. These models are constructed based on the potential abilities of the target individuals and recommend test questions that meet their learning needs based on the assessment results. However, since the cognitive diagnostic models only consider the low-order, single-dimensional potential abilities of the target individuals, they suffer from inaccurate assessments and fail to improve the rationality and effectiveness of test question recommendations.

[0004] In conclusion, improving the rationality and effectiveness of test question recommendations is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, this application provides a test question recommendation method and apparatus, which aims to improve the rationality and effectiveness of test question recommendation.

[0006] Firstly, this application provides a method for recommending test questions, including:

[0007] Collect the test answers from the target personnel;

[0008] Based on the test response results and the cognitive diagnostic model, predict the probability that the target person correctly answers the unanswered test questions;

[0009] The difficulty of unanswered questions in the question bank for the target personnel is determined based on the probability.

[0010] Recommend test questions to the target group based on the stated difficulty level.

[0011] Optionally, predicting the probability that the target person correctly answers unanswered questions based on the test response results and the cognitive diagnostic model includes:

[0012] The potential abilities of the target individuals are calculated based on their answers to the test questions and the cognitive diagnostic model.

[0013] The knowledge level of the target personnel is calculated based on the potential capabilities.

[0014] The level of knowledge attained by the target personnel is calculated based on their knowledge level.

[0015] The probability of the target personnel correctly answering or not answering the questions is calculated based on their level of mastery of the test questions.

[0016] Optionally, the step of calculating the potential ability of the target individual based on the test response results and the cognitive diagnostic model includes:

[0017] Based on the test answer results and cognitive diagnostic model, the first posterior probability distribution corresponding to the potential ability of the target person is calculated according to Bayes' formula, and a first sample sequence that satisfies the first posterior probability distribution is generated.

[0018] The mean of the first sample sequence is taken as the potential ability of the target person.

[0019] Optionally, before calculating the knowledge level of the target person based on the potential ability, the method further includes:

[0020] Based on the test answer results and the cognitive diagnostic model, the second posterior probability distribution corresponding to the discrimination of knowledge points for each ability of the target personnel is calculated according to Bayes' formula, and a second sample sequence that satisfies the second posterior probability distribution is generated.

[0021] The mean of the second sample sequence is used as the distinguishing factor of the knowledge point for each ability of the target personnel.

[0022] Based on the test answer results and cognitive diagnostic model, the third posterior probability distribution corresponding to the relative difficulty of the knowledge point for each ability of the target person is calculated according to Bayes' formula, and a third sample sequence that satisfies the third posterior probability distribution is generated.

[0023] The mean of the third sample sequence is used as the relative difficulty of the knowledge point of the target person to the various abilities of the target person;

[0024] The calculation of the target person's knowledge level based on the potential ability includes:

[0025] The knowledge level of the target person is calculated based on the potential ability, the distinguishability of the knowledge points to the target person's various abilities, and the relative difficulty of the knowledge points to the target person's various abilities.

[0026] Optionally, before calculating the target person's test-taking skills based on their knowledge level, the method further includes:

[0027] Based on the test answer results and the cognitive diagnostic model, the fourth posterior probability distribution corresponding to the discrimination of the test questions for each ability of the target personnel is calculated according to Bayes' formula, and a fourth sample sequence that satisfies the fourth posterior probability distribution is generated.

[0028] The mean of the fourth sample sequence is used as the discrimination index of the test item for each ability of the target personnel;

[0029] Based on the test answer results and cognitive diagnostic model, the fifth posterior probability distribution corresponding to the relative difficulty of the test questions for the target personnel's various abilities is calculated according to Bayes' formula, and a fifth sample sequence that satisfies the fifth posterior probability distribution is generated.

[0030] The mean of the fifth sample sequence is used as the relative difficulty of the test questions for the target personnel in relation to their various abilities.

[0031] The calculation of the target person's test-taking proficiency level based on the knowledge level includes:

[0032] Based on the knowledge level, the differentiation of the test questions among the target personnel's various abilities, and the relative difficulty of the test questions among the target personnel's various abilities, the target personnel's mastery of the test questions is calculated.

[0033] Optionally, before calculating the probability of the target person correctly answering or not answering the test questions based on their level of mastery of the test questions, the method further includes:

[0034] Based on the test answer results and cognitive diagnostic model, the sixth posterior probability distribution corresponding to the probability of the target person guessing the correct answer without knowing the test questions is calculated according to Bayes' formula, and a sixth sample sequence that satisfies the sixth posterior probability distribution is generated.

[0035] The mean of the sixth sample sequence is taken as the probability that the target person can answer correctly by guessing without knowing the test questions;

[0036] Based on the test answer results and cognitive diagnostic model, the seventh posterior probability distribution corresponding to the probability of the target person making an incorrect answer due to mistake under the condition of mastering the test questions is calculated according to Bayes' formula, and a seventh sample sequence that satisfies the seventh posterior probability distribution is generated.

[0037] The mean of the seventh sample sequence is taken as the probability that the target person will answer incorrectly due to mistake, given that they have mastered the test questions.

[0038] The calculation of the probability that the target person correctly answered the questions they did not answer based on their level of mastery of the test questions includes:

[0039] Based on the target person's level of mastery of the test questions, the probability of the target person answering correctly by guessing without mastering the test questions, and the probability of the target person answering incorrectly due to mistake even when mastering the test questions, the probability of the target person answering the test questions correctly or not is calculated.

[0040] Secondly, this application provides a test question recommendation device, including:

[0041] The collection module is used to collect the test answers from the target personnel.

[0042] The prediction module is used to predict the probability that the target person correctly answers the questions that were not answered, based on the test answer results and the cognitive diagnostic model.

[0043] The determination module is used to determine the difficulty of unanswered questions in the question bank for the target personnel based on the probability.

[0044] The recommendation module is used to recommend test questions to the target users based on the difficulty level.

[0045] Optionally, the prediction module is specifically used for:

[0046] The potential abilities of the target individuals are calculated based on their answers to the test questions and the cognitive diagnostic model.

[0047] The knowledge level of the target personnel is calculated based on the potential capabilities.

[0048] The level of knowledge attained by the target personnel is calculated based on their knowledge level.

[0049] The probability of the target personnel correctly answering or not answering the questions is calculated based on their level of mastery of the test questions.

[0050] Thirdly, this application provides an apparatus comprising a memory and a processor, the memory for storing instructions or code, and the processor for executing the instructions or code to cause the apparatus to perform the test item recommendation method described in any of the preceding first aspects.

[0051] Fourthly, this application provides a computer storage medium storing code, wherein when the code is executed, a device running the code implements the test question recommendation method described in any of the first aspects above.

[0052] This application provides a test question recommendation method. When executing the method, the test question answers of target personnel are first collected. Then, based on the test question answer results and a cognitive diagnostic model, the probability of the target personnel correctly answering unanswered questions is predicted. Next, the difficulty of unanswered questions in the question bank for the target personnel is determined based on the probability. Finally, test questions are recommended to the target personnel based on the difficulty. In this way, by directly predicting the probability of the target personnel correctly answering unanswered questions based on the test question answer results and a cognitive diagnostic model, the target personnel can be directly evaluated, thereby improving the rationality and effectiveness of test question recommendations. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings used in the description of the embodiment or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 A flowchart illustrating a test question recommendation method provided in this application embodiment;

[0055] Figure 2 A flowchart illustrating another test question recommendation method provided in this application embodiment;

[0056] Figure 3 This is a schematic diagram of the structure of a cognitive diagnostic model provided in an embodiment of this application;

[0057] Figure 4 A schematic diagram of a test question recommendation device provided in an embodiment of this application;

[0058] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0059] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. This application provides a test question recommendation method and apparatus, applicable to the field of big data technology. The above are merely examples and do not limit the application areas of the methods and apparatus provided in this application.

[0060] To meet the learning needs of employees regarding the various knowledge and skills required for their positions, many companies have built their own learning and training platforms. These platforms offer a wealth of learning resources for employees to choose from. However, employees often do not receive effective feedback during the learning process; they lack a clear understanding of their own knowledge level and are unable to select suitable practice questions from the vast amount of resources to improve their skills in a short period of time.

[0061] In existing technologies, target individuals are assessed based on cognitive diagnostic models, which are constructed based on their potential abilities. Based on the assessment results, test questions that meet the learning needs of the target individuals are recommended. However, since the cognitive diagnostic models only consider the potential abilities of the target individuals, they have the disadvantage of inaccurate assessment of the target individuals and cannot improve the rationality and effectiveness of the test question recommendations.

[0062] The inventors, through research, proposed the technical solution of this application. First, they collect the test-taking results of target personnel. Then, based on the test-taking results and a cognitive diagnostic model, they predict the probability that the target personnel will correctly answer unanswered questions. Next, based on the probability, they determine the difficulty level of unanswered questions in the question bank for the target personnel. Finally, based on the difficulty level, they recommend test questions to the target personnel. In this way, by directly predicting the probability of the target personnel correctly answering unanswered questions based on the test-taking results and a cognitive diagnostic model, they can intuitively evaluate the target personnel, thereby improving the rationality and effectiveness of test question recommendations.

[0063] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application. It should be noted that, for ease of description, only the parts related to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features in the embodiments of the present application can be combined with each other.

[0064] See Figure 1 , Figure 1 A flowchart of a test question recommendation method provided in this application embodiment includes:

[0065] S101: Collect the test answers from the target personnel.

[0066] The target group consists of existing learners, and the task is to collect their answers to the questions in the question bank.

[0067] S102: Based on the test answer results and the cognitive diagnostic model, predict the probability that the target person correctly answers the unanswered test questions.

[0068] The test results are input into a cognitive diagnostic model to predict the probability that a target individual will answer questions correctly or not. The cognitive diagnostic model is a mathematical model that describes the relationship between a learner's knowledge level, test item characteristics, and test answer results. Using a matching solution algorithm, the learner's knowledge level and test item characteristics can be deduced from the test answer results and the model structure.

[0069] S103: Determine the difficulty of unanswered questions in the question bank for the target personnel based on the stated probability.

[0070] Let (1 - the probability of the target person answering the question correctly or not) be taken as the difficulty of the question for the target person. The lower the difficulty, the higher the probability of answering correctly and the simpler the question is for the target person; the lower the difficulty, the lower the probability of answering correctly and the more difficult the question is for the target person.

[0071] S104: Recommend test questions to the target personnel based on the difficulty level.

[0072] Target personnel can choose questions of different difficulty levels to practice as needed. The lower the difficulty, the easier the question is for the target personnel to answer correctly, and such questions are suitable for consolidation and improvement. The higher the difficulty, the more difficult the target personnel are to answer correctly, and such questions are suitable for challenge and training.

[0073] This application provides a test question recommendation method. When executing the method, the test question answers of a target individual are first collected. Then, based on the test question answer results and a cognitive diagnostic model, the probability of the target individual correctly answering unanswered questions is predicted. Next, the difficulty of unanswered questions in the question bank for the target individual is determined based on the probability. Finally, test questions are recommended to the target individual based on the difficulty level. In this way, by directly predicting the probability of a target individual correctly answering unanswered questions based on the test question answer results and a cognitive diagnostic model, the target individual can be intuitively evaluated, thereby improving the rationality and effectiveness of test question recommendations.

[0074] See Figure 2 The figure is a flowchart of another test question recommendation method provided in an embodiment of this application, including:

[0075] S201: Collect the test answers from the target personnel.

[0076] The matrix of the target personnel's answers to the questions in the question bank is denoted as R = [r1, ... r2]. I ] T r i =[r i1 ,...riJ ]. Where r ij This represents the answer given by target person i to question j. ij =0 indicates that target person i answered question j incorrectly. ij =1 indicates that target person i correctly answered question j, r ij =-1 indicates that target person i has not answered question j.

[0077] S202: Calculate the potential abilities of the target personnel based on the test answers and the cognitive diagnostic model.

[0078] Potential abilities are the inherent abilities of the target individual, including memory, intelligence, etc.

[0079] Based on the test answer results and cognitive diagnostic model, the first posterior probability distribution corresponding to the potential ability of the target person is calculated according to Bayes' formula, and a first sample sequence that satisfies the first posterior probability distribution is generated.

[0080] The mean of the first sample sequence is taken as the potential ability of the target person.

[0081] S203: Calculate the knowledge level of the target personnel based on the potential capabilities.

[0082] Each knowledge point also has its own characteristics, such as the difficulty of the knowledge point and the degree to which the knowledge point distinguishes different abilities. For example, some knowledge points focus on testing the target person's memory, while others focus on testing the target person's logical thinking ability. These potential abilities of the target person, together with some characteristics of the knowledge point, determine the level of the target person's mastery of different knowledge points, that is, the target person's knowledge level.

[0083] Based on the test answer results and the cognitive diagnostic model, the second posterior probability distribution corresponding to the discrimination of knowledge points for each ability of the target personnel is calculated according to Bayes' formula, and a second sample sequence that satisfies the second posterior probability distribution is generated.

[0084] The mean of the second sample sequence is used as the distinguishing factor of the knowledge point for each ability of the target personnel.

[0085] Based on the test answer results and cognitive diagnostic model, the third posterior probability distribution corresponding to the relative difficulty of the knowledge point for each ability of the target person is calculated according to Bayes' formula, and a third sample sequence that satisfies the third posterior probability distribution is generated.

[0086] The mean of the third sample sequence is used as the relative difficulty of the knowledge point of the target person to the various abilities of the target person;

[0087] The calculation of the target person's knowledge level based on the potential ability includes:

[0088] Based on the potential abilities, the distinguishing power of the knowledge points for each of the target personnel's abilities, and the relative difficulty of the knowledge points for each of the target personnel's abilities, the knowledge level of the target personnel is calculated. The specific calculation method is as follows:

[0089]

[0090] Where x1 represents the target person's multidimensional potential ability, x2 represents the target person's knowledge level, w1 represents the distinguishing power of knowledge points on the target person's various abilities, b1 represents the relative difficulty of knowledge points on the target person's various abilities, and sigmoid() represents the neural network activation function.

[0091] S204: Calculate the target personnel's level of mastery of the test questions based on the stated knowledge level.

[0092] Based on the test answer results and the cognitive diagnostic model, the fourth posterior probability distribution corresponding to the discrimination of the test questions for each ability of the target personnel is calculated according to Bayes' formula, and a fourth sample sequence that satisfies the fourth posterior probability distribution is generated.

[0093] The mean of the fourth sample sequence is used as the discrimination index of the test item for each ability of the target personnel;

[0094] Based on the test answer results and cognitive diagnostic model, the fifth posterior probability distribution corresponding to the relative difficulty of the test questions for the target personnel's various abilities is calculated according to Bayes' formula, and a fifth sample sequence that satisfies the fifth posterior probability distribution is generated.

[0095] The mean of the fifth sample sequence is used as the relative difficulty of the test questions for the target personnel in relation to their various abilities.

[0096] Based on the stated knowledge level, the differentiation of the test questions among the target personnel's various abilities, and the relative difficulty of the test questions among the target personnel's various abilities, the target personnel's mastery of the test questions is calculated. The specific calculation method is as follows:

[0097] x2' = norm(x2)

[0098]

[0099] Where x3 represents the target personnel's mastery of the test questions, w2 represents the discrimination of the test questions against the target personnel's various knowledge levels, b2 represents the relative difficulty of the test questions against the target personnel's various knowledge levels, sigmoid() represents the neural network activation function, and norm() represents the standardization function.

[0100] S205: Calculate the probability that the target person correctly answers the questions they did not answer based on their level of mastery of the test questions.

[0101] Even if the target personnel have a complete grasp of the test questions, they may still answer incorrectly due to a mistake; even if they have no grasp of the questions, they may still answer correctly due to a guess.

[0102] Based on the test answer results and cognitive diagnostic model, the sixth posterior probability distribution corresponding to the probability of the target person guessing the correct answer without knowing the test questions is calculated according to Bayes' formula, and a sixth sample sequence that satisfies the sixth posterior probability distribution is generated.

[0103] The mean of the sixth sample sequence is taken as the probability that the target person can answer correctly by guessing without knowing the test questions;

[0104] Based on the test answer results and cognitive diagnostic model, the seventh posterior probability distribution corresponding to the probability of the target person making an incorrect answer due to mistake under the condition of mastering the test questions is calculated according to Bayes' formula, and a seventh sample sequence that satisfies the seventh posterior probability distribution is generated.

[0105] The mean of the seventh sample sequence is taken as the probability that the target person will answer incorrectly due to mistake, given that they have mastered the test questions.

[0106] Based on the target individual's level of mastery of the test questions, the probability of correctly answering by guessing without mastering the test questions, and the probability of incorrectly answering due to mistake even with mastery of the test questions, the probability of the target individual correctly answering or not answering the test questions is calculated. The specific calculation method is as follows:

[0107]

[0108] Where w3 represents the probability that the target person answers correctly by guessing without knowing the test questions, and b3 represents the probability that the target person answers incorrectly due to mistake, even if they know the test questions. P(r ij =1|·) represents the probability that target person i answers question j correctly.

[0109] The implementation methods of steps S206 and S207 are the same as those of steps S103 and S104, and will not be repeated here.

[0110] The above are some specific implementations of the test question recommendation method provided in the embodiments of this application. Based on this, this application also provides a corresponding device. The device provided in the embodiments of this application will be described below from the perspective of functional modularity.

[0111] Figure 3 The schematic diagram of a cognitive diagnostic model provided in this application embodiment includes a four-layer model structure, as shown in the figure, where x1 represents the potential ability layer, x2 represents the knowledge level layer, x3 represents the test item mastery level layer, and x4 represents the test item answer result layer.

[0112] The relationship between potential ability level x1 and knowledge level level x2 is as follows:

[0113]

[0114] Where w1 represents the degree to which the knowledge point distinguishes the target personnel's various abilities, b1 represents the relative difficulty of the knowledge point in relation to the target personnel's various abilities, and sigmoid() represents the neural network activation function.

[0115] The relationship between knowledge level layer x2 and test item mastery level layer x3 is as follows:

[0116] x2' = norm(x2)

[0117]

[0118] Where w2 represents the discrimination of the test questions against the target personnel's knowledge levels, b2 represents the relative difficulty of the test questions against the target personnel's knowledge levels, sigmoid() represents the neural network activation function, and norm() represents the standardization function.

[0119] x4 represents the test answer result layer, where P(r ij =1|·) represents the probability that target person i answers question j correctly. The relationship between this layer and the question mastery level layer x3 is as follows:

[0120]

[0121] Where w3 represents the probability that the target person answers correctly by guessing without knowing the test questions, and b3 represents the probability that the target person answers incorrectly due to mistake, even if they know the test questions.

[0122] See Figure 4 The present application provides a schematic diagram of the structure of a test question recommendation device, comprising:

[0123] The collection module 410 is used to collect the test answers of the target personnel;

[0124] The prediction module 420 is used to predict the probability that the target person correctly answers the questions that were not answered based on the test answer results and the cognitive diagnostic model;

[0125] The determination module 430 is used to determine the difficulty of unanswered questions in the question bank for the target personnel based on the probability.

[0126] The recommendation module 440 is used to recommend test questions to the target personnel based on the difficulty level.

[0127] Optionally, the prediction module 420 is specifically used for:

[0128] The potential abilities of the target personnel are calculated based on the test responses and the cognitive diagnostic model.

[0129] The knowledge level of the target personnel is calculated based on the potential capabilities.

[0130] The level of knowledge attained by the target personnel is calculated based on their knowledge level.

[0131] The probability of the target personnel correctly answering or not answering the questions is calculated based on their level of mastery of the test questions.

[0132] Optionally, the prediction module 420 is specifically used for:

[0133] Based on the test answer results and cognitive diagnostic model, the first posterior probability distribution corresponding to the potential ability of the target person is calculated according to Bayes' formula, and a first sample sequence that satisfies the first posterior probability distribution is generated.

[0134] The mean of the first sample sequence is taken as the potential ability of the target person.

[0135] Optionally, the device 400 further includes:

[0136] The first parameter determination module is used to calculate the second posterior probability distribution corresponding to the discrimination of knowledge points for each ability of the target personnel based on the test answer results and the cognitive diagnostic model according to Bayes' formula, and generate a second sample sequence that satisfies the second posterior probability distribution; the mean of the second sample sequence is used as the discrimination of the knowledge points for each ability of the target personnel.

[0137] The second parameter determination module is used to calculate the third posterior probability distribution corresponding to the relative difficulty of the knowledge point for each ability of the target person based on the test answer results and the cognitive diagnostic model according to Bayes' formula, and generate a third sample sequence that satisfies the third posterior probability distribution; the mean of the third sample sequence is used as the relative difficulty of the knowledge point for each ability of the target person.

[0138] The prediction module 420 is specifically used for:

[0139] The knowledge level of the target person is calculated based on the potential ability, the distinguishability of the knowledge points to the target person's various abilities, and the relative difficulty of the knowledge points to the target person's various abilities.

[0140] Optionally, the device 400 further includes:

[0141] The third parameter determination module is used to calculate the fourth posterior probability distribution corresponding to the discrimination of the test item for each ability of the target personnel based on the test item answer results and the cognitive diagnostic model according to Bayes' formula, and generate a fourth sample sequence that satisfies the fourth posterior probability distribution; the mean of the fourth sample sequence is used as the discrimination of the test item for each ability of the target personnel.

[0142] The fourth parameter determination module is used to calculate the fifth posterior probability distribution corresponding to the relative difficulty of the test question for each ability of the target person based on the test question answering results and the cognitive diagnostic model according to Bayes' formula, and generate a fifth sample sequence that satisfies the fifth posterior probability distribution; the mean of the fifth sample sequence is used as the relative difficulty of the test question for each ability of the target person.

[0143] The prediction module 420 is specifically used for:

[0144] Based on the knowledge level, the differentiation of the test questions among the target personnel's various abilities, and the relative difficulty of the test questions among the target personnel's various abilities, the target personnel's mastery of the test questions is calculated.

[0145] Optionally, the device 400 further includes:

[0146] The fifth parameter determination module is used to calculate the sixth posterior probability distribution corresponding to the probability that the target person answers correctly by guessing without knowing the test questions, based on the test question answering results and the cognitive diagnostic model, according to Bayes' formula, and generate a sixth sample sequence that satisfies the sixth posterior probability distribution; the mean of the sixth sample sequence is used as the probability that the target person answers correctly by guessing without knowing the test questions.

[0147] The sixth parameter determination module is used to calculate the seventh posterior probability distribution corresponding to the probability that the target person makes an incorrect answer due to mistake under the condition that they have mastered the test questions, based on the test question answering results and the cognitive diagnostic model, according to Bayes' formula, and generate a seventh sample sequence that satisfies the seventh posterior probability distribution; the mean of the seventh sample sequence is used as the probability that the target person makes an incorrect answer due to mistake under the condition that they have mastered the test questions.

[0148] The prediction module 420 is specifically used for:

[0149] Based on the target person's level of mastery of the test questions, the probability of the target person answering correctly by guessing without mastering the test questions, and the probability of the target person answering incorrectly due to mistake even when mastering the test questions, the probability of the target person answering the test questions correctly or not is calculated.

[0150] like Figure 5 As shown, the computer device 01 is represented in the form of a general-purpose computing device. The components of the computer device 01 may include, but are not limited to: one or more processors or processing units 03, system memory 08, and bus 04 connecting different system components (including system memory 08 and processing unit 03).

[0151] Bus 04 represents one or more of several bus architectures, including memory buses or memory controllers, peripheral buses, graphics acceleration ports, processors, or local buses using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0152] Computer device 01 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 01, including volatile and non-volatile media, removable and non-removable media.

[0153] System memory 08 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 09 and / or cache memory 10. Computer device 01 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 11 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 5 Not shown; usually referred to as a "hard drive"). Although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 04 via one or more data media interfaces. Memory 08 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0154] A program / utility 12 having a set (at least one) of program modules 13 may be stored in, for example, memory 08. Such program modules 13 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 13 typically perform the functions and / or methods described in the embodiments of the present invention.

[0155] Computer device 01 can also communicate with one or more external devices 02 (e.g., keyboard, pointing device, display 07, etc.), and with one or more devices that enable a user to interact with the computer device 01, and / or with any device that enables the computer device 01 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 06. Furthermore, computer device 01 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) through network adapter 05. Figure 5 As shown, network adapter 05 communicates with other modules of computer device 01 via bus 04. It should be understood that, although... Figure 5 As not shown in the diagram, it can be used in conjunction with computer device 01 with other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0156] The processor unit 03 executes various functional applications and data processing by running programs stored in the system memory 08, such as implementing a method for determining the standard name of an inspection item provided in an embodiment of this application.

[0157] In the embodiments of this application, the terms "first" and "second" (if they exist) are used only as name identifiers and do not represent the order of first and second.

[0158] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the methods of the above embodiments can be implemented by means of software plus a general-purpose hardware platform. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as a read-only memory (ROM) / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network communication device such as a router) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0159] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0160] The above description is merely an exemplary implementation of this application and is not intended to limit the scope of protection of this application.

Claims

1. A test question recommendation method characterized by comprising: include: Collect the test answers from the target personnel; The potential abilities of the target individuals are calculated based on their answers to the test questions and the cognitive diagnostic model. Based on the potential abilities, the distinguishing power of the knowledge points for each of the target personnel's abilities, and the relative difficulty of the knowledge points for each of the target personnel's abilities, the target personnel's knowledge level is calculated: ； in, This indicates the potential capability. This indicates the knowledge level of the target personnel. This indicates the degree to which the knowledge point distinguishes the various abilities of the target personnel. This indicates the relative difficulty of the knowledge point for each of the target personnel's various abilities; Based on the stated knowledge level, the differentiation of the test questions among the target personnel's various abilities, and the relative difficulty of the test questions among the target personnel's various abilities, the target personnel's level of mastery of the test questions is calculated: ； ； in, This indicates the level of mastery of the test questions by the target personnel. This indicates the degree to which the test questions differentiate between the target personnel and their levels of knowledge in various areas. This indicates the relative difficulty of the test questions for the target personnel's level of knowledge in various areas; Based on the target individual's level of understanding of the test questions, the probability of correctly answering by guessing without understanding the test questions, and the probability of incorrectly answering due to mistake even when understanding the test questions, the probability of the target individual correctly answering or not answering the test questions is calculated as follows: ； in This represents the probability that the target person will answer correctly by guessing without knowing the test questions. This represents the probability that the target individual, given their knowledge of the test questions, will answer incorrectly due to a mistake. Indicates target personnel Answer the questions correctly The probability of; The difficulty of the unanswered questions in the question bank for the target personnel is determined based on the probability that the target personnel answer the unanswered questions correctly. Recommend test questions to the target group based on the stated difficulty level.

2. The method of claim 1, wherein, The calculation of the target individual's potential abilities based on the test responses and the cognitive diagnostic model includes: Based on the test answer results and cognitive diagnostic model, the first posterior probability distribution corresponding to the potential ability of the target person is calculated according to Bayes' formula, and a first sample sequence that satisfies the first posterior probability distribution is generated. The mean of the first sample sequence is taken as the potential ability of the target person.

3. The method of claim 1, wherein, Before calculating the target person's knowledge level based on the potential abilities, the distinguishing power of the knowledge points for each of the target person's abilities, and the relative difficulty of the knowledge points for each of the target person's abilities, the method further includes: Based on the test answer results and the cognitive diagnostic model, the second posterior probability distribution corresponding to the discrimination of the knowledge point for each ability of the target person is calculated according to Bayes' formula, and a second sample sequence that satisfies the second posterior probability distribution is generated. The mean of the second sample sequence is used as the distinguishing factor of the knowledge point for each ability of the target personnel. Based on the test answer results and the cognitive diagnostic model, the third posterior probability distribution corresponding to the relative difficulty of the knowledge point with respect to the various abilities of the target personnel is calculated according to the Bayesian formula, and a third sample sequence that satisfies the third posterior probability distribution is generated. The mean of the third sample sequence is used as the relative difficulty of the knowledge point of the target person to the various abilities of the target person.

4. The method of claim 1, wherein, Before calculating the target person's level of test mastery based on the knowledge level, the discrimination of the test questions against the target person's various abilities, and the relative difficulty of the test questions against the target person's various abilities, the method further includes: Based on the test answer results and the cognitive diagnostic model, the fourth posterior probability distribution corresponding to the discrimination of the test questions for each ability of the target personnel is calculated according to Bayes' formula, and a fourth sample sequence that satisfies the fourth posterior probability distribution is generated. The mean of the fourth sample sequence is used as the discrimination index of the test questions for the various abilities of the target personnel; Based on the test answer results and the cognitive diagnostic model, the fifth posterior probability distribution corresponding to the relative difficulty of the test questions for each ability of the target personnel is calculated according to the Bayesian formula, and a fifth sample sequence that satisfies the fifth posterior probability distribution is generated. The mean of the fifth sample sequence is used as the relative difficulty of the test questions for the target personnel in relation to their various abilities.

5. The method of claim 1, wherein, Before calculating the probability of the target person correctly answering or not answering a question based on their level of mastery of the test questions, the probability of the target person answering correctly by guessing without mastering the test questions, and the probability of the target person answering incorrectly due to mistake while mastering the test questions, the method further includes: Based on the test answer results and cognitive diagnostic model, the sixth posterior probability distribution corresponding to the probability of the target person guessing the correct answer without knowing the test questions is calculated according to Bayes' formula, and a sixth sample sequence that satisfies the sixth posterior probability distribution is generated. The mean of the sixth sample sequence is taken as the probability that the target person can answer correctly by guessing without knowing the test questions; Based on the test answer results and the cognitive diagnostic model, the seventh posterior probability distribution corresponding to the probability of the target person making an incorrect answer due to mistake under the condition of mastering the test questions is calculated according to the Bayes formula, and a seventh sample sequence that satisfies the seventh posterior probability distribution is generated. The mean of the seventh sample sequence is taken as the probability that the target person will make a wrong answer due to mistake, given that they have mastered the test questions.

6. A test question recommendation device characterized by comprising: include: The collection module is used to collect the test answers from the target personnel. The prediction module is used to calculate the potential abilities of the target individual based on the test response results and the cognitive diagnostic model. Based on the potential abilities, the distinguishing power of the knowledge points for each of the target personnel's abilities, and the relative difficulty of the knowledge points for each of the target personnel's abilities, the target personnel's knowledge level is calculated: ； in, This indicates the potential capability. This indicates the knowledge level of the target personnel. This indicates the degree to which the knowledge point distinguishes the various abilities of the target personnel. This indicates the relative difficulty of the knowledge point for each of the target personnel's various abilities; Based on the stated knowledge level, the differentiation of the test questions among the target personnel's various abilities, and the relative difficulty of the test questions among the target personnel's various abilities, the target personnel's level of mastery of the test questions is calculated: ； ； in, This indicates the level of mastery of the test questions by the target personnel. This indicates the degree to which the test questions differentiate between the target personnel and their levels of knowledge in various areas. This indicates the relative difficulty of the test questions for the target personnel's level of knowledge in various areas; Based on the target individual's level of understanding of the test questions, the probability of correctly answering by guessing without understanding the test questions, and the probability of incorrectly answering due to mistake even when understanding the test questions, the probability of the target individual correctly answering or not answering the test questions is calculated as follows: ； in This represents the probability that the target person will answer correctly by guessing without knowing the test questions. This represents the probability that the target individual, given their knowledge of the test questions, will answer incorrectly due to a mistake. Indicates target personnel Answer the questions correctly The probability of; The determination module is used to determine the difficulty of unanswered questions in the question bank for the target personnel based on the probability that the target personnel answer the unanswered questions correctly. The recommendation module is used to recommend test questions to the target users based on the difficulty level.

7. A computer device, comprising: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the test item recommendation method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform the test item recommendation method as described in any one of claims 1-5.

Images