A test paper composition method, device and storage medium based on test paper information

Abstract

The present invention discloses a test paper assembly method, device, and storage medium based on test paper information. The test paper assembly method based on test paper information includes: obtaining test paper attribute information of a test paper to be assembled; retrieving a similar test paper set in a test paper library based on the test paper attribute information; analyzing the similar test paper set to obtain test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be assembled; retrieving similar test questions in the test question library using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions; and assembling the retrieved similar test questions into a test paper. The test paper assembly method of the present invention implements the function of automatically assembling a test paper according to test paper assembly requirements, meets the test paper assembly requirements, and greatly improves the test paper assembly efficiency.

Description

Technical Field

[0001] The present invention relates to the field of online education technology, and in particular to a test paper compilation method, device and storage medium based on test paper information. Background Art

[0002] Online education platforms typically rely on a robust database of test questions to provide services like photo search, intelligent practice, and homework grading. This robust database allows for the creation of test papers, which can then be used for student practice and exam simulations.

[0003] The existing test paper compilation method requires teachers to search and screen questions one by one in the test question bank based on the test paper's structure, difficulty, and knowledge points required to be tested, and finally complete the test paper compilation. During the test paper compilation process, teachers need to expend a great deal of energy on searching and screening questions. However, in reality, the test paper structure of each set of test papers, the knowledge points tested in the test papers at different stages, and the distribution of the difficulty values ​​of the test papers have certain regularities, such as the college entrance examination and the high school entrance examination. Therefore, how to solve the problem of automatically compiling test papers based on the regularity of the test papers for teachers to select can greatly reduce the teacher's workload, improve the teacher's user experience, and improve the teacher's work efficiency.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a test paper compilation method, device and storage medium based on test paper information. The specific technical solutions are as follows:

[0006] The present invention proposes a test paper composition method based on test paper information, comprising:

[0007] Get the test paper attribute information of the test paper to be grouped;

[0008] Retrieving a similar test paper set in the test paper library according to the test paper attribute information;

[0009] Analyze the similar test paper set to obtain test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be grouped;

[0010] Retrieving similar test questions in the test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions;

[0011] The retrieved similar test questions are combined into a test paper.

[0012] As an optional embodiment of the present invention, analyzing the similar test paper set to obtain the test paper structure information of the test paper to be grouped includes:

[0013] Analyze the test paper structure information of each test paper in the similar test paper set, wherein the test paper structure information includes question type distribution, the number of questions of each question type, and the question score;

[0014] Comprehensively analyze the test paper structure information of each test paper and predict the question type distribution, the number of questions of each question type and the question score of the test paper to be composed through preset rules;

[0015] Optionally, the preset rule is a system voting rule or a weighted mean calculation condition.

[0016] As an optional embodiment of the present invention, the analyzing the similar test paper set to obtain the test question knowledge point information of the test paper to be grouped includes:

[0017] Obtain the test knowledge point labels corresponding to the same question types and question numbers in each test paper set;

[0018] The knowledge points to be tested for each question in the test paper to be assembled are predicted by systematic voting based on the knowledge point labels of each question.

[0019] As an optional embodiment of the present invention, analyzing the similar test paper set to obtain the test question difficulty information includes:

[0020] Get the question difficulty value labels corresponding to the questions of the same question type and question number in each test paper set;

[0021] The difficulty value of each question in the test paper to be grouped is predicted by calculating the weighted average of the difficulty value labels of each question.

[0022] As an optional embodiment of the present invention, the searching of similar test questions in the test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions includes:

[0023] By using the predicted question types, question-tested knowledge points, and question difficulty values ​​as screening conditions, searching is performed in the question bank;

[0024] Filter out similar test questions that meet the test type, knowledge points tested and difficulty value.

[0025] As an optional embodiment of the present invention, the step of composing a test paper by retrieving similar test questions according to the test paper structure information includes:

[0026] Divide the retrieved similar test questions into corresponding question type sections according to the question type distribution in the test paper structure information;

[0027] Based on the number of questions in each question type, the knowledge points tested by each question, and the difficulty value of each question, similar questions in each question type section are screened and sorted to complete the test paper.

[0028] As an optional implementation manner of the present invention, if there are multiple similar test questions with the same question number in the same question type, one of the test questions is randomly selected or a test question with higher popularity among the similar test questions is selected.

[0029] As an optional embodiment of the present invention, searching for similar test paper sets in the test paper library according to the test paper attribute information includes:

[0030] The test paper attribute information includes region, grade, subject and semester information;

[0031] Using the set region, grade, subject and semester information as the filtering conditions, similar test paper sets with matching region, grade, subject and semester information tags are retrieved from the test paper library.

[0032] The present invention also provides a test paper assembling device based on test paper information, comprising:

[0033] Input module, obtains the test paper attribute information of the test paper to be composed;

[0034] An examination paper retrieval module searches for similar examination paper sets in the examination paper database according to the examination paper attribute information;

[0035] An analysis module analyzes the similar test paper set to obtain test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be grouped;

[0036] A test question retrieval module searches for similar test questions in a test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions;

[0037] And the test paper composition module, which combines the retrieved similar test questions into a test paper.

[0038] The present invention also provides a storage medium storing a computer executable program. When the computer executable program is executed, any one of the above-mentioned test paper composition methods based on test paper information is implemented.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention obtains the test paper attribute information of the test paper to be assembled, retrieves a similar test paper set from the test paper library, analyzes the test paper structure information, test question knowledge point information, and test question difficulty information of the similar test paper set to obtain the test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be assembled, and retrieves similar test questions from the test question library based on the above information to assemble the test paper. The test paper assembly method of the present invention realizes the function of automatically assembling the test paper according to the test paper assembly requirements, meets the test paper assembly requirements, and greatly improves the test paper assembly efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Flow chart of the test paper composition method based on test paper information of embodiment 1 of the present invention Figure 1 ;;

[0042] Figure 2 Flow chart of the test paper composition method based on test paper information of embodiment 1 of the present invention Figure 2 ;

[0043] Figure 3 Flow chart of the test paper composition method based on test paper information of embodiment 1 of the present invention Figure 3 ;

[0044] Figure 4 A processing flow chart of a method for marking the difficulty of test questions based on test paper structure according to a second embodiment of the present invention;

[0045] Figure 5 Example of a test question difficulty transfer diagram in a test question difficulty marking method based on test paper structure according to embodiment 2 of the present invention Figure 1 ;

[0046] Figure 6 Example of a test question difficulty transfer diagram in a test question difficulty marking method based on test paper structure according to embodiment 2 of the present invention Figure 2 ;

[0047] Figure 7 Flow chart of the method for marking the difficulty of test questions based on the test paper structure according to the second embodiment of the present invention Figure 1 ;

[0048] Figure 8 Flow chart of the method for marking the difficulty of test questions based on the test paper structure according to the second embodiment of the present invention Figure 2 ;

[0049] Figure 9 Flow chart of the method for marking the difficulty of test questions based on the test paper structure according to the second embodiment of the present invention Figure 3 ;

[0050] Figure 10 Flow chart of the method for marking the difficulty of test questions based on the test paper structure according to the second embodiment of the present invention Figure 4 ;

[0051] Figure 11 A processing flow chart of a method for evaluating the confidence level of a test question difficulty value according to a third embodiment of the present invention. DETAILED DESCRIPTION

[0052] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0053] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the claimed invention, but merely represents some embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0054] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions therein may be combined with each other.

[0055] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0056] In the description of the present invention, it should be noted that the terms "upper" and "lower" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or the orientations or positional relationships in which the inventive product is typically placed when in use, or the orientations or positional relationships commonly understood by those skilled in the art. Such terms are intended solely to facilitate the description of the present invention and simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on the present invention. Furthermore, the terms "first" and "second" and the like are used solely for distinction and should not be construed as indicating or implying relative importance.

[0057] Example 1

[0058] See also Figure 1 As shown, this embodiment provides a test paper composition method based on test paper information, including:

[0059] Get the test paper attribute information of the test paper to be grouped;

[0060] Retrieving a similar test paper set in the test paper library according to the test paper attribute information;

[0061] Analyze the similar test paper set to obtain test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be grouped;

[0062] Retrieving similar test questions in the test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions;

[0063] The retrieved similar test questions are combined into a test paper.

[0064] This embodiment obtains the test paper attribute information of the test paper to be assembled, retrieves a similar test paper set from the test paper database, analyzes the test paper structure information, test question knowledge point information, and test question difficulty information of the similar test paper set, and obtains the test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be assembled. Based on this information, the test paper database is retrieved for similar test questions to assemble the test paper. This test paper assembly method of this embodiment implements the function of automatically assembling test papers according to test paper assembly requirements, meets test paper assembly requirements, and greatly improves test paper assembly efficiency.

[0065] The test paper composition method based on test paper information in this embodiment can obtain the test paper attribute information of the test paper to be composed by receiving the user's input information. For example, if the received input information is "Beijing three-year first semester midterm mathematics test paper", the Beijing third grade first semester midterm mathematics test papers in previous years in the test paper library will be retrieved according to the test paper attribute information. By analyzing the test papers in previous years, the currently required "Beijing three-year first semester midterm mathematics test paper" can be predicted.

[0066] As an optional implementation of this embodiment, see Figure 2 As shown, the test paper structure information of the test paper to be grouped obtained by analyzing the similar test paper set in this embodiment includes:

[0067] Analyze the test paper structure information of each test paper in the similar test paper set, wherein the test paper structure information includes question type distribution, the number of questions of each question type, and the question score;

[0068] The test paper structure information of each test paper is comprehensively analyzed and the preset rules are used to predict the question type distribution of the test paper to be grouped, the number of questions of each question type and the question scores.

[0069] Optionally, the preset rule is a system voting rule or a weighted mean calculation condition.

[0070] Specifically, the system voting rule is to calculate the distribution of question types with the highest proportion, the number of questions of each question type, and the question scores as the test paper structure information for the test paper to be assembled. The weighted average calculation condition is to calculate the distribution of question types, the number of questions of each question type, and the question scores of similar test papers, and then calculate the distribution of question types, the number of questions of each question type, and the question scores of the test paper to be assembled using the average calculation method.

[0071] As an optional implementation of this embodiment, see Figure 2As shown, in this embodiment, the information of test questions and knowledge points of the test paper to be grouped is obtained by analyzing the similar test paper set, including:

[0072] Obtain the test knowledge point labels corresponding to the same question types and question numbers in each test paper set;

[0073] The knowledge points to be tested for each question in the test paper to be assembled are predicted by systematic voting based on the knowledge point labels of each question.

[0074] Specifically, the system voting rule is that the knowledge point labels corresponding to the test questions with the highest statistical proportions are used as the knowledge points for the test questions in the test paper to be assembled.

[0075] As an optional implementation of this embodiment, see Figure 2 As shown, in this embodiment, the difficulty information of the test questions in the test paper obtained by analyzing the similar test paper set includes:

[0076] Get the question difficulty value labels corresponding to the questions of the same question type and question number in each test paper set;

[0077] The difficulty value of each question in the test paper to be grouped is predicted by calculating the weighted average of the difficulty value labels of each question.

[0078] Specifically, the weighted mean calculation condition is to count the question difficulty value labels corresponding to the questions with the same question number in each similar test paper, and calculate the difficulty value of the corresponding question number of the test paper to be grouped according to the average value calculation method.

[0079] As an optional implementation of this embodiment, see Figure 2 As shown, in this embodiment, the method of searching similar test questions in the test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions includes:

[0080] By using the predicted question types, question-tested knowledge points, and question difficulty values ​​as screening conditions, searching is performed in the question bank;

[0081] Filter out similar test questions that meet the test type, knowledge points tested and difficulty value.

[0082] Furthermore, in this embodiment, the process of grouping the retrieved similar test questions into a test paper according to the test paper structure information includes:

[0083] Divide the retrieved similar test questions into corresponding question type sections according to the question type distribution in the test paper structure information;

[0084] Based on the number of questions in each question type, the knowledge points tested by each question, and the difficulty value of each question, similar questions in each question type section are screened and sorted to complete the test paper.

[0085] The test paper composition method of this embodiment retrieves multiple similar test questions from the test question bank, which can be freely combined according to the test paper structure to obtain multiple sets of test papers. The test paper difficulty values ​​of the multiple sets of test papers may have deviations, which are used for user selection so that users can get the most satisfactory test paper.

[0086] As an optional implementation of this embodiment, in a test paper composition method based on test paper information of this embodiment, if there are multiple similar test questions with the same question number in the same question type, one of the test questions is randomly selected or a test question with higher popularity among the similar test questions is selected.

[0087] In this embodiment, searching for similar test paper sets in the test paper library according to the test paper attribute information includes:

[0088] The test paper attribute information includes region, grade, subject and semester information;

[0089] Using the set region, grade, subject and semester information as the filtering conditions, similar test paper sets with matching region, grade, subject and semester information tags are retrieved from the test paper library.

[0090] See also Figure 3 The figure shows a processing flow chart of a specific implementation of a test paper composition method based on test paper information of this embodiment.

[0091] This embodiment also provides a test paper generating device based on test paper information, including:

[0092] Input module, obtains the test paper attribute information of the test paper to be composed;

[0093] An examination paper retrieval module searches for similar examination paper sets in the examination paper database according to the examination paper attribute information;

[0094] An analysis module analyzes the similar test paper set to obtain test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be grouped;

[0095] A test question retrieval module searches for similar test questions in a test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions;

[0096] And the test paper composition module, which combines the retrieved similar test questions into a test paper.

[0097] This embodiment also provides a storage medium storing a computer executable program. When the computer executable program is executed, the test paper composition method based on the test paper information is implemented.

[0098] The storage medium described in this embodiment may include a data signal propagated in baseband or as part of a carrier wave, which carries a readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0099] This embodiment also provides an electronic device, including a processor and a memory, wherein the memory is used to store a computer executable program. When the computer program is executed by the processor, the processor executes the test paper compilation method based on test paper information.

[0100] The electronic device is implemented as a general-purpose computing device. The processor may be one or multiple processors operating in concert. The present invention also does not exclude distributed processing, meaning the processors may be dispersed across different physical devices. The electronic device of the present invention is not limited to a single entity but may also be the sum of multiple physical devices.

[0101] The memory stores a computer executable program, typically a machine-readable code, which can be executed by the processor to enable the electronic device to perform the method of the present invention, or at least some of the steps in the method.

[0102] The memory includes a volatile memory, such as a random access memory unit (RAM) and / or a cache memory unit, and may also be a non-volatile memory, such as a read-only memory unit (ROM).

[0103] It should be understood that the electronic devices of the present invention may also include elements or components not shown in the above examples. For example, some electronic devices also include display units such as screens, and some electronic devices also include human-computer interaction elements such as buttons and keyboards. As long as the electronic device can execute a computer-readable program stored in its memory to implement the method of the present invention or at least some of the steps of the method, it is considered an electronic device covered by the present invention.

[0104] Through the above description of the implementation mode, it is easy for those skilled in the art to understand that the present invention can be implemented by hardware capable of executing a specific computer program, such as the system of the present invention, and the electronic processing unit, server, client, mobile phone, control unit, processor, etc. contained in the system. The present invention can also be implemented by computer software that executes the method of the present invention, such as control software executed by a microprocessor, an electronic control unit, a client, a server, etc. However, it should be noted that the computer software that executes the method of the present invention is not limited to being executed by one or a specific hardware entity, and it can also be implemented in a distributed manner by unspecified specific hardware. For computer software, the software product can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), or it can be distributed and stored on a network, as long as it enables an electronic device to execute the method according to the present invention.

[0105] Example 2

[0106] See also Figure 4 and Figure 7 As shown, this embodiment provides a method for marking the difficulty of test questions based on the test paper structure, including:

[0107] Step S1, obtaining a set of test papers with the same test paper attribute information in the test paper library;

[0108] Step S2, performing test paper structure analysis and test question information analysis on the test papers in the test paper set;

[0109] Step S3, constructing a question difficulty transfer structure diagram for all questions in the test paper set according to the question difficulty relationship corresponding to each type of test paper structure preset by the system;

[0110] Step S4: marking the difficulty of each test question based on the test question difficulty transfer diagram.

[0111] This embodiment provides a method for marking the difficulty of test questions based on the test paper structure. By constructing a test question difficulty transfer structure diagram for all test questions in the test paper set, the system automatically assigns a difficulty value to each test question according to the test question difficulty transfer structure diagram, thereby realizing the automation and batch marking of test question difficulty values. Compared with the manual marking method of each question, it is simpler and faster. Moreover, since it is based on the test question difficulty transfer structure diagram, the test question difficulty value is obtained through relative relationship, the marking basis of the test question difficulty value is more reasonable, and the test question difficulty value is more accurate and reliable.

[0112] The difficulty value labels of the test questions annotated by the test question difficulty marking method of this embodiment are used to calculate the test question difficulty values ​​when analyzing the similar test paper set in the first embodiment to obtain the test question difficulty information in the test papers.

[0113] Further, see Figure 8 As shown, in this embodiment, the question difficulty transfer graph of all questions in the test paper set is constructed according to the question difficulty relationship corresponding to each type of test paper structure preset by the system, including:

[0114] Step S301: In the same test paper, according to the test question difficulty relationship corresponding to the test paper structure preset by the system, a one-way acyclic graph is used to form a test paper graph structure in ascending order of difficulty;

[0115] Step S302: The test paper graph structures of different test papers are connected through the same test questions to construct a test question difficulty transfer structure graph of all test questions in the test paper set.

[0116] See also Figure 5 As shown in the figure, test questions 1, 2, 3, 4, and 5 belong to the same type of test questions in the same test paper, and are organized into a test paper diagram structure of 1→2→3→4→5 according to the difficulty relationship; and test questions 6, 7, 3, 8, 9, 10, and 11 belong to the same type of test questions in another test paper, and are organized into a test paper diagram structure of 6→7→3→8→9→10→11 according to the difficulty relationship. The two test papers contain the same test question 3, which realizes the connection of the two test paper diagram structures. In this way, all the test questions in the entire test paper set can be marked as follows Figure 7 The question difficulty transfer structure diagram shown may have a single, interconnected, and interwoven structure for all questions in the entire test set. It may also have multiple, independent difficulty transfer structures. Furthermore, a set of test papers may have a single, independent difficulty transfer structure, unrelated to any other. Regardless of the final difficulty transfer structure constructed for the test set, as long as there is a relative relationship between the difficulty levels of the questions, the difficulty value of each question can be calculated.

[0117] As an optional implementation of this embodiment, see Figure 8 As shown, the marking of the difficulty of each test question based on the test question difficulty transfer graph includes:

[0118] Step S410, finding the longest sequence in the test question difficulty transfer structure diagram;

[0119] Step S411: Set the difficulty value of the test questions at the head of the sequence to the initial value K0, and the difficulty value of the test questions at the tail of the sequence to Kt. According to the length of the longest sequence, form a uniform gradient between K0 and Kt to assign the difficulty values ​​of the test questions between the head and the tail of the longest sequence.

[0120] In the above-mentioned test question difficulty value algorithm of this embodiment, the longest sequence in the test question difficulty transfer structure diagram is first used as the basis, the minimum test question difficulty value K0 is assigned to the test question at the head of the sequence, and the maximum test question difficulty value Kt is assigned to the test question at the end of the sequence. The test questions between the head and tail of the sequence are evenly assigned, and then any test question in the middle is used to assign values ​​to other test questions in the sequence connected to it.

[0121] Optionally, the difficulty value of the test questions in this embodiment is between 0 and 1.0. Therefore, the initial value K0 of this embodiment is 0, Kt=1.0, and the difficulty values ​​of the test questions between the head and the tail of the sequence are all between 0 and 1.0.

[0122] For completely independent sequences in the question difficulty transmission structure diagram, independent calculations are performed using the method of assigning the minimum question difficulty value to the head question, the maximum question difficulty value to the tail question, and uniform distribution of difficulty values ​​in the middle. Alternatively, the head and tail questions in the independent sequence are sent to manual annotation. The manual annotation is performed on the head and tail questions in the independent sequence with reference to the question difficulty values ​​automatically annotated by the system, and then the difficulty values ​​are returned to the system. The system automatically calculates and copies the question difficulty values ​​of other questions in the independent sequence based on the manually annotated question difficulty values ​​of the head and tail questions.

[0123] Further, see Figure 8 As shown, in this embodiment, marking the difficulty of each question based on the question difficulty transfer graph includes:

[0124] Step S420, testing questions in a subsequence that is not the longest sequence in the test question difficulty transfer structure diagram;

[0125] Step S421, starting from the test question connected to the longest sequence, the difficulty value of the test question in the subsequence pointed to by the test question increases in sequence according to the gradient, and the difficulty value of the test question in the subsequence pointed to by the test question decreases in sequence.

[0126] The test question difficulty marking method based on the test paper structure of this embodiment can automatically mark the difficulty values ​​of all test questions with mutual correlation in batches through the test question difficulty transfer structure diagram, which is simpler and more intelligent.

[0127] In addition, in view of the special circumstances that exist in the process of constructing the question difficulty transfer structure diagram, the present embodiment of marking the difficulty of each question based on the question difficulty transfer diagram further includes:

[0128] Targeting the subgraphs with strong connected components in the test question difficulty transfer structure graph;

[0129] The strongly connected components in the subgraph are merged into a structural point, and the difficulty values ​​of the test questions in the strongly connected components are equal.

[0130] Specifically, in a directed graph G, if there is a directed path from u to v between two vertices u and v, and there is also a directed path from v to u, then the two vertices are said to be strongly connected. If every two vertices of a directed graph G are strongly connected, then G is said to be a strongly connected graph. The maximal strongly connected subgraph of a directed non-strongly connected graph is called a strongly connected component. Figure 3 In the test difficulty transfer diagram shown, 8→9→12→8 constitutes a strongly connected component S1. The formation of a strongly connected component will cause the difficulty transfer to fall into an infinite loop. We believe that the difficulty values ​​of the questions in the strongly connected component are equal and can be reduced to one point.

[0131] In the method for marking the difficulty of test questions based on the test paper structure of this embodiment, the relationship between the difficulty of test questions corresponding to the various types of test paper structures preset by the system is as follows:

[0132] The difficulty of each question in the same type of question in the same test paper increases with the increase of the serial number;

[0133] Alternatively, a neural network model may be used to train and learn test papers of various types of test paper structures to derive the difficulty relationship of test questions corresponding to each type of test paper structure.

[0134] In this embodiment, the difficulty relationships of the test questions corresponding to each type of test paper structure are determined using the two methods described above and then preset in the system. Taking the middle school entrance examination and college entrance examination papers of previous years as examples, each set of test papers includes several question types, the number of questions in each question type, and the difficulty relationships of the questions within each question type are all fixed. That is, the structure of the test paper is generally fixed. Based on this characteristic, the test paper structure types and the difficulty relationships of the test questions corresponding to each type of test paper structure can be summarized.

[0135] As an optional implementation of this embodiment, a method for marking the difficulty of test questions based on the test paper structure of this embodiment, wherein obtaining a set of test papers having the same test paper attribute information in the test paper library includes:

[0136] The test paper attribute information includes the test paper name, subject label, grade label and region label;

[0137] The test papers with similar test paper names, the same subject labels, the same grade labels and the same regional labels are screened out from the test paper library using the test paper names, the subject labels, the grade labels and the regional labels as screening conditions, and are stored as a test paper set.

[0138] Optionally, the similarity of the test paper names refers to a successful match of one or more keywords / words set in the test paper names.

[0139] See also Figure 9As shown, in the method for marking the difficulty of test questions based on test paper structure of this embodiment, the test paper structure analysis for the test papers in the test paper set includes:

[0140] Step S211, obtaining the question type and the number of questions contained in each question type for each test paper in the test paper set;

[0141] Step S212: Match the corresponding test paper structure in the test paper structure library preset by the system according to the test question types and the number of test questions contained in each test question type.

[0142] See also Figure 5 As shown, the test question information parsing for the test papers in the test paper set includes:

[0143] Step S221 , obtaining the question ID, subject information and grade information of each question for each set of test papers in the test paper set.

[0144] Taking mathematics test questions as an example, mathematics test papers have a particularly regular test paper structure and test question difficulty relationship. The question types of mathematics test papers generally include multiple-choice questions, fill-in-the-blank questions and essay questions, and the difficulty value of the questions in each question type increases as the test question sequence number increases. Based on the above-mentioned test paper structure of the mathematics test paper and the test question difficulty value relationship corresponding to the test paper structure, this embodiment can realize automatic batch marking of the difficulty values ​​of mathematics test questions.

[0145] The method for marking the difficulty of test questions based on the math test paper structure in this embodiment is as follows:

[0146] Step S1 ′: the test paper database pre-stores test paper structure information of mathematics test papers and the relationship between the test paper structure and the test question difficulty values ​​corresponding to the test paper structure.

[0147] In step S2', the examination paper screening conditions are set in the examination paper library. For example, if the selection condition is set as Beijing - 2018 - Grade 2 of Senior High School - Mathematics - First Semester Midterm Examination Paper, all mathematics examination papers of the first semester midterm examination of Grade 2 of Senior High School in Beijing in 2018 will be screened out in the examination paper library to form a mathematics examination paper set.

[0148] Step S3': In the same set of mathematics test papers, according to the relationship of test question difficulty corresponding to the test paper structure preset by the system, a test paper graph structure is formed in ascending order of difficulty using a one-way acyclic graph; the test paper graph structures of different test papers are connected through the same test questions to construct a test question difficulty transfer structure graph of all test questions in the test paper set.

[0149] In step S4', during the construction of the question difficulty transfer structure graph, if a subgraph containing strongly connected components exists, the strongly connected components in the subgraph are merged into a single structural point, with the difficulty values ​​of all questions in the strongly connected component being equal. The formation of strongly connected components can cause difficulty transfer to fall into an infinite loop. We believe that strongly connected components with equal difficulty values ​​can be collapsed into a single point to avoid an infinite loop during the construction of the question difficulty transfer structure graph.

[0150] Step S5', finding the longest sequence in the question difficulty transfer structure diagram; setting the question difficulty value of the question at the head of the sequence to 0, and the question difficulty value of the question at the tail of the sequence to 1.0, and forming a uniform gradient between 0 and 1.0 according to the length of the longest sequence to assign question difficulty values ​​to the questions between the head and tail of the longest sequence.

[0151] Step S6': for the questions in the subsequences that are not the longest sequence in the question difficulty transfer structure diagram, starting from the question connected to the longest sequence, the question difficulty values ​​of the subsequences pointed to by the questions are increased in sequence according to the gradient, and the question difficulty values ​​of the subsequences pointed to by the questions are decreased in sequence, thereby obtaining the question difficulty values ​​of the questions in each subsequence.

[0152] Example 3

[0153] See also Figure 11 As shown, this embodiment provides a confidence evaluation method for a test question difficulty value, which is used to evaluate the reliability of the test question difficulty value obtained by the test question difficulty marking method of Example 2, including:

[0154] Extract a certain number of test questions from the test question bank and form test question pairs in pairs;

[0155] Obtain the difficulty values ​​of the test questions in the test question pairs, compare the difficulty values ​​of the test questions, and summarize to obtain the system evaluation result data;

[0156] Conduct manual evaluation on the difficulty relationship of test questions in the test pair and obtain manual evaluation result data;

[0157] The manual evaluation result data is used as the evaluation standard, and the results are compared with the system evaluation result data. The proportion of the same test question pairs is statistically calculated to obtain the confidence level for evaluating the difficulty value information of the test questions in the test question bank.

[0158] Since each teacher has different evaluation criteria for the difficulty of test questions, which are highly subjective, simply evaluating the difficulty of each test question is not only time-consuming and labor-intensive, but also meaningless, because what is more important is to evaluate whether the rules for the difficulty of test questions are reliable, or whether the difficulty values ​​of most test questions in the test question bank are reliable.

[0159] Based on the above technical problems, in order to more objectively and accurately evaluate the reliability of the difficulty values ​​of test questions in the test question bank, this embodiment provides a confidence evaluation method for the difficulty values ​​of test questions, in which test questions are grouped into test question pairs, and the difficulty relationship of the test question pairs is manually evaluated. There are subjective differences in the scores of the test question difficulty values, but the comparison of the difficulty relationship between the two test questions in the test question pair is relatively objective. In this way, the subjective evaluation of the test question difficulty value of a single test question is transformed into a relatively objective evaluation of the comparison of the difficulty relationship of the test question pair, and the manual evaluation result data is obtained; at the same time, the size relationship of the test question difficulty values ​​in the test question pair is automatically compared by the system to obtain the system evaluation result data; the manual evaluation result data is used as the evaluation standard, and the results are compared with the system evaluation result data, and the proportion of the test question pairs that have the same comparison is statistically calculated to obtain the confidence level for evaluating the test question difficulty value information in the test question bank.

[0160] The confidence evaluation method for test difficulty values ​​in this embodiment no longer focuses excessively on the difficulty value of a specific test question. Instead, it compares the difficulty values ​​of the test questions and statistically calculates the percentage of data that agrees with the system evaluation results. If the percentage exceeds a certain value, it indicates that the confidence level of the test question difficulty value in the current test question bank is high, thereby achieving a confidence evaluation of the test question difficulty value. Therefore, the confidence evaluation method for test difficulty values ​​in this embodiment achieves an indicator-based confidence evaluation of test question difficulty values, providing an operational reference for determining the confidence level of test question difficulty values ​​in the test question bank, making it simpler, more objective, and more efficient.

[0161] As an optional implementation of this embodiment, a confidence evaluation method for a test question difficulty value of this embodiment, wherein the method obtains the test question difficulty values ​​of the test questions in the test question pair, compares the test question difficulty values, and summarizes the system evaluation result data includes:

[0162] The test questions in the test question pair are stored in the format of {test question A, test question B};

[0163] The difference in difficulty of the test questions is preset, n, and n is a positive number;

[0164] Compare the difference between the difficulty value of test question A and the difficulty value of test question B with the difference between the preset difficulty values;

[0165] If |difficulty value of test item A - difficulty value of test item B| < n;

[0166] It is determined that the difficulty value of test question A is equivalent to the difficulty value of test question B, and the system evaluation result data is recorded as i0;

[0167] If the difficulty value of question A - the difficulty value of question B ≥ n;

[0168] It is determined that the difficulty value of test question A is greater than the difficulty value of test question B, and the system evaluation result data is recorded as i1;

[0169] If the difficulty value of question A - the difficulty value of question B ≤ -n;

[0170] It is determined that the difficulty value of test question A is less than the difficulty value of test question B, and the system evaluation result data is recorded as i2;

[0171] Summarize the statistical system evaluation results data i0, i1 and i2.

[0172] The system evaluation result data of this embodiment is obtained by the system directly obtaining the difficulty values ​​of test questions A and test questions B and performing a difference comparison. Considering that the test question difficulty value is a subjective evaluation indicator, in order to reduce the deviation of the test question difficulty value caused by subjective differences, this embodiment introduces a test question difficulty value difference n. If |the test question difficulty value of test question A - the test question difficulty value of test question B| is less than n, then it is determined that the test question difficulty value of test question A is equivalent to the test question difficulty value of test question B. This relaxes the restriction condition that the test question difficulty values ​​of the test questions in the system evaluation result data are equal, and can better correspond and compare with the manual evaluation result data.

[0173] In this embodiment, the system evaluation result data i0, i1 and i2 are mainly used to record the system comparison results of the test difficulty values ​​in three situations: the test difficulty value of test question A is greater than the test difficulty value of test question B, the test difficulty value of test question A is less than the test difficulty value of test question B, and the test difficulty value of test question A is equivalent to the test difficulty value of test question B.

[0174] As an optional implementation of this embodiment, a confidence evaluation method for a test question difficulty value in this embodiment, wherein manually evaluating the difficulty relationship of test questions in a test question pair and obtaining manual evaluation result data includes:

[0175] The test questions in the test question pair are stored as a test question pair data packet in the format of {test question A, test question B};

[0176] Sending the test question pair data packet to at least one manual evaluation account;

[0177] If the difficulty value of the manually evaluated test question A is greater than the difficulty value of the test question B, then the manual evaluation result data j1;

[0178] If the difficulty value of the manually evaluated test question A is less than the difficulty value of the test question B, then the manual evaluation result data j2;

[0179] If the difficulty value of the manually evaluated test question A is equal to the difficulty value of the test question B, then the manual evaluation result data j0;

[0180] Summarize and count the manual evaluation result data j0, j1 and j2.

[0181] The confidence evaluation method for the difficulty value of test questions in this embodiment sets the manual evaluation results of test questions A and test questions B as three evaluation results based on possible situations in manual evaluation: the test question difficulty value of test question A is greater than the test question difficulty value of test question B, the test question difficulty value of test question A is less than the test question difficulty value of test question B, and the test question difficulty value of test question A is equivalent to the test question difficulty value of test question B. The manual evaluation submits the test question difficulty value comparison results of the test question pairs in a selective manner, and summarizes the manual evaluation result data j0, j1 and j2.

[0182] In this way, the confidence evaluation method of the difficulty value of the test questions in this embodiment provides a simpler and more convenient way for manually evaluating the relationship between the difficulty values ​​of the test questions, and is consistent with the type of system evaluation result data, making it convenient to compare the system evaluation result data with the manual evaluation result data one by one to obtain the proportion of relatively consistent results.

[0183] Furthermore, in a confidence evaluation method for the difficulty value of a test question of the present embodiment, during the process of manually evaluating the relationship between the difficulty values ​​of the test questions, if the same test question pair data packet is sent to multiple manual evaluation accounts, the manual evaluation result data of the multiple manual evaluation accounts are obtained respectively; the manual evaluation result data of each test question pair in the test question pair data packet are statistically analyzed and the manual evaluation result data with a high proportion are voted as the manual evaluation result of the test question pair; if there are test question pairs with the same proportion of manual evaluation result data, the manual evaluation result of the test question pair is determined by comprehensively considering the manual evaluation result data of other test question pairs in the test question pair data packet, or the system extracts the test question pair for manual evaluation again.

[0184] In the confidence evaluation method of the test question difficulty value of this embodiment, manual evaluation of the relationship between the difficulty values ​​of the test questions is performed, and evaluations are performed separately through multiple manual evaluation accounts and the evaluation results are summarized. The manual evaluation result data is more objective and accurate.

[0185] As an optional implementation of this embodiment, a confidence evaluation method for the difficulty value of a test question of this embodiment, using the manual evaluation result data as an evaluation standard, comparing the results with the system evaluation result data, and statistically calculating the proportion of test question pairs that are identical in the comparison, is used to evaluate the confidence of the test question difficulty value information in the test question database, including:

[0186] For each test question pair, the system evaluation result data is compared with the manual evaluation result data;

[0187] Whether the system evaluation result data i0 corresponds to the manual evaluation result data j0;

[0188] Whether the system evaluation result data i1 corresponds to the manual evaluation result data j1;

[0189] Whether the system evaluation result data i2 corresponds to the manual evaluation result data j2;

[0190] If the judgment result in the above step is yes, the system evaluation result data is the same as the manual evaluation result data, and is marked as R;

[0191] If the judgment result in the above step is no, then the system evaluation result data is different from the manual evaluation result data, and it is marked as F;

[0192] The number of marks R is counted, the proportion of marks R is calculated and output, and the confidence level used to evaluate the difficulty value information of the test questions in the test question bank is obtained.

[0193] Optionally, the system evaluation result data i0 and the manual evaluation result data j0 are both recorded as 0, the system evaluation result data i1 and the manual evaluation result data j1 are both recorded as 1, and the system evaluation result data i2 and the manual evaluation result data j2 are both recorded as 2; the comparison result mark R is recorded as 1, and the comparison result mark F is recorded as 0.

[0194] As an optional implementation of this embodiment, a confidence evaluation method for a test question difficulty value of this embodiment, wherein a certain number of test questions are extracted from a test question bank and formed into test question pairs, comprises:

[0195] Randomly selecting a certain number of test questions from the test question bank;

[0196] Filter out test questions with the same test question attributes according to the test question attribute screening conditions;

[0197] The screened test questions are divided into test question pairs and numbered;

[0198] Alternatively, a test question attribute screening condition is preset, and test questions with the same test question attributes that meet the screening condition are screened out from the test question database;

[0199] A certain number of screened test questions are randomly selected, divided into pairs, and numbered.

[0200] The test questions in the test question bank extracted in this embodiment should have the same test question attributes, or be grouped and numbered according to the test question attributes, because test questions are only meaningful for comparison in the same subject and grade, and the test questions also need to be sent to the corresponding teachers for manual evaluation according to the corresponding subject, grade and other test question attribute information.

[0201] Optionally, the test question attributes include grade, subject and question type. Furthermore, the test question attributes may also include region and others (such as Mathematical Olympiad test questions).

[0202] This embodiment extracts a certain number of question pair samples from the question bank. The number of question pair samples cannot be too many, otherwise the evaluation workload will be too heavy, nor can it be too few, otherwise the evaluation reliability will be insufficient. Therefore, the number of question pair samples extracted in this embodiment should not be less than 50% of the number of questions under the corresponding question attribute conditions in the question bank.

[0203] As an optional implementation of this embodiment, in a method for evaluating the confidence level of a test question difficulty value of this embodiment, the test question difficulty values ​​of a certain number of test questions extracted from the test question database are annotated by the same manual annotation account or the same test question difficulty value annotation rule;

[0204] The accuracy of the manual labeling account or the test question difficulty labeling rule in labeling the test question difficulty is evaluated based on the obtained confidence level.

[0205] As an optional implementation of this embodiment, a confidence evaluation method for a test question difficulty value in this embodiment includes:

[0206] The system presets a first confidence level Z1 and a second confidence level Z2, wherein the first confidence level Z1 is smaller than the second confidence level Z2;

[0207] The relationship between the confidence level obtained by statistical calculation and the first confidence level Z1 and the second confidence level Z2;

[0208] If the confidence level obtained by statistical calculation is greater than the second confidence level Z2;

[0209] The difficulty values ​​of the questions extracted from the question bank are accurate, and the difficulty value labels of the current questions are retained;

[0210] If the confidence level obtained by statistical calculation is less than the first confidence level Z1;

[0211] The difficulty value of the test question extracted from the test question bank is inaccurate, and the current test question difficulty value label is discarded;

[0212] Re-labeling the test questions with a difficulty value;

[0213] If the confidence level obtained by statistical calculation is greater than or equal to the first confidence level Z1 and less than or equal to the second confidence level Z2;

[0214] The difficulty values ​​of test questions extracted from the test question bank are to be evaluated, and the test questions are again evaluated for the confidence level of the difficulty values.

[0215] The above embodiments are only used to illustrate the present invention and are not intended to limit the technical solutions described in the present invention. Although this specification has described the present invention in detail with reference to the above embodiments, the present invention is not limited to the above specific implementation methods. Therefore, any modification or equivalent replacement of the present invention; and all technical solutions and improvements thereof that do not depart from the spirit and scope of the invention are included in the scope of the claims of the present invention.

Claims

1. A test paper composition method based on test paper information, characterized in that: include: Get the test paper attribute information of the test paper to be grouped; Retrieving a similar test paper set in the test paper library according to the test paper attribute information; Analyze the similar test paper set to obtain test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be grouped; Retrieving similar test questions in the test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions; The retrieved similar test questions are combined into a test paper; The retrieving similar test paper sets in the test paper library according to the test paper attribute information comprises: The test paper attribute information includes region, grade, subject and semester information; Using the set region, grade, subject, and semester information as the filtering conditions, similar test paper sets with matching region, grade, subject, and semester information tags are retrieved from the test paper database; The test paper structure information of the test paper to be grouped obtained by analyzing the similar test paper set includes: Analyze the test paper structure information of each test paper in the similar test paper set, wherein the test paper structure information includes question type distribution, the number of questions of each question type, and the question score; Comprehensively analyze the test paper structure information of each test paper and predict the question type distribution, the number of questions of each question type and the question score of the test paper to be composed through preset rules; The preset rules are system voting rules or weighted mean calculation conditions; The information of test questions and knowledge points obtained by analyzing the similar test paper set to be grouped includes: Obtain the test knowledge point labels corresponding to the same question types and question numbers in each test paper set; The knowledge points to be tested for each question in the test paper to be compiled are predicted by system voting based on the knowledge point labels of each question. The difficulty information of the test questions in the test paper obtained by analyzing the similar test paper set includes: Get the question difficulty value labels corresponding to the questions of the same question type and question number in each test paper set; The difficulty value of each question in the test paper to be grouped is predicted by calculating the weighted average of the difficulty value labels of each question.

2. A test paper composition method based on test paper information according to claim 1, characterized in that: The method of searching similar test questions in the test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions includes: By using the predicted question types, question-tested knowledge points, and question difficulty values ​​as screening conditions, searching is performed in the question bank; Filter out similar test questions that meet the test type, knowledge points tested and difficulty value.

3. A test paper composition method based on test paper information according to claim 2, characterized in that: The similar test questions retrieved are grouped into test papers according to the test paper structure information, including: Divide the retrieved similar test questions into corresponding question type sections according to the question type distribution in the test paper structure information; Based on the number of questions in each question type, the knowledge points tested by each question, and the difficulty value of each question, similar questions in each question type section are screened and sorted to complete the test paper.

4. A test paper composition method based on test paper information according to claim 3, characterized in that: If there are multiple similar questions with the same question number in the same question type, one of the questions will be randomly selected or a question with higher popularity among the similar questions will be selected.

5. A test paper assembling device based on test paper information, characterized in that: include: Input module, obtains the test paper attribute information of the test paper to be composed; An examination paper retrieval module searches for similar examination paper sets in the examination paper database according to the examination paper attribute information; An analysis module analyzes the similar test paper set to obtain test paper structure information, test question knowledge point information, and test question difficulty information of the test paper to be grouped; A test question retrieval module searches for similar test questions in a test question bank using the test paper structure information, test question knowledge point information, and test question difficulty information as screening conditions; and the test paper composition module, which composes the retrieved similar test questions into a test paper; The retrieving similar test paper sets in the test paper library according to the test paper attribute information comprises: The test paper attribute information includes region, grade, subject and semester information; Using the set region, grade, subject, and semester information as the filtering conditions, similar test paper sets with matching region, grade, subject, and semester information tags are retrieved from the test paper database; The test paper structure information of the test paper to be grouped obtained by analyzing the similar test paper set includes: Analyze the test paper structure information of each test paper in the similar test paper set, wherein the test paper structure information includes question type distribution, the number of questions of each question type, and the question score; Comprehensively analyze the test paper structure information of each test paper and predict the question type distribution, the number of questions of each question type and the question score of the test paper to be composed through preset rules; The preset rules are system voting rules or weighted mean calculation conditions; The information of test questions and knowledge points obtained by analyzing the similar test paper set to be grouped includes: Obtain the test knowledge point labels corresponding to the same question types and question numbers in each test paper set; The knowledge points to be tested for each question in the test paper to be compiled are predicted by system voting based on the knowledge point labels of each question. The difficulty information of the test questions in the test paper obtained by analyzing the similar test paper set includes: Get the question difficulty value labels corresponding to the questions of the same question type and question number in each test paper set; The difficulty value of each question in the test paper to be grouped is predicted by calculating the weighted average of the difficulty value labels of each question.

6. A storage medium, characterized in that A computer executable program is stored, and when the computer executable program is executed, a test paper composition method based on test paper information as described in any one of claims 1 to 4 is implemented.

Images