Test question generation method and device, electronic device, storage medium

Abstract

Embodiments of the present disclosure provide a method and apparatus for generating test questions, an electronic device, and a storage medium, which relate to the field of artificial intelligence technology. The method for generating test questions includes: obtaining question bank data; performing answer collection processing on the question bank data to obtain user question bank answering data; performing answer analysis processing on the user question bank answering data to obtain the answer concentration degree of the user question bank answering data; performing screening processing on the question bank data according to the answer concentration degree to obtain test question data; and performing matching processing according to the user question bank answering data to obtain initial answer data corresponding to the test question data. The method for generating test questions provided by the embodiments of the present disclosure can improve the generation efficiency of test questions.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular, to a method and device for generating test questions, an electronic device, and a storage medium. Background Art

[0002] Crowdsourcing products require users to complete tasks related to text entry. To prevent users from maliciously and randomly submitting task answers and affecting system answer collection, crowdsourcing products generally have a test question mechanism. The operation staff adds test questions similar to ordinary entry tasks to the system, including the correct answers to the test questions. These questions will be mixed in with ordinary entry tasks without the user's awareness. If a user gets the test questions wrong multiple times, it is determined that the user has abnormal behavior and relevant penalties are imposed.

[0003] The current configuration mechanism of test questions is still manual configuration, and there is a low efficiency in generating test questions. Summary of the Invention

[0004] The main purpose of the embodiments of the present disclosure is to propose a method and device for generating test questions, an electronic device, and a storage medium, which can improve the efficiency of generating test questions.

[0005] To achieve the above object, a first aspect of the embodiments of the present disclosure proposes a method for generating test questions, including:

[0006] Obtain question bank data;

[0007] Perform answer collection processing on the question bank data to obtain user question bank answering data;

[0008] Perform answer analysis processing on the user question bank answering data to obtain the answer concentration degree of the user question bank answering data;

[0009] Perform screening processing on the question bank data according to the answer concentration degree to obtain test question data;

[0010] Perform matching processing according to the user question bank answering data to obtain initial answer data corresponding to the test question data.

[0011] In some embodiments, the method further includes:

[0012] Dispatch the test question data to a question answering task queue, collect test answers of users for the test question data in the question answering task queue, and use the test answers as user test answering data;

[0013] Perform discrimination processing on the user test answering data according to the initial answer data to obtain answering result data;

[0014] Correct the initial answer data according to the answer result data to obtain the target answer data.

[0015] In some embodiments, the answer result data includes answering errors; the step of correcting the initial answer data according to the answer result data to obtain the target answer data includes:

[0016] If the answer result data is the answering error, perform penalty matching processing according to preset penalty rule information to obtain answering penalty information;

[0017] Perform penalty processing according to the answering penalty information and collect dissenting evaluations of the user's feedback on the penalty processing;

[0018] Detect the appeal information of the user's feedback according to the dissenting evaluation;

[0019] Perform answer analysis processing on the initial answer data according to the appeal information to obtain the answer analysis result of the initial answer data, and the answer analysis result includes ratio information and standard deviation information;

[0020] Perform answer matching processing according to the answer analysis result to obtain the target answer data.

[0021] In some embodiments, the step of performing answer matching processing according to the answer analysis result to obtain the target answer data includes:

[0022] If the answer analysis result meets the first condition, use the answer corresponding to the first condition as the target answer data; the first condition is that the ratio information of the answer with the largest ratio information is greater than or equal to the first threshold.

[0023] In some embodiments, the step of performing answer matching processing according to the answer analysis result to obtain the target answer data includes:

[0024] If the answer analysis result meets the second condition, use the two answers corresponding to the second condition as the target answer data; the second condition is that the ratio information of all answers is less than the second threshold, the total ratio of the two answers with the largest ratio information is greater than or equal to the first threshold, and the standard deviation information of the answers is greater than the third threshold.

[0025] In some embodiments, the step of performing answer matching processing according to the answer analysis result to obtain the target answer data includes:

[0026] If the answer analysis result does not meet the first condition and the second condition, perform manual discrimination processing on the test question data corresponding to the appeal information to obtain the target answer data.

[0027] In some embodiments, the method further includes:

[0028] Performing a search process according to the target answer data to obtain misjudged questions; the misjudged questions are the test question data misjudged by the initial answer data;

[0029] Performing a compensation process on the user corresponding to the misjudged questions according to preset compensation rule information.

[0030] To achieve the above object, a second aspect of the present disclosure provides a test question generation device, including:

[0031] A question bank data acquisition module for acquiring question bank data;

[0032] An answer collection module for performing an answer collection process on the question bank data to obtain user question bank answering data;

[0033] An answer analysis module for performing an answer analysis process on the user question bank answering data to obtain the answer concentration degree of the user question bank answering data;

[0034] A screening module for screening the question bank data according to the answer concentration degree to obtain test question data;

[0035] A matching module for performing a matching process according to the user question bank answering data to obtain initial answer data corresponding to the test question data.

[0036] To achieve the above object, a third aspect of the present disclosure provides an electronic device, including:

[0037] At least one memory;

[0038] At least one processor;

[0039] At least one program;

[0040] The program is stored in the memory, and the processor executes the at least one program to implement the method as described in the first aspect of the present disclosure.

[0041] To achieve the above object, a fourth aspect of the present disclosure provides a storage medium, which is a computer-readable storage medium, and the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute:

[0042] The method as described in the first aspect above.

[0043] The test question generation method and device, electronic device, and storage medium provided by the embodiments of the present disclosure obtain question bank data and perform answer collection processing on the question bank data to obtain user question bank answering data. Then, answer analysis processing is performed on the user question bank answering data to obtain the answer concentration of the user question bank answering data. Furthermore, the question bank data is screened based on the answer concentration to obtain test question data. Finally, matching processing is performed based on the user question bank answering data to obtain initial answer data corresponding to the test question data. Through the technical solution provided by the embodiments of the present disclosure, the generation efficiency of test questions can be improved, the dependence on operation personnel in the test question release process can be eliminated, the operation cost can be reduced, the threshold for releasing new question types can be lowered, and it is ensured that test questions cannot be easily recognized by test users. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flowchart of the test question generation method provided by the embodiments of the present disclosure.

[0045] Figure 2 is a partial flowchart of the test question generation method provided by another embodiment of the present disclosure.

[0046] Figure 3 is Figure 2 a flowchart of step S230 in

[0047] Figure 4 is Figure 3 a flowchart of step S350 in

[0048] Figure 5 is a partial flowchart of the test question generation method provided by another embodiment of the present disclosure.

[0049] Figure 6 is a schematic hardware structure diagram of the electronic device provided by the embodiments of the present disclosure.

[0050] Reference numerals: processor 601, memory 602, input / output interface 603, communication interface 604, bus 605. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following further describes the present application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] It should be noted that although the functional modules are divided in the device schematic diagram and the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in a different module division from that in the device or a different sequence from that in the flowchart. Terms such as "first" and "second" in the specification, claims, and the above-mentioned drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this invention belongs. The terms used herein are only for the purpose of describing embodiments of the present invention and are not intended to limit the present invention.

[0054] First, the following explanations are made for several terms involved in this application:

[0055] Crowdsourcing: Crowdsourcing refers to the practice of a company or organization outsourcing work tasks that were previously performed by employees to non-specific volunteer members of the public in a free and voluntary manner. Through the Internet, product development requirements are surveyed, and tasks are distributed based on the real usage experiences of users. Crowdsourcing tasks are usually undertaken by individuals, but if they involve tasks that require multiple people to collaborate to complete, they may also appear in the form of relying on open-source individual production.

[0056] Current crowdsourcing products require users to complete tasks related to text entry. To prevent users from maliciously and randomly submitting task answers and affecting the system's answer collection, crowdsourcing products generally have a test question mechanism. The operation staff add test questions similar to ordinary entry tasks to the system, including the correct answers to the test questions. These questions will be mixed in with ordinary entry tasks without the users' awareness. If a user answers the test questions incorrectly multiple times, it is determined that the user has abnormal behavior and relevant penalties are imposed.

[0057] The current methods for generating test questions mainly have the following problems: (1) When each question type is released, a batch of test questions with undisputed answers must be prepared and added to the system, which greatly increases the threshold for releasing new question types; (2) As the time for test questions to enter the system increases, users will definitely be more and more likely to recognize the test questions they have encountered before, resulting in the failure of the test mechanism. Therefore, it is necessary to manually replace the test questions regularly, increasing the operation cost; (3) Once the correct answers to the test questions are set incorrectly, users who encounter this test question will be wrongly punished, affecting the user experience. As a result, the generation efficiency of test questions is relatively low and the answer accuracy rate of test questions is relatively low.

[0058] Based on this, the embodiments of the present disclosure provide a test question generation method, an apparatus, an electronic device, and a storage medium, which can improve the generation efficiency of test questions, get rid of the dependence on operation personnel in the test question release process, reduce the operation cost, lower the threshold for releasing new question types, ensure that test questions cannot be easily recognized by test users, and at the same time improve the accuracy of the answers corresponding to the test questions and reduce the misjudgment of questions.

[0059] The embodiments of the present disclosure provide a test question generation method, an apparatus, an electronic device, and a storage medium, which will be specifically described through the following embodiments. First, the test question generation method in the embodiments of the present disclosure will be described.

[0060] The embodiments of the present application can obtain and process relevant data based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technology, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0061] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0062] The test question generation method provided by the embodiments of the present disclosure relates to the field of artificial intelligence / machine learning technology, and particularly relates to the field of data mining technology. The test question generation method provided by the embodiments of the present disclosure can be applied to a terminal, or to a server side, or can also be software running on a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, or a smart watch, etc.; the server can be an independent server, or can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms; the software can be an application that implements the question recommendation method, etc., but is not limited to the above forms.

[0063] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0064] An embodiment of the present disclosure provides a method for generating test questions, including: obtaining question bank data; performing answer collection processing on the question bank data to obtain user question bank answering data; performing answer analysis processing on the user question bank answering data to obtain the answer concentration of the user question bank answering data; performing screening processing on the question bank data according to the answer concentration to obtain test question data; and performing matching processing according to the user question bank answering data to obtain initial answer data corresponding to the test question data.

[0065] Figure 1 is an optional flowchart of the method for generating test questions provided by the embodiment of the present disclosure, Figure 1 The method in may include but is not limited to steps S110 to S150, specifically including:

[0066] S110, obtaining question bank data;

[0067] S120, performing answer collection processing on the question bank data to obtain user question bank answering data;

[0068] S130, performing answer analysis processing on the user question bank answering data to obtain the answer concentration of the user question bank answering data;

[0069] S140, performing screening processing on the question bank data according to the answer concentration to obtain test question data;

[0070] S150, performing matching processing according to the user question bank answering data to obtain initial answer data corresponding to the test question data.

[0071] In step S110, the question bank data is a task for the crowdsourcing product to collect information such as personal information, research results, ideas, etc. from users. Such tasks exist in the form of questions. The system publishes these tasks in the form of questions to users and obtains the answers of users to these questions to complete a relatively large-scale task.

[0072] In step S120, the collection and processing means that the system publishes these tasks in the form of questions to users and collects the answers of users to these questions; the user question bank answering data is the answers of users to these questions.

[0073] In step S130, the system performs answer analysis and processing on the user question bank answering data of all collected users. In a specific embodiment, the answer analysis and processing includes counting all the answers of each test question data and calculating the answer concentration degree of each user question bank answering data corresponding to each test question data. Specifically, the answer concentration degree characterizes the concentration degree of each answer of the test question data. The larger the ratio information of the test question, the higher the answer concentration degree of the test question data, where the ratio information is the ratio of the number of answers to this answer to the total number of users who answer this test question.

[0074] For example, the answers to question bank data 1 include answer A, answer B, answer C, and answer D, where the ratio information of answer A is 0.4; the ratio information of answer B is 0.3; the ratio information of answer C is 0.2; the ratio information of answer D is 0.1.

[0075] For another example, the answers to question bank data 2 include answer E, answer F, answer G, and answer H, where the ratio information of answer E is 0.7; the ratio information of answer F is 0.1; the ratio information of answer H is 0.1; the ratio information of answer G is 0.1.

[0076] In step S140, the screening processing method includes but is not limited to: selecting the question bank data with a higher answer concentration degree among all the answers as the test question data.

[0077] For example, when screening between question bank data 1 and question bank data 2, since the option with the highest ratio information in question bank data 1 is answer A, and the option with the highest ratio information in question bank data 2 is answer E, and the ratio information of answer E, 0.7, is greater than the ratio information of answer A, 0.4, the answer concentration degree of question bank data 1 is greater than that of question bank data 2. Therefore, question bank data 2 is selected as a test question data.

[0078] This application adopts this screening method, ensuring that the answers of the selected test questions are relatively concentrated, and such questions are more suitable as test questions to identify the behavior of brushing questions.

[0079] In step S150, the matching process is to match, according to the test question data filtered in step S140, the answer with the highest answer concentration among all the answers of the test question data as the initial answer data. In a specific embodiment, if the multiple-choice question bank data 2 is selected as a test question data in step S140, since the answer concentration of answer E is 0.7, which is greater than the answer concentrations of answers F, H, and G, which are 0.1, answer E is selected as the initial answer data for this test question data.

[0080] In a specific embodiment, after a user completes answering a question, there will be a certain reward. Therefore, it is very likely that some users will frequently brush questions through question-brushing tools and other means. This will not only affect the normal completion of work tasks but may also lead to the collapse of the crowdsourcing system, thus greatly affecting work efficiency. Therefore, operation personnel often manually add test questions to the question bank data. These test questions are often relatively simple and have clear answers, and it is possible to determine whether a user is brushing questions based on the user's answering situation for these questions, so as to take measures to avoid or punish the question-brushing behavior.

[0081] To improve the generation efficiency of test questions, the test question generation method provided by the embodiments of the present disclosure publishes the question bank data to a task queue, directly performs answer collection processing on the question bank data, screens out the questions with relatively concentrated answers from the question bank data as test question data, and uses the answers of the test question data as the initial answer data, thus getting rid of the dependence on operation personnel in the test question publishing process, reducing the operation cost, and improving the generation efficiency of test questions.

[0082] The test question generation method proposed by the embodiments of the present disclosure obtains the user question bank answering data by obtaining the question bank data and performing answer collection processing on the question bank data, then performs answer analysis processing on the user question bank answering data to obtain the answer concentration of the user question bank answering data, and then filters the question bank data according to the answer concentration to obtain the test question data. Finally, matching processing is performed according to the user question bank answering data to obtain the initial answer data corresponding to the test question data. Through the technical solution provided by the embodiments of the present disclosure, the generation efficiency of test questions can be improved, the dependence on operation personnel in the test question publishing process can be eliminated, the operation cost can be reduced, the threshold for releasing new question types can be lowered, and it is ensured that test questions cannot be easily recognized by test users.

[0083] In some embodiments, the method further includes: dispatching the test question data to a question answering task queue, collecting the test answers of the users for the test question data in the question answering task queue, and using the test answers as the user test answering data; performing discrimination processing on the user test answering data according to the initial answer data to obtain the answering result data; and performing correction processing on the initial answer data according to the answering result data to obtain the target answer data.

[0084] Such asFigure 2 As shown Figure 2 is a flowchart of a test question generation method provided by some other embodiments. The test question generation method further includes:

[0085] S210. Dispatch the test question data to the answering task queue, collect the test answers of the users for the test question data in the answering task queue, and use the test answers as the user test answering data;

[0086] S220. Perform discrimination processing on the user test answering data according to the initial answer data to obtain the answering result data;

[0087] S230. Perform correction processing on the initial answer data according to the answering result data to obtain the target answer data.

[0088] In step S210, the answering task queue is the work task queue dispatched for the crowdsourcing product. Each work task is dispatched to different work queues, and different work queues correspond to different users. Therefore, the dispatch of the test question data needs to comply with the overall dispatch rules of the system tasks. Specifically, each test question data will be dispatched to each different task queue to achieve full coverage of the test question data for each user to be tested, and then obtain the answers feedback by the users for the test question data, and use this answer as the user test answering data.

[0089] Specifically, if the number of current task queues is N, then N copies are generated according to the test question data and are respectively added to N test question dispatch queues.

[0090] It should be noted that the collection principle of the user question bank answering data in step S120 is similar to that of the user test answering data in step S210, both of which are collected by using the answer feedback of the users, but their collection sequences and functions are different. Among them, the user question bank answering data is used to obtain the initial answer data; while the user test answering data is the user feedback during the test process when the question is used as the test question data, and is used to identify the users who are currently performing the question brushing behavior.

[0091] In step S220, the answering result data includes answering correctly and answering wrongly. The discrimination processing method is: if the user test answering data is consistent with the initial answer data, it is determined as answering correctly; if the user test answering data is inconsistent with the initial answer data, it is determined as answering wrongly. The answering result data is used for subsequent correction of the test question answers to obtain the target answer data.

[0092] In step S230, if the answer result data obtained in step S220 indicates an incorrect answer, the user will receive a penalty. The user can choose to file an appeal based on whether they have any objections to the penalty, thus initiating the process of correcting the initial answer information. Specifically, the correction process involves collecting all users' answer situations for the test question data to re-determine the answer to the test question data, and then correcting the initial answer data to obtain the target answer data. The target answer data is the correct answer to the test question data after correction, and based on this correct answer, the task distribution of the next round of test question data is carried out.

[0093] In some embodiments, the answer result data includes an incorrect answer; correcting the initial answer data according to the answer result data to obtain the target answer data includes:

[0094] If the answer result data is an incorrect answer, penalty matching processing is performed according to the preset penalty rule information to obtain the answer penalty information;

[0095] Penalty processing is performed according to the answer penalty information, and the objection evaluation to the penalty processing feedback by the user is collected;

[0096] The appeal information feedback by the user is detected according to the objection evaluation;

[0097] Answer analysis processing is performed on the initial answer data according to the appeal information to obtain the answer analysis result of the initial answer data, and the answer analysis result includes ratio information and standard deviation information;

[0098] Answer matching processing is performed according to the answer analysis result to obtain the target answer data.

[0099] Figure 3 It is a flowchart of step S230 in some embodiments, Figure 3 The illustrated step S230 includes but is not limited to steps S310 to S350:

[0100] S310, if the answer result data is an incorrect answer, penalty matching processing is performed according to the preset penalty rule information to obtain the answer penalty information;

[0101] S320, penalty processing is performed according to the answer penalty information, and the objection evaluation to the penalty processing feedback by the user is collected;

[0102] S330, the appeal information feedback by the user is detected according to the objection evaluation;

[0103] S340, answer analysis processing is performed on the initial answer data according to the appeal information to obtain the answer analysis result of the initial answer data;

[0104] In S350, answer matching processing is performed according to the answer analysis result to obtain target answer data.

[0105] In step S310, if the answer result data is an incorrect answer, the system determines that the user is in the process of doing practice questions. Among them, the penalty rule information includes but is not limited to: selecting to deduct the reward points that should have been obtained according to the cumulative number of incorrect answers, or pausing answering questions, or blocking the account. In a specific embodiment, an example of obtaining the answer penalty information through penalty matching processing is as follows:

[0106] If the cumulative number of incorrect answers on the same day is 1, the answer penalty information is: deduct 10 reward points that the user should have obtained; if the cumulative number of incorrect answers on the same day is 2, the answer penalty information is: deduct 20 reward points that the user should have obtained; if the cumulative number of incorrect answers on the same day is greater than 2 and less than or equal to 5, the answer penalty information is: pause answering questions; if the cumulative number of incorrect answers within one week is greater than 10, the answer penalty information is: block the account.

[0107] In step S320, the penalty processing is to punish the user according to the answer penalty information matched in step S310. After receiving the penalty, the user can feedback the user evaluation result to the system. The user evaluation result is used to represent the user's opinion on this penalty behavior. The user evaluation result data includes consent evaluation and dissent evaluation.

[0108] In step S330, if the user evaluation result is a consent evaluation, indicating that the user agrees with the current system's penalty behavior, the user can continue the answering process; if the user evaluation result is a dissent evaluation, indicating that the user does not agree with the current system's penalty behavior, that is, the user believes that he does not have the behavior of doing practice questions, but the answer to this test question data is incorrect. At this time, the user can appeal against the penalty behavior, and the system collects the appeal information feedback by the user to re-evaluate the answer to this test question. The evaluation includes performing answer analysis processing.

[0109] It should be noted that when initiating an appeal, the system will inform the user of the number of points that will be returned if the appeal is successful, and the number of points that will be deducted if the appeal fails. After the user accepts, the appeal information is confirmed and submitted. Among them, the appeal itself does not affect the current system's determination. If the current user is suspended from answering questions due to an incorrect answer, then after the appeal, the user will still be suspended from answering questions. The user can only wait for the appeal to be successful, the answer to this test question to be corrected and enter the compensation link. After the suspension of answering questions for this user is cancelled, or after the time limit for suspending answering questions expires, the user can continue to answer questions.

[0110] In step S340, the answer analysis result includes ratio information and standard deviation information. The answer analysis result includes ratio information and standard deviation information. Among them, the ratio information is the ratio of the number of answers to this answer to the total number of users who answered this test question, and is used to characterize the concentration degree of the answers; the standard deviation information is the data standard deviation of the ratio information of each answer, and is used to characterize the stability degree of the answers.

[0111] The method of answer analysis processing is: analyze the answers of all users who have answered the data of this test question in the past, that is, the analysis objects of the answers include: the user question bank answering data in step S120 and the user test answering data in step S210.

[0112] For example, the answers to test question 1 include answer A, answer B, answer C, and answer D. Among them, the ratio information of answer A is 0.4; the ratio information of answer B is 0.3; the ratio information of answer C is 0.2; the ratio information of answer D is 0.1. The average of its ratio information is 0.25, then the standard deviation information is:

[0113]

[0114] In step S350, the basis for the correction process includes: judging whether this test question needs to be corrected according to the specific values of the ratio information and standard deviation information of each test question. The process of the correction process is: correct the initial answer data of this test question data to the target answer data, where the target answer data is the correct answer judged according to the analysis result.

[0115] In some embodiments, answer matching processing is performed according to the answer analysis result to obtain target answer data, including: if the answer analysis result meets the first condition, the answer corresponding to the first condition is used as the target answer data; the first condition is: the ratio information of the answer with the largest ratio information is greater than or equal to the first threshold.

[0116] In some embodiments, answer matching processing is performed according to the answer analysis result to obtain target answer data, including: if the answer analysis result meets the second condition, the two answers corresponding to the second condition are used as the target answer data; the second condition is: the ratio information of all answers is less than the second threshold, and the total ratio of the two answers with the largest ratio information is greater than or equal to the first threshold, and the standard deviation information of the answers is greater than the third threshold.

[0117] In some embodiments, answer matching processing is performed according to the answer analysis result to obtain target answer data, including: if the answer analysis result does not meet the first condition and the second condition, the test question data corresponding to the appeal information is manually judged to obtain the target answer data.

[0118] Figure 4It is a flowchart of step S350 in some embodiments. Figure 4 The illustrated step S350 includes but is not limited to steps S410 to S460:

[0119] S410, obtain the answer analysis result;

[0120] S420, determine whether the answer analysis result meets the first condition; if the determination result is yes, execute step S430; if the determination result is no, execute step S440;

[0121] S430, determine whether the answer analysis result meets the second condition; if the determination result is yes, execute step S450; if the determination result is no, execute step S460;

[0122] S440, use the answer corresponding to the first condition as the target answer data;

[0123] S450, use the two answers corresponding to the second condition as the target answer data;

[0124] S460, perform manual discrimination processing on the test question data corresponding to the appeal information to obtain the target answer data.

[0125] In step S410, the answer analysis result includes the ratio information and standard deviation information of the answers corresponding to the test question data. The analysis objects of the answers include: user question bank answering data and user test answering data.

[0126] In steps S420 and S440, the first condition is: the ratio information of the answer with the largest ratio information is greater than or equal to the first threshold, where the first threshold is 0.8.

[0127] Specifically, if the answer analysis result meets the first condition, it indicates that the answers to the test question data are relatively concentrated, then it is determined that the answer with the largest ratio information is the correct answer, and this correct answer is used as the target answer data to correct the initial answer data; if the answer analysis result does not meet the first condition, continue with the subsequent judgment.

[0128] In steps S430 and S450, the second condition is: the ratio information of all answers is less than the second threshold, and the total ratio of the two answers with the largest ratio information is greater than or equal to the first threshold, and the standard deviation information of the answers is greater than the third threshold, where the first threshold is 0.8, the second threshold is 0.5, and the third threshold is 0.05.

[0129] Specifically, if the answer analysis result meets the second condition, it indicates that there is a large divergence in the answers to this question among users, but both answers are reasonable. The two answers corresponding to the second condition are used as the target answer data, and as long as the answer submitted by the user meets one of them, it is determined to be correct. However, this question is not suitable as a test question, so the distribution of this question is stopped.

[0130] In step S460, if the answer analysis result neither meets the first condition nor meets the second condition, it indicates that the answer to this question is too ambiguous. Therefore, the distribution of this question is stopped, and manual discrimination processing is performed to obtain the target answer data.

[0131] It should be noted that after the generation of the target answer data for the embodiments shown Figure 4 above, it is necessary to re-determine the answers of all users who answered this test question according to the latest answer, and perform compensation or punishment. Then, this test question enters the distribution queue again.

[0132] Figure 4 For the embodiments shown above, the test question data is classified and discriminated according to the answer analysis result to judge the clarity level of its answer, realizing the correction of the initial answer data and improving the correctness of the test question answer.

[0133] In some embodiments, the method further includes: performing a search process according to the target answer data to obtain misjudged questions; misjudged questions are test question data misjudged by the initial answer data; and compensating the users corresponding to the misjudged questions according to the preset compensation rule information.

[0134] As Figure 5 shown, Figure 5 is a flowchart of a test question generation method provided by some other embodiments. The test question generation method further includes:

[0135] S510, performing a search process according to the target answer data to obtain misjudged questions;

[0136] S520, compensating the users corresponding to the misjudged questions according to the preset compensation rule information.

[0137] In step S510, misjudged questions are test question data misjudged by the initial answer data; the search process is: if the answer has passed the appeal stage and the appeal is successful, then this test question is found according to the corrected target answer data, and the test question data misjudged by the initial answer data is the misjudged question.

[0138] In step S520, the compensation rule information includes but is not limited to: compensating the user according to the answer penalty information of the system at the time of misjudgment. In specific embodiments, examples of the compensation rule are as follows:

[0139] If the answering penalty information is to deduct 10 points from the reward points that the user should have obtained, the compensation information is: compensate the user's points by 10 points; if the answering penalty information is to deduct 20 points from the reward points that the user should have obtained, the compensation information is: compensate the user's points by 20 points. If the answering penalty information is to suspend answering, the compensation information is: lift the suspension of answering; if the answering penalty information is to block the account, the compensation information is: lift the blockage.

[0140] In addition, in some embodiments, the test question generating method further includes: performing a random check on users who have answered the test question based on the target answer data of the test question data; if the random check finds that the previously submitted user test answer data is inconsistent with the target answer data, that is, inconsistent with the latest answer, then the user is penalized according to the penalty rule information.

[0141] The test question generation method provided by the disclosed embodiment reduces the threshold for new types of questions to access the system. Users do not need to prepare a batch of tasks with standard answers first, and can directly access and start delivery. There is no need to manually change the test questions regularly, which reduces the manual maintenance cost of this test question mechanism and reduces the possibility that users can identify the test questions. After the user's appeal is successful, the punishment for the user who submitted the wrong answer enhances the judgment of the user's answer, which is equivalent to the user also assuming the responsibility of reviewing other users' answers. The wrong answer can be more accurately located, and the reliability of the user's answer is improved. In actual use, the number of times the test question is distributed does not exceed 20 times. If the number of distributions is set too small, the reliability of the comprehensive final answer will be reduced. If it is set too large, the time for automatically processing the appeal will be excessively extended, reducing the user experience. Setting it to 20 is a time that is more acceptable to the operator.

[0142] The disclosed embodiment proposes a test question generating device, including: a question bank data acquisition module, used to acquire question bank data; an answer collection module, used to perform answer collection processing on the question bank data to obtain user question bank answer data; an answer analysis module, used to perform answer analysis processing on the user question bank answer data to obtain the answer concentration of the user question bank answer data; a screening module, used to perform screening processing on the question bank data according to the answer concentration to obtain test question data; and a matching module, used to perform matching processing on the user question bank answer data to obtain initial answer data corresponding to the test question data.

[0143] The specific implementation of the test question generating device of this embodiment is basically the same as the specific implementation of the test question generating method described above, and will not be described in detail here.

[0144] The present disclosure also provides an electronic device, including:

[0145] at least one memory;

[0146] at least one processor;

[0147] At least one program;

[0148] The program is stored in a memory, and a processor executes the at least one program to implement the topic recommendation method described above in the present disclosure. The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA for short), an in-vehicle computer, etc.

[0149] Please refer to Figure 6 , Figure 6 which illustrates the hardware structure of an electronic device according to another embodiment. The electronic device includes:

[0150] A processor 601, which can be implemented by using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present disclosure;

[0151] A memory 602, which can be implemented in the form of a ROM (Read Only Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory), etc. The memory 602 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 602, and the processor 601 is called to execute the topic recommendation method of the embodiments of the present disclosure;

[0152] An input / output interface 603, which is used to implement information input and output;

[0153] A communication interface 604, which is used to implement communication interaction between this device and other devices, and can implement communication through a wired method (such as USB, network cable, etc.) or through a wireless method (such as mobile network, WIFI, Bluetooth, etc.); and

[0154] A bus 605, which transmits information between various components of the device (such as the processor 601, the memory 602, the input / output interface 603, and the communication interface 604);

[0155] Wherein the processor 601, the memory 602, the input / output interface 603, and the communication interface 604 are communicatively connected to each other inside the device through the bus 605.

[0156] The embodiments of the present disclosure also provide a storage medium, which is a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the above test question generation method.

[0157] The test question generation method, device, electronic device, and storage medium provided by the embodiments of the present disclosure obtain question bank data, perform answer collection processing on the question bank data to obtain user question bank answering data, then perform answer analysis processing on the user question bank answering data to obtain the answer concentration degree of the user question bank answering data, and then perform screening processing on the question bank data according to the answer concentration degree to obtain test question data. Finally, matching processing is performed according to the user question bank answering data to obtain initial answer data corresponding to the test question data. Through the technical solution provided by the embodiments of the present disclosure, the generation efficiency of test questions can be improved, the dependence on operation personnel in the test question release process can be eliminated, the operation cost can be reduced, the threshold for releasing new question types can be lowered, it is ensured that test questions cannot be easily recognized by test users, and at the same time, the accuracy of the answers corresponding to the test questions can be improved, and the misjudgment of questions can be reduced.

[0158] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0159] The embodiments described in the embodiments of the present disclosure are for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are equally applicable to similar technical problems.

[0160] Those skilled in the art can understand that Figures 1 - 5 the technical solutions shown in do not constitute a limitation on the embodiments of the present disclosure, and may include more or fewer steps than those shown in the figure, or combine certain steps, or different steps.

[0161] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or a suitable combination thereof.

[0163] As used in the specification of this application and the above-mentioned drawings, the terms "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0164] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may mean: only A exists, only B exists, and both A and B exist at the same time. Here, A and B can be singular or plural. The character " / " generally means that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or a similar expression means any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0165] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, 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 displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

[0166] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0167] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0168] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0169] The preferred embodiments of the present disclosure have been described above with reference to the accompanying drawings, and thus do not limit the scope of rights of the present disclosure. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the present disclosure should be within the scope of rights of the present disclosure.

Claims

1. A method for generating test questions, characterized in that, Including: Obtain question bank data; Perform answer collection processing on the question bank data to obtain user question bank answering data; Perform answer analysis processing on the user question bank answering data to obtain the answer concentration degree of the user question bank answering data; wherein, the answer concentration degree includes ratio information of each answer corresponding to the question bank data; Determine the highest one among the ratio information of each answer corresponding to the question bank data as the highest ratio information; Select the question bank data according to the highest ratio information to obtain test question data; Perform matching processing according to the user question bank answering data to obtain initial answer data corresponding to the test question data; wherein, the initial answer data is the answer with the highest ratio information among all answers of the test question data; Dispatch the test question data to the answering task queue, collect the test answers of the user for the test question data in the answering task queue, and use the test answers as user test answering data; Perform discrimination processing on the user test answering data according to the initial answer data to obtain answering result data; If the answering result data is an answering error, perform penalty matching processing according to preset penalty rule information to obtain answering penalty information; Perform penalty processing according to the answering penalty information, and collect the objection evaluation of the user's feedback on the penalty processing; Detect the appeal information feedback by the user according to the objection evaluation; Perform answer analysis processing on the initial answer data according to the appeal information to obtain the answer analysis result of the initial answer data, and the answer analysis result includes ratio information and standard deviation information; Perform answer matching processing according to the answer analysis result to obtain target answer data, and determine whether to stop dispatching the test question data according to the answer analysis result.

2. The method according to claim 1, wherein The performing answer matching processing according to the answer analysis result to obtain the target answer data includes: If the answer analysis result meets the first condition, use the answer corresponding to the first condition as the target answer data; the first condition is: the ratio information of the answer with the largest ratio information is greater than or equal to the first threshold.

3. The method according to claim 2, wherein The performing answer matching processing according to the answer analysis result to obtain the target answer data includes: If the answer analysis result meets the second condition, use the two answers corresponding to the second condition as the target answer data, and stop dispatching the test question data; the second condition is: the ratio information of all answers is less than the second threshold, and the total ratio of the two answers with the largest ratio information is greater than or equal to the first threshold, and the standard deviation information of the answers is greater than the third threshold.

4. The method according to claim 3, wherein The performing answer matching processing according to the answer analysis result to obtain the target answer data includes: If the answer analysis result does not meet the first condition and the second condition, perform manual discrimination processing on the test question data corresponding to the appeal information to obtain the target answer data, and stop dispatching the test question data.

5. The method according to claim 1, wherein The method further includes: Perform a search process based on the target answer data to obtain misjudged questions; the misjudged questions are the test question data misjudged by the initial answer data. Perform a compensation process on the user corresponding to the misjudged questions according to the preset compensation rule information.

6. A test question generation device, characterized in that, Including: A question bank data acquisition module for acquiring question bank data; An answer collection module for performing an answer collection process on the question bank data to obtain user question bank answering data; An answer analysis module for performing an answer analysis process on the user question bank answering data to obtain the answer concentration of the user question bank answering data; wherein, the answer concentration includes the ratio information of each answer corresponding to the question bank data; A screening module for determining the highest one among the ratio information of each answer corresponding to the question bank data as the highest ratio information, and selecting the question bank data according to the highest ratio information to obtain test question data; A matching module for performing a matching process according to the user question bank answering data to obtain initial answer data corresponding to the test question data; wherein, the initial answer data is the answer with the highest ratio information among all the answers of the test question data; The device is further configured to: Dispatch the test question data to a question answering task queue, collect the test answers of the user for the test question data in the question answering task queue, and use the test answers as user test answering data; Perform a discrimination process on the user test answering data according to the initial answer data to obtain answering result data; If the answering result data is an answering error, perform a penalty matching process according to the preset penalty rule information to obtain answering penalty information; Perform a penalty process according to the answering penalty information, and collect the dissenting evaluation of the user's feedback on the penalty process; Detect the appeal information of the user's feedback according to the dissenting evaluation; Perform an answer analysis process on the initial answer data according to the appeal information to obtain the answer analysis result of the initial answer data, and the answer analysis result includes ratio information and standard deviation information; Perform an answer matching process according to the answer analysis result to obtain target answer data, and determine whether to stop dispatching the test question data according to the answer analysis result.

7. An electronic device, characterized in that, Including: At least one memory; At least one processor; At least one program; The program is stored in the memory, and the processor executes the at least one program to implement: The method according to any one of claims 1 to 5.

8. A storage medium, the storage medium being a computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute: The method according to any one of claims 1 to 5.

Images