Method and device for intelligently generating test questions

Abstract

The invention discloses an intelligent test question generation method and device, and the method comprises the steps: firstly screening a test question list meeting a preset condition from a question bank, and determining the user information of a test applicant; according to the user information of the person to be tested, the post relevancy of each test question in the multiple test questions is calculated; calculating a weighted average probability value of each test question according to the post correlation of each test question and the historical occurrence probability of each test question; further according to the weighted average probability value of each test question, calculating to obtain a probability value of occurrence of each test question as an examination question; and finally, according to the probability value of occurrence of each test question as the test question and the target number of the test paper questions, generating the test questions matched with the user information of the test applicant. According to the technical scheme, through storage and statistical calculation of the occurrence probability of the historical test questions, the occurrence randomness of the examination questions is realized, and the comprehensive coverage of the examination content is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a method and device for intelligently generating test questions. Background Art

[0002] Regularly testing employees' business knowledge and operational skills through examinations and random tests to ensure that employees master and follow the standard procedures of banking business and reduce operational errors and violations is an important means for commercial banks to ensure business quality, strengthen risk management and improve service levels.

[0003] Currently, the scope of examinees and the question bank for random tests of branch personnel are usually set by the administrator, and the test questions are generated by the system program using random functions.

[0004] Due to computer program reasons, some questions appear frequently, some questions are rarely drawn, and the coverage of the test content is low. Summary of the invention

[0005] In view of this, the present application provides a method and device for intelligently generating test questions, aiming to reduce the probability of repeated questions and improve the comprehensive coverage of test content.

[0006] In a first aspect, the present application provides a method for intelligently generating test questions, the method comprising:

[0007] Screening a list of test questions that meet preset conditions from a question bank, and determining user information of a test taker; the test question list includes a plurality of test questions, and the user information of the test taker includes information about the institution to which the test taker belongs and information about the position of the test taker;

[0008] Calculating the job relevance of each of the multiple test questions according to the user information of the test taker;

[0009] Calculate the weighted average probability value of each test question according to the job relevance of each test question and the historical occurrence probability of each test question;

[0010] Calculate the probability value of each test question appearing as a test question according to the weighted average probability value of each test question;

[0011] According to the probability value of each test question appearing as a test question and the target number of test paper questions, test questions matching the user information of the test taker are generated.

[0012] Optionally, screening a list of test questions that meet preset conditions from the question bank includes:

[0013] According to the test configuration parameters, a list of test questions that meet the test configuration parameters is screened from a question bank; wherein the test configuration parameters include test difficulty level and test scope information.

[0014] Optionally, the calculating, based on the weighted average probability value of each test question, the probability value of each test question appearing as an examination question comprises:

[0015] Circularly calculating the weighted average probability value of each test question, normalizing the weighted average probability value of each test question, and obtaining the normalized value of each test question;

[0016] The normalized value of each test question is used as the probability value of each test question appearing as an examination question.

[0017] Optionally, generating test questions matching the user information of the examinee according to the probability value of each test question appearing as a test question and the target number of test questions includes:

[0018] Sorting the probability value of each test question appearing as a test question from large to small to obtain a sorted test question probability value;

[0019] According to the ranked test question probability values ​​and the target number of test questions, a random function is used to generate test questions that match the user information of the test taker.

[0020] Optionally, after generating the test questions matching the user information of the test taker, the method further includes:

[0021] The probability value of each test question appearing as a test question is stored in a database.

[0022] In a second aspect, the present application provides an intelligent test question generation device, the device comprising:

[0023] A screening module is used to screen a list of test questions that meet preset conditions from a question bank, and determine the user information of the examinee; the list of test questions includes a plurality of test questions, and the user information of the examinee includes the information of the institution to which the examinee belongs and the position information of the examinee;

[0024] A calculation module, used for calculating the job relevance of each of the multiple test questions according to the user information of the test taker;

[0025] The calculation module is further used to calculate the weighted average probability value of each test question according to the job relevance of each test question and the historical occurrence probability of each test question;

[0026] The calculation module is further used to calculate the probability value of each test question appearing as a test question according to the weighted average probability value of each test question;

[0027] A generation module is used to generate test questions that match the user information of the examinee according to the probability value of each test question appearing as a test question and the target number of test questions.

[0028] Optionally, the device further includes a parameter configuration module;

[0029] The parameter configuration module is used to manage and maintain system parameters.

[0030] Optionally, the device further comprises an information import module;

[0031] The information import module is used to realize the functions of importing, editing and deleting the list of candidates.

[0032] Optionally, the device further comprises a question bank import module;

[0033] The question bank import module is used to implement the import, editing and deletion functions of the test alternative questions.

[0034] Optionally, the device further comprises a historical data processing module;

[0035] The historical data processing module is used to store the probability value of each test question appearing as a test question in a database.

[0036] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:

[0037] A memory for storing one or more programs;

[0038] Processor; when the one or more programs are executed by the processor, the intelligent test question generation method described in any one of the first aspects above is implemented.

[0039] In a fourth aspect, an embodiment of the present application provides a computer storage medium, in which a program is stored. When the program is executed by a processor, the intelligent test question generation method described in any one of the first aspects is implemented.

[0040] The above technical solution has the following beneficial effects:

[0041] The present application provides a method and device for intelligently generating test questions. When executing the method, first, a list of test questions that meet preset conditions is screened from a question bank, and the user information of the examinee is determined; wherein the list of test questions includes multiple test questions, and the user information of the examinee includes the information of the institution to which the examinee belongs and the position information of the examinee; then, according to the user information of the examinee, the position relevance of each test question in the multiple test questions is calculated respectively; then, according to the position relevance of each test question and the historical occurrence probability of each test question, the weighted average probability value of each test question is calculated; further, according to the weighted average probability value of each test question, the probability value of each test question appearing as a test question is calculated; finally, according to the probability value of each test question appearing as a test question and the target number of test paper questions, the test questions that match the user information of the examinee are generated. Through the above technical scheme, the present application generates test questions that match the tester's position by calculating the matching degree between the test question and the examinee's position, avoiding the situation where the test question is irrelevant to the actual work of the examinee. Moreover, by storing and statistically calculating the probability of occurrence of historical test questions, the randomness of the test questions can be achieved, which can prevent test takers from encountering test questions with the same probability in multiple tests, reduce the probability of repeated questions, and improve the comprehensive coverage of test content. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A flow chart of the intelligent generation method of test questions provided in the embodiment of the present application;

[0044] Figure 2 A structural schematic diagram of the intelligent generation device of test questions provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0046] In order to facilitate further understanding of the technical solution provided by this application, the background technology involved in this application will be explained below.

[0047] At present, common test sampling is usually generated by system programs using random functions. Randomly generated test questions are often not highly matched with the specific positions of branch personnel and cannot meet the needs of job integration; at the same time, because the probability of questions being drawn from the question bank cannot be controlled, some of the same questions may appear repeatedly over a period of time, while some questions rarely appear.

[0048] That is, the current test sampling method cannot meet the needs of generating matching test questions for different positions in the job integration scenario, nor can it adjust the probability of a question appearing again based on the historical appearance of the question, and cannot meet the need for comprehensive coverage of the test content.

[0049] In order to overcome the above technical problems, the embodiment of the present application provides an intelligent generation method of test questions, firstly, a list of test questions that meet the preset conditions is screened from the question bank, and the user information of the examinee is determined; wherein, the list of test questions includes multiple test questions, and the user information of the examinee includes the information of the institution to which the examinee belongs and the position information of the examinee; then, according to the user information of the examinee, the position relevance of each test question in the multiple test questions is calculated respectively; then, according to the position relevance of each test question and the historical occurrence probability of each test question, the weighted average probability value of each test question is calculated; further, according to the weighted average probability value of each test question, the probability value of each test question appearing as a test question is calculated; finally, according to the probability value of each test question appearing as a test question and the target number of test paper questions, the test questions that match the user information of the examinee are generated. Through the above technical scheme, the present application generates test questions that match the tester's position by calculating the matching degree between the test question and the examiner's position, avoiding the situation where the test question is irrelevant to the actual work of the examinee. Moreover, by storing and statistically calculating the probability of occurrence of historical test questions, the randomness of the test questions can be achieved, which can prevent test takers from encountering test questions with the same probability in multiple tests, reduce the probability of repeated questions, and improve the comprehensive coverage of test content.

[0050] The method of the embodiment of the present invention can be executed by an intelligent test question generation device, which can be implemented by software and / or hardware and can generally be integrated into a server or terminal device.

[0051] See also Figure 1 , Figure 1 A flow chart of the intelligent generation method of test questions provided in an embodiment of the present application.

[0052] The method may include:

[0053] Step S101: screening a list of test questions that meet preset conditions from a question bank, and determining user information of an examinee; the list of test questions includes a plurality of test questions, and the user information of the examinee includes information about the institution to which the examinee belongs and information about the position of the examinee.

[0054] In this step, the intelligent generation device for test questions first preliminarily screens a list of test questions that meet preset conditions from the question bank, wherein the screened list of test questions includes multiple test questions.

[0055] The intelligent generation device of the test questions determines the user information of the examinee, and the user information of the examinee includes the information of the institution to which the examinee belongs and the position information of the examinee.

[0056] The candidate's institution information refers to the institution to which the candidate belongs, and the candidate's position information refers to the position or job the candidate holds in the institution, which is used to evaluate the candidate's professional knowledge and ability level.

[0057] It should be noted that the preset conditions refer to the criteria used when selecting test questions, such as the difficulty, type, and knowledge points of the test questions. The preset conditions can be set according to the purpose and requirements of the test.

[0058] In a possible implementation, the step of selecting a list of test questions that meet preset conditions from a test bank includes:

[0059] According to the test configuration parameters, a list of test questions that meet the test configuration parameters is screened from the question bank; wherein the test configuration parameters may include test difficulty level and test scope information.

[0060] In this embodiment, the question bank is a resource library containing a large number of test questions, and these test questions can be classified according to different levels of difficulty, type, knowledge points, etc.

[0061] According to the test configuration parameters, a list of test questions that meet the test configuration parameters is screened from the question bank for subsequent calculation of the job relevance of the test questions.

[0062] Step S102: Calculate the job relevance of each of the multiple test questions based on the user information of the test taker.

[0063] In this step, after screening the list of test questions that meet the preset conditions and determining the user information of the examinee in step S101, the job relevance of each test question in the plurality of test questions is calculated based on the user information of the examinee.

[0064] The calculation formula is as follows:

[0065]

[0066] Among them, U and Q represent the user position set and the topic position set respectively, and the two are aligned in the position dimension. i and Q i represents the value of the set U and Q in the i-th position, and n represents the number of positions. If the i-th position exists in U, then U i is equal to the current position relevance set in the exam, otherwise it is equal to 0; if the i-th position exists in Q, then Q i is equal to 1, otherwise it is equal to 0.

[0067] It should be noted that the embodiment of the present application generates test questions that match the positions of the test personnel by calculating the matching degree between the test questions and the positions of the test personnel, thereby avoiding the situation where the test questions are irrelevant to the actual work of the test personnel.

[0068] Step S103: Calculate the weighted average probability value of each test question according to the job relevance of each test question and the historical occurrence probability of each test question.

[0069] In this step, after the job relevance of each of the multiple test questions is calculated in step S102, the weighted average probability value of each test question is calculated according to the job relevance of each test question and the historical occurrence probability of each test question.

[0070]

[0071] in, is the probability of occurrence of this question, P1, P2, P3...P n W1, W2, W3...W are the probability of the question appearing once, twice, three times, or n times before. The probability of the question appearing for the first time is δ, and δ is the calculated job relevance of the question. n is the weighting coefficient of the previous, second, third, and nth test questions, W is an exponential decay function, and the specific calculation rules are as follows:

[0072] If the current question is drawn for the nth time, then

[0073] If the current question is not drawn for the nth time, then

[0074] It should be noted that n can be adjusted as needed. For example, if the examination frequency is once a month and if only the examination situation in the past year is concerned, n can be 12.

[0075] It can be understood that the present application achieves the randomness of the appearance of test questions by storing and statistically calculating the probability of appearance of historical test questions, thereby preventing test takers from encountering test questions with the same probability in multiple tests.

[0076] Step S104: Calculate the probability value of each test question appearing as a test question based on the weighted average probability value of each test question.

[0077] After the weighted average probability value of each test question is calculated in step S103, the probability value of each test question appearing as a test question is further calculated based on the weighted average probability value of each test question.

[0078] In a possible implementation, calculating the probability value of each test question appearing as a test question according to the weighted average probability value of each test question includes:

[0079] Circularly calculating the weighted average probability value of each test question, normalizing the weighted average probability value of each test question, and obtaining the normalized value of each test question;

[0080] The normalized value of each test question is used as the probability value of each test question appearing as an examination question.

[0081] Specifically, the probability of each question appearing in the question bank is calculated cyclically, and then the probability of all questions appearing is normalized. The processed value is used as the final probability of the question appearing. The processing method is as follows:

[0082]

[0083] Among them, P i is the weighted average probability value of the ith question, pr i is the normalized probability.

[0084] Step S105: generating test questions that match the user information of the examinee according to the probability value of each test question appearing as a test question and the target number of test questions.

[0085] After the probability value of each test question appearing as a test question is calculated, test questions matching the user information of the examinee are generated according to the probability value of each test question appearing as a test question and the target number of test paper questions.

[0086] In a possible implementation, generating the test questions matching the user information of the examinee according to the probability value of each test question appearing as a test question and the target number of test questions includes:

[0087] Sorting the probability value of each test question appearing as a test question from large to small to obtain a sorted test question probability value;

[0088] According to the ranked test question probability values ​​and the target number of test questions, a random function is used to generate test questions that match the user information of the test taker.

[0089] Specifically, the probability values ​​of each test question appearing as a test question are sorted from large to small to obtain the sorted test question probability values; using a random function, pr i To determine whether to select the current question randomly by probability until the target number of test questions is met, the specific method is as follows:

[0090] If random() ≤ pr i , then the i-th question is drawn, otherwise it is not drawn.

[0091] It can be seen from the above technical scheme that the present application firstly selects a list of test questions that meet the preset conditions from the question bank, and determines the user information of the examinee; wherein the test question list includes multiple test questions, and the user information of the examinee includes the information of the institution to which the examinee belongs and the position information of the examinee; then, according to the user information of the examinee, the position relevance of each test question in the multiple test questions is calculated respectively; then, according to the position relevance of each test question and the historical occurrence probability of each test question, the weighted average probability value of each test question is calculated; further, according to the weighted average probability value of each test question, the probability value of each test question appearing as a test question is calculated; finally, according to the probability value of each test question appearing as a test question and the target number of test questions, the test questions that match the user information of the examinee are generated. Through the above technical scheme, the present application generates test questions that match the tester's position by calculating the matching degree between the test question and the examinee's position, avoiding the situation where the test question is irrelevant to the actual work of the examinee. Moreover, by storing and statistically calculating the probability of occurrence of historical test questions, the randomness of the test questions can be achieved, which can prevent test takers from encountering test questions with the same probability in multiple tests, reduce the probability of repeated questions, and improve the comprehensive coverage of test content.

[0092] In a possible implementation, after generating the test questions matching the user information of the test taker, the method further includes:

[0093] The probability value of each test question appearing as a test question is stored in a database.

[0094] In this embodiment, the probability value of each test question appearing as a test question is stored in a database for easy calculation and use next time.

[0095] For the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0096] The above are some specific implementations of the intelligent generation method of test questions provided in the embodiment of the present application. Based on this, the present application also provides a corresponding device. The intelligent generation device of test questions provided in the embodiment of the present application will be introduced from the perspective of functional modularization.

[0097] See also Figure 2 , is a structural schematic diagram of an intelligent generation device for test questions provided in an embodiment of the present application, the device comprising:

[0098] The screening module 201 is used to screen a list of test questions that meet preset conditions from the question bank and determine the user information of the examinee; the list of test questions includes a plurality of test questions, and the user information of the examinee includes the information of the institution to which the examinee belongs and the position information of the examinee;

[0099] A calculation module 202, configured to calculate the job relevance of each of the plurality of test questions according to the user information of the test taker;

[0100] The calculation module 202 is further used to calculate the weighted average probability value of each test question according to the job relevance of each test question and the historical occurrence probability of each test question;

[0101] The calculation module 202 is further used to calculate the probability value of each test question appearing as a test question according to the weighted average probability value of each test question;

[0102] The generating module 203 is used to generate the test questions matching the user information of the test taker according to the probability value of each test question appearing as a test question and the target number of test questions.

[0103] It can be seen from the above technical scheme that the embodiment of the present application first screens a list of test questions that meet the preset conditions from the question bank, and determines the user information of the examinee; wherein the test question list includes multiple test questions, and the user information of the examinee includes the information of the institution to which the examinee belongs and the position information of the examinee; then, according to the user information of the examinee, the position relevance of each test question in the multiple test questions is calculated respectively; then, according to the position relevance of each test question and the historical occurrence probability of each test question, the weighted average probability value of each test question is calculated; further, according to the weighted average probability value of each test question, the probability value of each test question appearing as an exam question is calculated; finally, according to the probability value of each test question appearing as an exam question and the target number of test paper questions, the test questions that match the user information of the examinee are generated. Through the above technical scheme, the present application generates test questions that match the tester's position by calculating the matching degree between the test question and the examinee's position, avoiding the situation where the test question is irrelevant to the actual work of the examinee. Moreover, by storing and statistically calculating the probability of occurrence of historical test questions, the randomness of the test questions can be achieved, which can prevent test takers from encountering test questions with the same probability in multiple tests, reduce the probability of repeated questions, and improve the comprehensive coverage of test content.

[0104] Optionally, the device further includes a parameter configuration module; the parameter configuration module is used to manage and maintain system parameters.

[0105] It can be understood that the main function of the parameter configuration module is to uniformly manage and maintain the parameters required for the operation of the device and the various parameters relied on during the operation of the intelligent test question generation device, and to provide a web-side display interface for other modules to query. The main parameters are shown in Table 1, including:

[0106]

[0107] Table 1

[0108] Optionally, the device further comprises an information import module;

[0109] The information import module is used to realize the functions of importing, editing and deleting the list of candidates.

[0110] Specifically, the information import module mainly provides the function of maintaining the list of examinees. Users can use this module to import, edit and delete the list of examinees. In the job fusion scenario, users can have multiple jobs. The imported elements are shown in Table 2, including:

[0111]

[0112] Table 2

[0113] Optionally, the device further comprises a question bank import module; the question bank import module is used to implement the functions of importing, editing and deleting alternative examination questions.

[0114] Specifically, the question bank import module mainly provides the function of maintaining the exam question bank. Users can use this module to import, edit and delete the exam alternative questions. The imported elements are shown in Table 3, including:

[0115]

[0116]

[0117] Table 3

[0118] Optionally, the device further comprises a historical data processing module;

[0119] The historical data processing module is used to store the probability value of each test question appearing as a test question in a database.

[0120] An embodiment of the present application further provides an electronic device, comprising: a memory for storing one or more programs;

[0121] Processor; when the one or more programs are executed by the processor, the intelligent generation method of test questions described in the above embodiment is implemented.

[0122] An embodiment of the present application also provides a computer storage medium, in which a program is stored. When the program is executed by a processor, the intelligent generation method of test questions described in the above embodiment is implemented.

[0123] The "first" and "second" in the names such as "first" and "second" (if any) mentioned in the embodiments of the present application are only used as name identifiers and do not represent the first or second in order.

[0124] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0125] Those skilled in the art can understand that the flowchart shown in the figure is only an example in which the embodiments of the present application can be implemented, and the scope of application of the embodiments of the present application is not limited by any aspect of the flowchart.

[0126] In the several embodiments provided in the present application, it should be understood that the disclosed methods, devices and equipment can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0127] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0128] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0129] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligently generating test questions, characterized in that: The method comprises: Screening a list of test questions that meet preset conditions from a question bank, and determining user information of a test taker; the test question list includes a plurality of test questions, and the user information of the test taker includes information about the institution to which the test taker belongs and information about the position of the test taker; Calculating the job relevance of each of the multiple test questions according to the user information of the test taker; Calculate the weighted average probability value of each test question according to the job relevance of each test question and the historical occurrence probability of each test question; Calculate the probability value of each test question appearing as a test question according to the weighted average probability value of each test question; According to the probability value of each test question appearing as a test question and the target number of test paper questions, test questions matching the user information of the test taker are generated.

2. The method according to claim 1, characterized in that The step of selecting a list of test questions that meet preset conditions from the question bank includes: According to the test configuration parameters, a list of test questions that meet the test configuration parameters is screened from a question bank; wherein the test configuration parameters include test difficulty level and test scope information.

3. The method according to claim 1, characterized in that The step of calculating the probability value of each test question appearing as an examination question according to the weighted average probability value of each test question comprises: Circularly calculating the weighted average probability value of each test question, normalizing the weighted average probability value of each test question, and obtaining the normalized value of each test question; The normalized value of each test question is used as the probability value of each test question appearing as an examination question.

4. The method according to claim 1, characterized in that: Generating test questions matching the user information of the test taker according to the probability value of each test question appearing as a test question and the target number of test questions includes: Sorting the probability value of each test question appearing as a test question from large to small to obtain a sorted test question probability value; According to the ranked test question probability values ​​and the target number of test questions, a random function is used to generate test questions that match the user information of the test taker.

5. The method according to claim 1, characterized in that After generating the test questions matching the user information of the test taker, the method further includes: The probability value of each test question appearing as a test question is stored in a database.

6. An intelligent test question generation device, characterized in that: The device comprises: A screening module is used to screen a list of test questions that meet preset conditions from a question bank, and determine the user information of the examinee; the list of test questions includes a plurality of test questions, and the user information of the examinee includes the information of the institution to which the examinee belongs and the position information of the examinee; A calculation module, used for calculating the job relevance of each of the multiple test questions according to the user information of the test taker; The calculation module is further used to calculate the weighted average probability value of each test question according to the job relevance of each test question and the historical occurrence probability of each test question; The calculation module is further used to calculate the probability value of each test question appearing as a test question according to the weighted average probability value of each test question; A generation module is used to generate test questions that match the user information of the examinee according to the probability value of each test question appearing as a test question and the target number of test questions.

7. The device according to claim 6, characterized in that The device also includes a parameter configuration module; The parameter configuration module is used to manage and maintain system parameters.

8. The device according to claim 6, characterized in that The device also includes an information import module; The information import module is used to realize the functions of importing, editing and deleting the list of candidates.

9. The device according to claim 6, characterized in that The device also includes a question bank import module; The question bank import module is used to implement the import, editing and deletion functions of the test alternative questions.

10. The device according to claim 6, characterized in that The device also includes a historical data processing module; The historical data processing module is used to store the probability value of each test question appearing as a test question in a database.

Images