Test paper compiling method and device, electronic equipment and storage medium

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for generating test papers, relating to the field of artificial intelligence technology. The method includes: acquiring information about the test-takers of a target test paper and information about reference test papers of the same type as the target test paper; constructing multiple candidate test papers based on the reference test paper information; calculating the fitness of each of the multiple candidate test papers according to the test-takers' information, whereby the fitness indicates the degree of matching between the candidate test papers and the test-takers' information; and determining at least one target test paper from the multiple candidate test papers based on their fitness. Embodiments of this disclosure can, by constructing multiple candidate test papers, calculating their fitness, and adjusting the content of the candidate test papers according to their fitness, ultimately obtain a target test paper suitable for the test-takers.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to a method, apparatus, electronic device, and storage medium for creating test papers. Background Technology

[0002] As a direct means of assessing students' abilities and an important tool for talent selection, examinations occupy an extremely important position in the field of education. The compilation of examination papers, or test paper assembly, is a core factor affecting the effectiveness of examinations in assessment and selection.

[0003] In related technologies, teaching and research teachers often need to evaluate factors such as the difficulty of the test questions, the scope of knowledge tested, and the level of the test takers based on their practical experience, and then select a number of questions from a set of alternative test questions or a question bank to form a test paper. Therefore, the test paper compilation method of related technologies is time-consuming and labor-intensive, and is also affected by the subjectivity of teaching and research teachers, which places high demands on their professional level and teaching experience. Summary of the Invention

[0004] In view of this, this disclosure relates to the field of artificial intelligence technology, and more specifically, to a method, apparatus, computer device, and storage medium for creating test papers.

[0005] Firstly, a test paper generation method is provided, comprising: obtaining information on the examinees of the target test paper and information on reference test papers of the same type as the target test paper; constructing multiple candidate test papers based on the reference test paper information; calculating the fitness of the multiple candidate test papers according to the examinee information, wherein the fitness is used to indicate the degree of matching between the candidate test papers and the examinee information; and determining at least one target test paper from the multiple candidate test papers based on the fitness of the multiple candidate test papers.

[0006] In some embodiments, determining at least one target test paper from multiple candidate test papers based on their fitness includes: selecting multiple undetermined test papers from multiple candidate test papers based on their fitness; randomly combining the questions in the multiple undetermined test papers to obtain new multiple candidate test papers; repeating the above steps until the fitness of the multiple candidate test papers meets a preset condition; and determining at least one target test paper from the multiple candidate test papers.

[0007] In some embodiments, the fitness of multiple candidate test papers is calculated based on the assessment subject information, including: for each candidate test paper among the multiple candidate test papers, predicting the probability of answering each question in the candidate test paper based on the assessment subject information; and calculating the fitness of the candidate test paper based on the assessment subject information and the probability of answering each question in the candidate test paper.

[0008] In some embodiments, the fitness of a candidate test paper is calculated based on the assessment subject information and the probability of answering each question in the candidate test paper, including: calculating a first discrete entropy based on the probability of answering each question in the candidate test paper; calculating a second discrete entropy based on the assessment subject information and the probability of answering each question in the candidate test paper; and calculating the fitness of the candidate test paper based on the first discrete entropy and the second discrete entropy.

[0009] In some embodiments, after calculating the fitness of the candidate test paper based on the assessment subject information and the probability of answering each question in the candidate test paper, the method further includes: obtaining the difficulty configuration information of the target test paper, the difficulty configuration information being used to indicate the expected assessment result of the target test paper; and adjusting the fitness of the candidate test paper based on the difficulty configuration information.

[0010] In some embodiments, the difficulty configuration information includes expected score distribution information; adjusting the fitness of candidate test papers based on the difficulty configuration information includes: calculating the relative entropy between the expected score distribution information and the expected score distribution of candidate test papers, wherein the expected score distribution of candidate test papers is calculated based on the probability of answering each question correctly in the candidate test papers; and adjusting the fitness of candidate test papers based on the relative entropy.

[0011] In some embodiments, after randomly combining the questions from multiple candidate test papers to obtain multiple new candidate test papers, the method further includes: replacing the questions in the multiple candidate test papers with similar questions, wherein the similar questions are obtained by matching through a preset similar question bank.

[0012] Secondly, a test paper generation device is provided, comprising: an acquisition module for acquiring assessment subject information of a target test paper and reference test paper information of the same type as the target test paper; a construction module for constructing multiple candidate test papers based on the reference test paper information; a calculation module for calculating the fitness of the multiple candidate test papers according to the assessment subject information, wherein the fitness is used to indicate the degree of matching between the candidate test papers and the assessment subject information; and a selection module for determining at least one target test paper from the multiple candidate test papers based on the fitness of the multiple candidate test papers.

[0013] Thirdly, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of the first aspect by executing the executable instructions.

[0014] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method of the first aspect described above.

[0015] The test paper assembly method provided in this disclosure involves obtaining information about the test takers of the target test paper and information about reference test papers of the same type as the target test paper; constructing multiple candidate test papers based on the reference test paper information; calculating the fitness of each candidate test paper according to the test taker information, whereby the fitness indicates the degree of matching between the candidate test papers and the test taker information; and determining at least one target test paper from the multiple candidate test papers based on their fitness. This disclosure dynamically adjusts the test paper questions based on the fitness of the multiple candidate test papers to complete the test paper assembly and obtain a target test paper suitable for the test takers. Attached Figure Description

[0016] Figure 1 A schematic diagram of the system architecture of a volume creation method according to an embodiment of this disclosure is shown.

[0017] Figure 2 The diagram shows a flowchart of a document assembly method according to an embodiment of this disclosure.

[0018] Figure 3 This illustration shows a flowchart of how the fitness of multiple candidate test papers is calculated based on the information of the test subjects in an embodiment of this disclosure.

[0019] Figure 4 This illustration shows a flowchart of a process for determining at least one target test paper from multiple candidate test papers based on the fitness of multiple candidate test papers in an embodiment of this disclosure.

[0020] Figure 5 A schematic diagram of a roll-up device according to an embodiment of this disclosure is shown.

[0021] Figure 6 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0022] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0023] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0024] As one of the educational evaluation indicators, examinations play a particularly important role in the entire teaching process and its outcomes. A well-designed and comprehensive examination paper can provide timely and accurate feedback on teaching results, offer more meaningful guidance strategies, and optimize the entire teaching process. In the process of compiling examination papers, it is often necessary to weigh various factors, including the overall difficulty and difficulty level of the paper, its ability to differentiate between test takers, the relevance of the questions to the scope of knowledge being tested, and the stability of the examination results.

[0025] In this approach, teaching and research teachers need to evaluate the above factors from multiple perspectives based on their practical experience, and then select several questions from the pool of candidate questions to form an exam paper. However, this method is time-consuming and labor-intensive, relies on the subjective judgment of teaching and research teachers, and places high demands on their professional level and teaching experience.

[0026] In view of this, this disclosure provides a test paper generation method, which involves obtaining information about the target test paper's examinees and reference test papers of the same type as the target test paper; constructing multiple candidate test papers based on the reference test paper information; calculating the fitness of each candidate test paper according to the examinee information, where fitness indicates the degree of matching between the candidate test papers and the examinee information; and determining at least one target test paper from the multiple candidate test papers based on their fitness. Therefore, embodiments of this disclosure can generate test papers suitable for the examinees and achieving good assessment results based on the examinee's level, the difficulty of the questions, and the scope of knowledge tested.

[0027] This disclosure provides a method, apparatus, electronic device, and storage medium for creating volumes. Specifically, the volume-creating apparatus can be integrated into an electronic device, such as a terminal or server.

[0028] It is understood that the volume assembly method of this embodiment can be executed on a terminal, on a server, or jointly by a terminal and a server. The above examples should not be construed as limiting this disclosure.

[0029] Figure 1 An exemplary system architecture diagram is shown that can be applied to the volume-compilation method or volume-compilation apparatus in the embodiments of this disclosure.

[0030] like Figure 1 As shown, the system architecture 100 includes a terminal 101 and a server 102. The terminal 101 and the server 102 are connected via a network, such as a wired or wireless network, wherein the volume-compilation device can be integrated into the server.

[0031] Server 102 can be used to obtain the assessment object information of the target test paper and the reference test paper information of the same type as the target test paper; construct multiple candidate test papers based on the reference test paper information; calculate the fitness of multiple candidate test papers according to the assessment object information, and the fitness is used to indicate the degree of matching between the candidate test papers and the assessment object information; and determine at least one target test paper from the multiple candidate test papers based on the fitness of the multiple candidate test papers.

[0032] Server 102 can be a single server, a server cluster composed of multiple servers, or a cloud server. For example, a server can be an interoperability server between multiple heterogeneous systems, a backend server, an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, and big data and artificial intelligence platforms, etc. As in the speech synthesis method or apparatus disclosed in this disclosure, multiple servers can form a blockchain, and the server is a node on the blockchain.

[0033] Terminal 101 can send the target test paper's examinee information and reference test paper information of the same type as the target test paper to server 102, or receive the target test paper generated by server 102. Terminal 101 may include a mobile phone, smart TV, tablet computer, laptop computer, or personal computer (PC), etc. A client can also be set on terminal 101, which can be an application client or a browser client, etc.

[0034] Those skilled in the art will know that Figure 1 The number of terminals and servers shown is merely illustrative. Depending on actual needs, there may be any number of terminals and servers, and this disclosure does not impose any limitation on this.

[0035] The following will describe the exemplary implementation method in detail with reference to the accompanying drawings and embodiments.

[0036] First, this disclosure provides a method for creating a volume, which can be executed by any electronic device with computing power.

[0037] Figure 2 This diagram illustrates a flow chart of a document compilation method according to an embodiment of the present disclosure, as shown below. Figure 2 As shown, the documented method for creating a file includes the following steps.

[0038] S201, Obtain the assessment object information of the target test paper and the reference test paper information of the same type as the target test paper.

[0039] In some embodiments, the assessment subject information of the target test paper refers to all factors related to the assessment subject's life and learning, including the assessment subject's learning attitude, learning foundation, learning habits, learning ability, interests, family environment, age characteristics, and psychological characteristics. For example, the assessment subject's learning foundation can be obtained by analyzing their usual homework, exam, and other answer data. Reference test paper information of the same type as the target test paper includes the question types and the scope of knowledge to be tested. For example, the question types can be multiple choice, true / false, or short answer questions, and the scope of knowledge to be tested can be analytic geometry or classical poetry recitation.

[0040] S202, Based on the reference test paper information, construct multiple candidate test papers.

[0041] In some embodiments, there is a large amount of pre-set test question information, including the question stem, answer, knowledge point information, explanation, etc. This information is vectorized using natural language processing methods and stored in a test question bank.

[0042] The reference test paper information is processed using natural language processing methods. Based on vector retrieval technology, multiple similar questions that are similar to each question in the reference test paper are retrieved from the question bank, and multiple candidate test papers are constructed based on the similar questions.

[0043] S203, calculate the fitness of multiple candidate test papers based on the information of the test subjects.

[0044] Specifically, the fitness of a candidate test paper represents the degree of matching between the candidate test paper and the information of the test takers, reflecting the ability of the candidate test paper to meet the needs of the test creator. A candidate test paper with higher fitness is more suitable for the test creator's needs. For example, for a final exam paper, the test creator needs to construct a test paper with high reliability, high discrimination, and moderate difficulty. Test paper reliability represents the consistency and stability of the test takers' scores when repeated testing with parallel test papers; discrimination represents the difference in average score rate between high-ability and low-ability test takers on the questions, reflecting the ability of the questions to differentiate between the test takers; difficulty refers to the level of difficulty of the questions.

[0045] In some embodiments, such as Figure 3 As shown, calculating the fitness of multiple candidate test papers based on the information of the test subjects includes the following steps.

[0046] S2031, For each of the multiple candidate test papers, based on the information of the examinee, predict the probability of answering each question correctly in the candidate test paper.

[0047] In some embodiments, each candidate test paper contains n questions, and each question has the same score, denoted as z1,…,z1. n There are m assessment subjects, whose assessment subjects are θ1,…,θ m .

[0048] A pre-trained score prediction engine f can predict scores based on the assessment objects θ1,…,θ2. m Information on the assessment subjects, predicting θ for each assessment subject. i In each question z j The probability of answering correctly is f(θ) i ,z j ), that is, the assessment object θ i Answered the question correctly. j The probability is f(θ) i ,z j Here, i and j are both positive integers, representing the index of the assessment subject and the question, respectively. For example, the score prediction engine f could be knowledge tracking, learning profiling, cognitive diagnosis, etc.

[0049] S2032, calculate the fitness of the candidate test paper based on the information of the test subjects and the probability of answering each question correctly in the candidate test paper.

[0050] In some embodiments, the correct answer probability f(θ) can be used. i ,z j ) Calculate the assessment target θ i The probability p(θ) of answering s questions correctly on this candidate test paper i The calculation process for ,s) is as follows:

[0051]

[0052] in The set of indices representing the question numbers. This represents s random questions out of n questions. Representing the topic z j For one of the s questions, Representing the topic z j Let be one of the problems other than s problems. Clearly, 0 ≤ s ≤ n, and

[0053] Furthermore, the fitness of candidate test papers can be calculated based on relevant information theory.

[0054] In some embodiments, a first discrete entropy H(Y) is first calculated based on the information of the examinee, where Y represents the exam result, and the first discrete entropy is used to represent the degree of dispersion of the examinee's exam score, corresponding to the discrimination of the candidate test paper. The calculation process is as follows:

[0055]

[0056] Discrete entropy p is a discrete probability distribution (p0,…,p) n ),and

[0057] Then, the second discrete entropy H(Y|X) is calculated based on the probability of answering each question correctly in the candidate test paper, where X represents the level of the examinee. The second discrete entropy is essentially conditional entropy, used to represent the uncertainty of the test result given the level of the examinee. The calculation process is as follows:

[0058]

[0059] Based on the first and second discrete entropies, the fitness G1({z1,…,z) of the candidate test papers can be calculated. n},{θ1,…,θ m The calculation process is as follows:

[0060] G1({z1,…,z n},{θ1,…,θ m})=I(X;Y)=H(Y)-H(Y|X)

[0061] Where I(X;Y) represents the mutual information between the assessment level X and the examination result Y. Mutual information represents the amount of information contained in one random variable about another, or the reduction in uncertainty of one random variable due to the knowledge of another random variable. Therefore, mutual information I(X;Y) can represent the amount of uncertainty that the examination result Y eliminates in relation to the assessment level X.

[0062] In some embodiments, the difficulty configuration information of the target test paper can also be obtained, and the fitness of the candidate test papers can be adjusted according to the difficulty configuration information of the target test paper. The difficulty configuration information of the target test paper is used to indicate the expected assessment result of the target test paper; for example, it may be a uniform distribution of question difficulty or maximized discrimination.

[0063] In some embodiments, the difficulty configuration information includes expected score distribution information. in Let represent the probability of answering n questions correctly, and let represent the expected score distribution information, which represents the score distribution that the test creator expects for this exam. Therefore, the fitness of candidate test papers can be adjusted based on the expected score distribution information so that its fitness reflects the degree of matching between the candidate test papers and the test creator's expected score distribution.

[0064] First, calculate the expected score distribution of the candidate test papers. Furthermore, calculate the expected performance distribution information p. ＊ The relative entropy between the expected score distribution p of the candidate test papers and the test papers Relative entropy is a measure of the asymmetry between two probability distributions, specifically the difference between the expected score distribution and the expected score distribution of candidate test papers. Its calculation process is as follows:

[0065]

[0066] According to relative entropy The existing fitness can be adjusted to obtain a new fitness G2({z1,…,z...) n},{θ1,…,θ m},p ＊ The calculation process is as follows:

[0067]

[0068] Where α is a weighting coefficient used to adjust how well the candidate test papers fit the expected score distribution.

[0069] Therefore, the fitness of candidate test papers can reflect the degree of matching between candidate test papers and expected test results, and at the same time reflect the reliability of candidate test papers, that is, the uncertainty of test results on the level of the test subjects.

[0070] S204, Based on the fitness of multiple candidate test papers, determine at least one target test paper from multiple candidate test papers.

[0071] Specifically, based on the required number of test papers, several test papers with the highest suitability can be selected from multiple candidate test papers. The selected test papers are those with high reliability, meet the test requirements, and are highly matched with the test takers.

[0072] In some embodiments, such as Figure 4 As shown, determining at least one target test paper from multiple candidate test papers based on their fitness includes the following steps.

[0073] S401, based on the fitness of multiple candidate test papers, selects multiple test papers to be determined from multiple candidate test papers.

[0074] Specifically, L candidate test papers with the highest fitness can be selected from multiple candidate test papers, where the number of candidate test papers is less than the number of candidate test papers.

[0075] S402, randomly combine the questions from multiple pending test papers to obtain multiple new candidate test papers.

[0076] Two undetermined test papers are randomly selected, and candidate test papers for the next generation are generated based on these two undetermined test papers. Each question in the candidate test papers is randomly inherited from the corresponding question in the two undetermined test papers. This process is repeated until K candidate test papers for the next generation are generated, where K can be the same as the number of candidate test papers in the first generation.

[0077] In some embodiments, after generating a new generation of candidate test papers, one or more candidate test papers can be randomly selected, and one or more questions from one of them can be randomly replaced with similar questions. The similar questions are obtained through matching from a preset similar question bank.

[0078] S403, Repeat the above steps until the fitness of multiple candidate test papers meets the preset conditions.

[0079] Specifically, the process involves repeatedly selecting the most suitable candidate test papers from the previous generation of candidate test papers, and generating a new generation of candidate test papers based on these. Iteration continues until the difference between the fitness of the current candidate test paper and the fitness of the previous generation of candidate test papers is less than a threshold, or the maximum number of iterations is reached. For example, the fitness of a candidate test paper can be the highest fitness of the candidate test papers, or the average fitness of all candidate test papers.

[0080] S404, determine at least one target test paper from the plurality of candidate test papers.

[0081] Based on the required number of exam papers, the most suitable exam papers can be selected from multiple candidate papers.

[0082] Therefore, embodiments of this disclosure can dynamically adjust the questions in candidate test papers based on their fitness. By leveraging information theory, the test paper generation process is automated, quantified, and made more scientific, resulting in target test papers with high reliability and discrimination and difficulty levels that meet expectations.

[0083] Based on the same inventive concept, this disclosure also provides a file-compilation device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to that of the method embodiments described above, the implementation of this device embodiment can refer to the implementation of the method embodiments described above, and repeated details will not be repeated.

[0084] Figure 5 This diagram illustrates the structure of a roll-building device according to an embodiment of the present disclosure, as shown below. Figure 5As shown, the volume assembly device 500 includes: an acquisition module 501, a construction module 502, a calculation module 503, and a selection module 504.

[0085] Specifically, the acquisition module 501 is used to acquire the assessment object information of the target test paper and the reference test paper information of the same type as the target test paper. The construction module 502 is used to construct multiple candidate test papers based on the reference test paper information. The calculation module 503 is used to calculate the fitness of the multiple candidate test papers according to the assessment object information, and the fitness is used to indicate the degree of matching between the candidate test papers and the assessment object information. The selection module 504 is used to determine at least one target test paper from the multiple candidate test papers based on the fitness of the multiple candidate test papers.

[0086] In some embodiments, the selection module 504 is further configured to: select multiple candidate test papers from multiple candidate test papers based on the fitness of the multiple candidate test papers; randomly combine the questions in the multiple candidate test papers to obtain new multiple candidate test papers; repeat the above steps until the fitness of the multiple candidate test papers meets the preset conditions; and determine at least one target test paper from the multiple candidate test papers.

[0087] In some embodiments, the calculation module 503 is further configured to, for each of the multiple candidate test papers, predict the probability of answering each question in the candidate test paper according to the assessment subject information; and calculate the fitness of the candidate test paper based on the assessment subject information and the probability of answering each question in the candidate test paper.

[0088] In some embodiments, the calculation module 503 is further configured to: calculate a first discrete entropy based on the probability of answering each question in the candidate test paper; calculate a second discrete entropy based on the assessment subject information and the probability of answering each question in the candidate test paper; and calculate the fitness of the candidate test paper based on the first discrete entropy and the second discrete entropy.

[0089] In some embodiments, the calculation module 503 is further configured to: obtain the difficulty configuration information of the target test paper, the difficulty configuration information being used to indicate the expected assessment results of the target test paper; and adjust the fitness of the candidate test papers based on the difficulty configuration information.

[0090] In some embodiments, the calculation module 503 is further configured to calculate the relative entropy of the expected score distribution information and the expected score distribution of the candidate test papers, wherein the expected score distribution of the candidate test papers is calculated based on the probability of answering each question correctly in the candidate test papers; and adjust the fitness of the candidate test papers based on the relative entropy.

[0091] In some embodiments, the selection module 504 is further configured to replace questions in multiple candidate test papers with similar questions, the similar questions being obtained by matching through a preset similar question bank.

[0092] It should be noted that the file-building device provided in the above embodiments is only illustrated by the division of the above functional modules when used for file building. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the file-building device and the file-building method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0093] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0094] The following reference Figure 6 To describe an electronic device 600 according to such an embodiment of the present disclosure. Figure 6 The electronic device 600 shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0095] like Figure 6 As shown, the electronic device 600 is manifested in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, and a bus 630 connecting different system components (including storage unit 620 and processing unit 610).

[0096] The storage unit stores program code, which can be executed by the processing unit 610, causing the processing unit 610 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0097] In some embodiments, the processing unit 610 may perform the following steps of the above method embodiments: obtaining the assessment object information of the target test paper and the reference test paper information of the same type as the target test paper; constructing multiple candidate test papers based on the reference test paper information; calculating the fitness of the multiple candidate test papers according to the assessment object information, wherein the fitness is used to indicate the degree of matching between the candidate test papers and the assessment object information; and determining at least one target test paper from the multiple candidate test papers according to the fitness of the multiple candidate test papers.

[0098] Storage unit 620 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 6201 and / or cache memory 6202, and may further include a read-only memory (ROM) 6203.

[0099] Storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: 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.

[0100] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0101] Electronic device 600 can also communicate with one or more external devices 640 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 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) via network adapter 660. As shown, network adapter 660 communicates with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0102] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0103] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the methods described above is stored thereon. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code, which, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0104] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0105] In this disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0106] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0107] In practical implementation, program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0108] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0109] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0110] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0111] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A method for generating test papers, characterized in that, include: Obtain information on the examinees of the target test paper and information on reference test papers of the same type as the target test paper; Based on the reference test paper information, multiple candidate test papers are constructed; Based on the assessment subject information, the fitness of the multiple candidate test papers is calculated respectively, and the fitness is used to indicate the degree of matching between the candidate test papers and the assessment subject information; Based on the fitness of the multiple candidate test papers, at least one target test paper is determined from the multiple candidate test papers; The step of calculating the fitness of the multiple candidate test papers based on the assessment subject information includes: For each of the multiple candidate test papers, based on the assessment subject information, predict the probability of answering each question correctly in the candidate test paper. Calculate the first discrete entropy based on the probability of answering each question correctly in the candidate test paper; Based on the information of the assessment subjects and the probability of answering each question correctly in the candidate test papers, the second discrete entropy is calculated; The fitness of the candidate test paper is calculated based on the first discrete entropy and the second discrete entropy.

2. The method according to claim 1, characterized in that, The step of determining at least one target test paper from the plurality of candidate test papers based on their fitness includes: Based on the suitability of the multiple candidate test papers, multiple test papers to be determined are selected from the multiple candidate test papers; The questions from the multiple undetermined test papers are randomly combined to obtain multiple new candidate test papers; Repeat the above steps until the fitness of the multiple candidate test papers meets the preset conditions; At least one target test paper is determined from the plurality of candidate test papers.

3. The method according to claim 1, characterized in that, After calculating the fitness of the candidate test paper based on the assessment subject information and the probability of answering each question correctly in the candidate test paper, the method further includes: Obtain the difficulty configuration information of the target test paper, which is used to indicate the expected assessment results of the target test paper; Based on the difficulty configuration information, the fitness of the candidate test papers is adjusted.

4. The method according to claim 3, characterized in that, The difficulty configuration information includes expected score distribution information; Adjusting the fitness of the candidate test papers based on the difficulty configuration information includes: Calculate the relative entropy between the expected score distribution information and the expected score distribution of the candidate test papers, wherein the expected score distribution of the candidate test papers is obtained based on the probability of answering each question correctly in the candidate test papers; The fitness of the candidate test papers is adjusted based on the relative entropy.

5. The method according to claim 2, characterized in that, After randomly combining the questions from the multiple undetermined test papers to obtain a new number of candidate test papers, the process also includes: The questions in the multiple candidate test papers are replaced with similar questions, which are obtained by matching through a preset similar question bank.

6. A roll-building device, characterized in that, include: The acquisition module is used to acquire information about the examinees of the target test paper and information about reference test papers of the same type as the target test paper. A construction module is used to construct multiple candidate test papers based on the reference test paper information; The calculation module is used to calculate the fitness of the multiple candidate test papers according to the assessment object information, and the fitness is used to indicate the degree of matching between the candidate test papers and the assessment object information; The selection module is used to determine at least one target test paper from the multiple candidate test papers based on their fitness. The calculation module is further configured to: for each of the multiple candidate test papers, predict the probability of answering each question in the candidate test paper according to the assessment subject information; calculate a first discrete entropy based on the probability of answering each question in the candidate test paper; calculate a second discrete entropy based on the assessment subject information and the probability of answering each question in the candidate test paper; and calculate the fitness of the candidate test paper based on the first discrete entropy and the second discrete entropy.

7. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the volume assembly method according to any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the volume assembly method according to any one of claims 1 to 5.

Images