Answer acquisition method, device, electronic device and readable storage medium

Abstract

Embodiments of the present disclosure provide a method, apparatus, electronic device, and storage medium for obtaining answers. The method includes: receiving answers to a first number of question-and-answer questions fed back by multiple users; wherein the question-and-answer questions include a second number of questions to be verified and a third number of detection questions; screening at least one target user meeting a preset condition from the multiple users according to the answers to the detection questions fed back by the multiple users; determining the confidence level of each option in each of the questions to be verified according to the answers to the questions to be verified fed back by the target user; and determining the target answer to each of the questions to be verified according to the confidence level. The present disclosure can effectively identify cheating users, and the finally adopted result is more real, accurate, flexible, and easy to understand.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of Internet technologies, and in particular, to a method for obtaining answers, an apparatus for obtaining answers, an electronic device, and a readable storage medium. Background Art

[0002] In order to collect some user usage habits, each website or merchant usually provides a series of questions for users to answer online to collect user information. Currently, most question providers convert the questions into multiple-choice questions for users to answer online. For example, the question: "Is the merchant type of this merchant glasses?" The corresponding answer options are: "Yes", "No", "Uncertain, next question", etc. By providing the same question to multiple users to answer, the answer with the largest number of selected people is selected as the final adopted result.

[0003] However, in the above solution, the situation of user cheating is not considered. For example, some users randomly select answers, and the more cheating users there are, the lower the accuracy of the final adopted result will be. Summary of the Invention

[0004] Embodiments of the present disclosure provide a method for obtaining answers, an apparatus, an electronic device, and a readable storage medium, which are used to identify cheating users who answer questions and improve the accuracy of the adopted results corresponding to the questions.

[0005] According to a first aspect of the embodiments of the present disclosure, there is provided a method for obtaining answers, including:

[0006] Receiving answers of a first number of question-and-answer questions feedback by multiple users; wherein, the question-and-answer questions include a second number of questions to be verified and a third number of detection questions;

[0007] Based on the answers of the detection questions feedback by the multiple users, screening out at least one target user from the multiple users who meets a preset condition;

[0008] Based on the answers of the questions to be verified feedback by the target user, determining the confidence level of each option in each of the questions to be verified; and

[0009] Based on the confidence level, determining the target answer for each of the questions to be verified.

[0010] In a specific implementation of the embodiments of the present invention, before the step of receiving answers of a first number of question-and-answer questions feedback by multiple users, it further includes:

[0011] Obtaining the questions to be verified and the detection questions;

[0012] Mixing the detection questions into the questions to be verified to generate the question-and-answer questions; and

[0013] Push the question-and-answer questions to the multiple users.

[0014] In a specific implementation of the embodiment of the present invention, the step of screening at least one target user meeting a preset condition from the multiple users according to the answers of the detection questions fed back by the multiple users includes:

[0015] For a single user among the multiple users, obtain a fourth quantity of the single user answering the detection questions correctly according to the answers of the detection questions fed back by the single user; and

[0016] When the fourth quantity is greater than a preset quantity threshold, determine that the single user is one of the target users.

[0017] In a specific implementation of the embodiment of the present invention, the step of determining the confidence level of each option in each of the questions to be verified according to the answers of the questions to be verified fed back by the target users includes:

[0018] Obtain a first number of people corresponding to the target users and a second number of people corresponding to cheating users from the multiple users; the cheating users refer to users who do not meet the preset conditions;

[0019] For each of the questions to be verified, obtain a first option among the multiple options corresponding to the question to be verified and at least one second option other than the first option; and

[0020] Determine the confidence level of the first option according to the second quantity, the third quantity, the first number of people, the second number of people, the first option, and the second option.

[0021] In a specific implementation of the embodiment of the present invention, the step of determining the confidence level of the first option according to the second quantity, the third quantity, the first number of people, the second number of people, the first option, and at least one of the second options includes:

[0022] Calculate a first probability that the cheating users select the first option according to the number of options included in the question to be verified;

[0023] Calculate a second probability that the cheating users pass the anti-cheating strategy according to the third quantity and the total number of options included in the detection questions;

[0024] Calculate the answering accuracy rate of the target users according to the second probability, the first number of people, and the second number of people;

[0025] Obtain the third number of people who select the first option and the fourth number of people who select the second option among the target users; and

[0026] Calculate the confidence level of the first option based on the first probability, the answering accuracy rate, the third number, and the fourth number.

[0027] In a specific implementation of the embodiment of the present invention, the step of determining the target answer for each of the to-be-verified questions based on the confidence level includes:

[0028] Compare the confidence level of each option in the to-be-verified question with a confidence level threshold; and

[0029] Determine the target answer for each of the to-be-verified questions based on the comparison result.

[0030] In a specific implementation of the embodiment of the present invention, the step of determining the target answer for each of the to-be-verified questions based on the comparison result includes:

[0031] Obtain the target options whose confidence level is greater than the confidence level threshold from each option of the to-be-verified question; and

[0032] When the number of the target options is at least one, use the target option with the highest confidence level as the target answer for the to-be-verified question; or, when the number of the target options is zero, determine that the target answer for the to-be-verified question is a null value.

[0033] According to the second aspect of the embodiments of the present disclosure, there is provided an answer acquisition device, including:

[0034] A short-answer question answer receiving module, configured to receive answers to a first number of short-answer questions fed back by a plurality of users; wherein, the short-answer questions include a second number of to-be-verified questions and a third number of detection questions;

[0035] A target user screening module, configured to screen out at least one target user meeting a preset condition from the plurality of users according to the answers to the detection questions fed back by the plurality of users;

[0036] A confidence level determination module, configured to determine the confidence level of each option in each of the to-be-verified questions according to the answers to the to-be-verified questions fed back by the target users; and

[0037] A target answer determination module, configured to determine the target answer for each of the to-be-verified questions based on the confidence level.

[0038] In a specific implementation of the embodiment of the present invention, it further includes:

[0039] A problem acquisition module, configured to acquire the problem to be verified and the detection questions;

[0040] An answer question generation module, configured to mix the detection questions into the problem to be verified to generate the answer questions; and

[0041] An answer question pushing module, configured to push the answer questions to the multiple users.

[0042] In a specific implementation of the embodiment of the present invention, the target user screening module includes:

[0043] A fourth quantity acquisition sub-module, configured to, for a single user among the multiple users, acquire a fourth quantity of the single user answering the detection questions correctly according to the answers of the detection questions fed back by the single user; and

[0044] A target user determination sub-module, configured to determine that the single user is one of the target users when the fourth quantity is greater than a preset quantity threshold.

[0045] In a specific implementation of the embodiment of the present invention, the confidence determination module includes:

[0046] A first and second number acquisition sub-module, configured to acquire a first number corresponding to the target users and a second number corresponding to cheating users from the multiple users; the cheating users refer to users who do not meet the preset conditions;

[0047] An option acquisition sub-module, configured to, for each problem to be verified, acquire a first option among multiple options corresponding to the problem to be verified and at least one second option other than the first option; and

[0048] A confidence determination sub-module, configured to determine the confidence of the first option according to the second quantity, the third quantity, the first number, the second number, the first option, and the second option.

[0049] In a specific implementation of the embodiment of the present invention, the confidence determination sub-module includes:

[0050] A first probability calculation sub-module, configured to calculate a first probability that the cheating users select the first option according to the number of options included in the problem to be verified;

[0051] A second probability calculation sub-module, configured to calculate a second probability that the cheating users pass the anti-cheating strategy according to the third quantity and the total number of options included in the detection questions;

[0052] An answer accuracy calculation sub-module, configured to calculate the answer accuracy of the target user according to the second probability, the first number of people, and the second number of people;

[0053] A third and fourth number of people acquisition sub-module, configured to acquire a third number of people who select the first option and a fourth number of people who select the second option among the target users; and

[0054] A confidence level calculation sub-module, configured to calculate the confidence level of the first option according to the first probability, the answer accuracy, the third number of people, and the fourth number of people.

[0055] In a specific implementation of an embodiment of the present invention, the target answer determination module includes:

[0056] A confidence level comparison sub-module, configured to compare the confidence level of each option in the to-be-verified question with a confidence level threshold; and

[0057] A target answer determination sub-module, configured to determine the target answer of each to-be-verified question according to the comparison result.

[0058] In a specific implementation of an embodiment of the present invention, the target answer determination sub-module includes:

[0059] A target option acquisition sub-module, configured to acquire a target option whose confidence level is greater than the confidence level threshold from each option of the to-be-verified question; and

[0060] A target answer acquisition sub-module, configured to, when the number of target options is at least one, use the target option with the highest confidence level as the target answer of the to-be-verified question; or, when the number of target options is zero, determine that the target answer of the to-be-verified question is a null value.

[0061] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0062] A processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor implements the above-mentioned answer acquisition method or methods when executing the program.

[0063] According to a fourth aspect of an embodiment of the present disclosure, there is provided a readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the above-mentioned answer acquisition method or methods.

[0064] Embodiments of the present disclosure provide a solution for obtaining question answers. By receiving answers to a first number of question-and-answer questions fed back by multiple users, where the question-and-answer questions include a second number of questions to be verified and a third number of detection questions, at least one target user meeting preset conditions is screened out from multiple users according to the answers to the detection questions fed back by the multiple users. According to the answers to the questions to be verified fed back by the target user, the confidence level of each option in each question to be verified is determined, and according to the confidence level, the target answer to each question to be verified is determined. Embodiments of the present disclosure can effectively identify cheating users according to the detection questions, and for each option of each question to be verified, the confidence level is used as the final adoption basis, rather than determining the adoption result according to the number of people who select each option, so that the final adoption result obtained is more true, accurate, flexible and easy to understand. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings required for the description of the embodiments of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0066] Figure 1 is a flowchart of the steps of a method for obtaining answers provided by an embodiment of the present disclosure;

[0067] Figure 2 is a flowchart of the steps of a method for obtaining answers provided by an embodiment of the present disclosure;

[0068] Figure 3 is a schematic structural diagram of an apparatus for obtaining answers provided by an embodiment of the present disclosure;

[0069] Figure 4 is a schematic structural diagram of an apparatus for obtaining answers provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the embodiments of the present disclosure without creative efforts fall within the scope of protection of the embodiments of the present disclosure.

[0071] Embodiment 1

[0072] Referring to Figure 1 , a flowchart of the steps of a method for obtaining answers provided by an embodiment of the present disclosure is shown. As Figure 1As shown, the method may specifically include the following steps:

[0073] Step 101: Receive answers to a first number of question-and-answer questions feedback by multiple users; wherein, the question-and-answer questions include a second number of questions to be verified and a third number of detection questions.

[0074] In the embodiments of the present disclosure, the question-and-answer questions may include questions to be verified and detection questions. The questions to be verified may be questions launched by an Internet platform or a certain merchant, etc., that is, questions for which the Internet platform or a certain merchant, etc. needs to adopt corresponding results. For example, questions such as "What type of clothing do you like?" or "What color of shoes do you like the most?" proposed by a certain merchant, or social survey questions launched by an Internet platform, such as "Will you buy an old-age insurance for yourself?" and so on.

[0075] The detection questions refer to questions mixed in the questions to be verified for detecting cheating users and non-cheating users. The detection questions are relatively simple questions, aiming to detect whether the user carefully reads the questions and answers seriously during the answering process, or randomly selects the answers. The detection questions can be simple questions such as "1 + 1 =?", "5 * 8 =?", etc.

[0076] The first number refers to the number of question-and-answer questions answered by the answering users, that is, the first number is the same as the number of question-and-answer questions. For example, when the number of question-and-answer questions is 20, the first number is 20.

[0077] The second number refers to the number of questions to be verified included in the question-and-answer questions, and the third number refers to the number of detection questions included in the question-and-answer questions. For example, the total number of question-and-answer questions is 50, and the number of questions to be verified is 30, then the second number is 30, and the third number is 20 (that is, 20 detection questions are mixed in the question-and-answer questions).

[0078] That is, the first number is equal to the sum of the second number and the third number.

[0079] It can be understood that the above examples are only examples listed for better understanding the technical solutions of the embodiments of the present disclosure, and do not serve as the sole limitation to the embodiments of the present disclosure.

[0080] After sending the first number of question-and-answer questions to multiple users, answers to the first number of question-and-answer questions feedback by multiple users can be received.

[0081] Of course, the number of answers to the question-and-answer questions feedback by each user can be the first number, or greater than the first number, mainly considering that there may be a process where a user selects multiple options for a certain question-and-answer question. This is not the inventive point of the embodiments of the present disclosure, but only for a brief description of this form.

[0082] After sending the first quantity of question-and-answer questions to multiple users, there may be a situation where individual users do not answer and directly ignore them. This embodiment of the present disclosure does not consider such a situation and only uses the users who have provided answers as a reference for selecting and adopting the results.

[0083] After receiving the answers to the first quantity of question-and-answer questions feedback by multiple users, step 102 is executed.

[0084] Step 102: According to the answers to the detection questions feedback by the multiple users, screen out at least one target user who meets the preset conditions from the multiple users.

[0085] The target user refers to a non-cheating user among the multiple users who have provided answers to the question-and-answer questions.

[0086] The preset condition refers to the condition for determining whether a user is a cheating user based on the accuracy of the answers to the detection questions provided by each user. For example, when there are 20 detection questions mixed in the question-and-answer questions, the preset condition can be set to 12, that is, when a user answers 12 or more of the detection questions correctly, the user is determined to be a non-cheating user; otherwise, the user is determined to be a cheating user.

[0087] Of course, the detailed process of determining whether a user is a target user according to the preset conditions will be described in Embodiment 2 below, and this embodiment of the present disclosure will not elaborate here.

[0088] After receiving the answers to the first quantity of question-and-answer questions feedback by multiple users, it is possible to determine whether the user is a target user according to the answers to the detection questions provided by each user, and then complete screening out at least one target user who meets the preset conditions from the multiple users.

[0089] After screening out at least one target user from the multiple users according to the answers to the detection questions feedback by the multiple users, step 103 is executed.

[0090] Step 103: According to the answers to the questions to be verified feedback by the target users, determine the confidence level of each option in each of the questions to be verified.

[0091] The confidence level refers to the credibility of each option corresponding to each question to be verified as an adopted result. The confidence level can be a numerical value, such as 0.5, 0.8, etc. Specifically, it can be determined according to business requirements, and this embodiment of the present disclosure does not limit it.

[0092] After screening out at least one target user who meets the preset conditions from the multiple users, it is possible to determine the confidence level of each option in each of the questions to be verified according to the answers to the questions to be verified feedback by the target users.

[0093] That is, in the present disclosure, the answers feedback by non-target users (i.e., cheating users) among multiple users are not considered, but instead, the answers to the questions to be verified feedback by non-cheating users are directly used to determine the adoption result (i.e., the target answer) of each question to be verified.

[0094] Of course, for the above-described method of determining the confidence of each option of the question to be verified, a Bayesian probability model can be used to calculate the confidence of each option of the question to be verified. The specific calculation process will be described in detail in the second embodiment below, and will not be elaborated in the embodiments of the present disclosure here.

[0095] After determining the confidence of each option in each question to be verified according to the answers to the questions to be verified feedback by the target users, step 104 is executed.

[0096] Step 104: Determine the target answer of each question to be verified according to the confidence.

[0097] After determining the confidence of each option in each question to be verified according to the answers to the questions to be verified feedback by the target users, the target answer of the question to be verified can be determined according to the confidence of each option in each question to be verified.

[0098] In the present disclosure, a confidence threshold can be preset. When the confidence of each option in the question to be verified is less than or equal to the confidence threshold, the target answer of the question to be verified is determined to be a null value, that is, there is no target answer. When there is one or more options in the confidence of each option in the question to be verified whose confidence is greater than the confidence threshold, the option corresponding to the maximum confidence value is selected from the one or more options whose confidence is greater than the confidence threshold, and the option corresponding to the maximum confidence is used as the target answer of the question to be verified.

[0099] The above process will be described in detail in the second embodiment below, and will not be elaborated in the embodiments of the present disclosure here.

[0100] The embodiments of the present disclosure can effectively identify cheating users according to the detection questions, and for each option of each question to be verified, the confidence is used as the final adoption basis, rather than determining the adoption result according to the number of people who select each option, so that the finally obtained adoption result is more real and accurate.

[0101] The question answer acquisition method provided by the embodiments of the present disclosure receives the answers to the first quantity of question-and-answer questions feedback by multiple users. Among them, the question-and-answer questions include the second quantity of questions to be verified and the third quantity of detection questions. According to the answers to the detection questions feedback by multiple users, at least one target user meeting the preset conditions is screened out from multiple users. According to the answers to the questions to be verified feedback by the target user, the confidence level of each option in each question to be verified is determined, and according to the confidence level, the target answer of each question to be verified is determined. The embodiments of the present disclosure can effectively identify cheating users according to the detection questions. Moreover, for each option of each question to be verified, the confidence level is used as the final adoption basis, rather than determining the adoption result according to the number of people who choose each option, so that the final adoption result obtained is more true, accurate, flexible and easy to understand.

[0102] Embodiment 2

[0103] Refer to Figure 2 , which shows the step flowchart of the answer acquisition method provided by the embodiments of the present disclosure. As Figure 2 shown, the method may specifically include the following steps:

[0104] Step 201: Obtain the questions to be verified and the detection questions.

[0105] In the embodiments of the present disclosure, the questions to be verified may be questions launched by an Internet platform or a certain merchant, etc., that is, questions for which an Internet platform or a certain merchant, etc. needs to adopt corresponding results. For example, questions raised by a certain merchant such as "What type of clothing do you like?" or "What color of shoes do you like the most?", or social survey questions launched by an Internet platform, such as "Will you buy an old-age insurance for yourself?" and so on.

[0106] The detection question refers to a question mixed in the questions to be verified for detecting cheating users and non-cheating users. The detection question is a relatively simple question, aiming to detect whether the user carefully examines the questions and answers them seriously during the answering process, or answers randomly. The detection question can be a simple and easy-to-answer question such as "1 + 1 =?", "5 * 8 =?", etc.

[0107] The quantity of the questions to be verified can be determined by an Internet platform or a merchant, etc. The quantity of the detection questions can be determined by the quantity of the questions to be verified. For example, when there are 30 questions to be verified, if it is pre-set to mix one detection question every 2 questions, the quantity of the mixed detection questions is 15; and if it is pre-set to mix one detection question every 5 questions, the quantity of the mixed detection questions is 6.

[0108] It can be understood that the above examples are only examples listed for better understanding the technical solutions of the embodiments of the present disclosure, and do not serve as the sole limitation of the embodiments of the present disclosure.

[0109] After obtaining the to-be-verified questions launched by an Internet platform or a certain merchant, etc., a matching number of detection questions can be obtained according to the pre-set rules.

[0110] After obtaining the to-be-verified questions and the detection questions, perform step 202.

[0111] Step 202: Mix the detection questions into the to-be-verified questions to generate the question-and-answer questions.

[0112] After obtaining the to-be-verified questions and the detection questions, the detection questions can be mixed into the to-be-verified questions. The mixing rule can be a random rule, that is, a specified number of detection questions are randomly mixed into the to-be-verified questions, and the mixing interval is random.

[0113] Of course, the interval of the detection questions can also be pre-set. For example, 1 detection question is mixed into every 3 or 5 to-be-verified questions, etc.

[0114] In specific implementation, those skilled in the art can set the mixing method of the detection questions according to business requirements, and the embodiments of the present disclosure do not limit this.

[0115] After mixing the detection questions into the to-be-verified questions, question-and-answer questions can be generated based on the to-be-verified questions and the mixed detection questions, that is, the question-and-answer questions are a combination of the to-be-verified questions and the detection questions.

[0116] After mixing the detection questions into the to-be-verified questions to generate the question-and-answer questions, perform step 203.

[0117] Step 203: Push the question-and-answer questions to the multiple users.

[0118] After generating the question-and-answer questions, the question-and-answer questions can be pushed to multiple users. It can be understood that in the process of pushing, when a user accesses the Internet platform, the question-and-answer questions launched by the Internet are pushed to the currently accessing user for display on the user terminal screen; for a merchant, when a user accesses the merchant through the Internet, the question-and-answer questions launched by the merchant are pushed to the user.

[0119] Of course, in actual applications, other pushing methods can also be adopted. Specifically, it can be determined according to the actual situation, and the embodiments of the present disclosure do not limit this.

[0120] After pushing the question-and-answer questions to multiple users, perform step 204.

[0121] Step 204: Receive answers to the first number of question-and-answer questions fed back by multiple users; wherein, the question-and-answer questions include the second number of to-be-verified questions and the third number of detection questions.

[0122] The first quantity refers to the number of short-answer questions answered by the answering user, that is, the first quantity is the same as the number of short-answer questions. For example, when the number of short-answer questions is 20, the first quantity is 20.

[0123] The second quantity refers to the number of questions to be verified included in the short-answer questions, and the third quantity refers to the number of detection questions included in the short-answer questions. For example, the total number of short-answer questions is 50, and the number of questions to be verified is 30, then the second quantity is 30, and the third quantity is 20 (that is, there are 20 detection questions mixed in the short-answer questions).

[0124] That is, the first quantity is equal to the sum of the second quantity and the third quantity.

[0125] It can be understood that the above examples are only examples listed for better understanding the technical solutions of the embodiments of the present disclosure, and do not serve as the sole limitation to the embodiments of the present disclosure.

[0126] After sending the short-answer questions of the first quantity to multiple users, the answers to the short-answer questions of the first quantity fed back by the multiple users can be received.

[0127] Of course, after sending the short-answer questions of the first quantity to multiple users, there may be a situation where individual users do not answer and directly ignore. The embodiments of the present disclosure do not consider this situation, and only use the users who have fed back the answers as the reference basis for selecting and adopting the results.

[0128] After receiving the answers to the short-answer questions of the first quantity fed back by multiple users, step 205 is executed.

[0129] Step 205: For a single user among the multiple users, according to the answers to the detection questions fed back by the single user, obtain the fourth quantity of the single user answering the detection questions correctly.

[0130] A single user refers to any one of the multiple users.

[0131] The fourth quantity refers to the number of questions that a single user answers and answers correctly for the detection questions. For example, the total number of detection questions is 20, and among them, the number of questions answered correctly by a certain user is 15, then for this user, the fourth quantity is 15; and when the number of questions answered correctly by a certain user for the detection questions is 18, then for this user, the fourth quantity is 18.

[0132] It can be understood that the above examples are only examples listed for better understanding the technical solutions of the embodiments of the present disclosure, and do not serve as the sole limitation to the embodiments of the present disclosure.

[0133] After receiving the answers to the first quantity of question-and-answer questions feedback by multiple users, the fourth quantity of a single user answering the detection question correctly can be obtained based on the answer to the detection question feedback by the single user.

[0134] After obtaining, for a single user among multiple users, the fourth quantity of the single user answering the detection question correctly based on the answer to the detection question feedback by the single user, step 206 is executed.

[0135] Step 206: When the fourth quantity is greater than the preset quantity threshold, determine that the single user is one of the target users.

[0136] The target user refers to a non-cheating user among multiple users who feedback the answers to the question-and-answer questions.

[0137] The preset quantity threshold refers to the threshold set in advance by business personnel for determining whether a single user is a target user. The preset quantity threshold can be 15, 16, etc. Specifically, it can be determined according to the actual situation, and the embodiments of the present disclosure do not limit this.

[0138] After obtaining the fourth quantity of each user among multiple users answering the detection question correctly, the respective fourth quantities can be compared with the preset quantity threshold. When the fourth quantity corresponding to a single user is less than or equal to the preset quantity threshold, it can be determined that the single user is a non-target user (i.e., a cheating user), that is, the user may randomly answer the question-and-answer questions launched by the Internet platform or merchants, etc., without seriously examining the questions; while when the fourth quantity corresponding to a single user is greater than the preset quantity threshold, it can be determined that the single user is a target user (i.e., a non-cheating user).

[0139] After obtaining the target users from multiple users based on the fourth quantity of each user among multiple users answering the detection question correctly, step 207 is executed.

[0140] Step 207: Obtain the first number of people corresponding to the target users and the second number of people corresponding to the cheating users from the multiple users; the cheating users refer to users who do not meet the preset conditions.

[0141] The cheating users refer to users who do not meet the preset conditions, that is, the fourth quantity of the cheating users answering the detection question correctly is less than or equal to the preset quantity threshold.

[0142] The first number of people refers to the number of people who are target users (i.e., non-cheating users) among multiple users, and the second number of people refers to the number of cheating users among multiple users.

[0143] Understandably, the sum of the first number of people and the second number of people is the total number of users who answered the feedback questions. For example, if the total number of users is 38 and the first number of people corresponding to the target user is 20, then the second number of people is 38 - 20 = 18, that is, the number of cheating users is 18.

[0144] After obtaining the first number of people corresponding to the target user and the second number of people corresponding to the cheating users from among the multiple users, step 208 is executed.

[0145] Step 208: For each of the to-be-verified questions, obtain a first option among the multiple options corresponding to the to-be-verified question, and at least one second option other than the first option.

[0146] The first option refers to one option among the multiple options corresponding to the to-be-verified question, and the second option refers to the other options among the multiple options corresponding to the to-be-verified question other than the first option. For example, if the to-be-verified question includes options a, b, and c, when option a is identified as the first option, then options b and c are the second options; when option b is identified as the first option, then options a and c are the second options.

[0147] Understandably, the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present disclosure and do not serve as the sole limitation to the embodiments of the present disclosure.

[0148] For each to-be-verified question, after determining the first option and at least one second option of each to-be-verified question according to a pre-set rule (such as regarding the option ranked first in the order of the to-be-verified questions as the first option), step 209 is executed.

[0149] Step 209: Determine the confidence level of the first option based on the second quantity, the third quantity, the first number of people, the second number of people, the first option, and the second option.

[0150] The confidence level refers to the credibility of each option corresponding to each to-be-verified question as an adopted result. The confidence level can be a numerical value, such as 0.5, 0.8, etc. Specifically, it can be determined according to business requirements, and the embodiments of the present disclosure do not limit this.

[0151] In the above steps, after obtaining the second quantity (the number of to-be-verified questions), the third quantity (the number of detection questions), the first number of people (the number of target users), the second number of people (the number of cheating users), the first option (one option in each to-be-verified question), and the second option (the other options in each to-be-verified question other than the first option), the confidence level of the first option can be determined by combining the second quantity, the third quantity, the first number of people, the second number of people, the first option, and the second option.

[0152] In the present disclosure, the second quantity, the third quantity, the first number of people, the second number of people, the first option, and the second option can be used as parameters. Referring to the Bayesian probability model, the confidence level of the first option of each question to be verified can be calculated. For the specific calculation process, it can be described in detail in combination with the following specific implementation manners.

[0153] In a specific implementation of the embodiment of the present disclosure, step 209 above may include:

[0154] Sub-step S1: Calculate a first probability that the cheating user selects the first option according to the number of options included in the question to be verified.

[0155] The embodiment of the present disclosure can calculate the confidence level of each option in each question to be verified in combination with the Bayesian probability model, that is, the confidence level of an option (i.e., the first option) in a question to be verified in the following implementation process.

[0156] After selecting a question to be verified from the question-and-answer questions, the number of options of the question to be verified can be determined. For example, when the options of the question to be verified include options A and B, the number of options of the question to be verified is 2; when the options of the question to be verified include A, B, C, and D, the number of options of the question to be verified is 4.

[0157] After obtaining the number of options included in the question to be verified, a first probability that the cheating user selects the first option can be calculated according to the number of options included in the question to be verified. It can be understood that the first option refers to one of the multiple options included in the question to be verified. It can be understood that the embodiment of the present disclosure calculates the confidence level of each option in the question to be verified separately. Then, any one of the multiple options in the question to be verified can be used as the first option. For example, if the question to be verified includes options A and B, option A can be used as the first option first. After calculating the confidence level of option A, option B can be used as the first option to calculate the confidence level of option B.

[0158] It can be understood that the above examples are only examples listed to better understand the technical solution of the embodiment of the present disclosure and do not serve as the sole limitation to the embodiment of the present disclosure.

[0159] After obtaining the number of options included in the question to be verified, a first probability that the cheating user selects the first option can be calculated according to the number of options included in the question to be verified. The specific calculation process can be as shown in the following formula (1).

[0160]

[0161] In the above formula (1), t represents the number of options for the question to be verified, P(A|a) represents the first probability, a represents the first option, and A represents the event that the user clicks on the first option.

[0162] It can be understood that since the cheating user randomly selects options for each question to be verified, for each cheating user, the probability of selecting each option is the same. That is, when the number of options is t, the probability that the cheating user selects the first option is

[0163] After calculating the first probability that the cheating user selects the first option based on the number of options included in the question to be verified, sub-step S2 is executed.

[0164] Sub-step S2: Calculate the second probability that the cheating user passes the anti-cheating strategy based on the third quantity and the total number of all options included in the detection question.

[0165] The anti-cheating strategy is the strategy adopted in the embodiments of the present disclosure by mixing detection questions in the questions to be verified to screen out cheating users.

[0166] Of course, in actual applications, not all cheating users can be screened out by mixing detection questions, and there may still be some cheating users who pass the anti-cheating strategy.

[0167] The second probability refers to the second probability that the cheating user passes the anti-cheating strategy, that is, the second probability that a certain cheating user passes the anti-cheating strategy.

[0168] The total number of all options refers to the sum of the numbers of options corresponding to all the detection questions mixed in. For example, if the number of detection questions mixed in is 10 and the number of options for each detection question is 4, then the total number of all options included in the detection questions is 10 * 4 = 40.

[0169] After obtaining the third quantity of the detection questions mixed in and the total number of all options included in the detection questions, the second probability that the cheating user passes the anti-cheating strategy can be calculated. The specific calculation process can be referred to the following formula (2):

[0170]

[0171] In the above formula (2), h represents the second probability, e represents the third quantity, and L represents the total number of all options included in the detection questions mixed in.

[0172] By substituting the third quantity and the total number of all options included in the detection questions into the above formula (2), the second probability that the cheating user passes the anti-cheating strategy can be calculated.

[0173] Sub-step S3: Calculate the answering accuracy rate of the target user based on the second probability, the first number of people, and the second number of people.

[0174] The answering accuracy rate refers to the accuracy rate of the target user (non-cheating user) answering the question to be verified.

[0175] In the above process, after obtaining the second probability, the first number of people, and the second number of people, the answering accuracy rate of the target user can be calculated based on the second probability, the first number of people, and the second number of people. Specifically, the calculation process can be described in detail with reference to the following formula.

[0176] Suppose that in a certain answering session, a total of z people (i.e., the target users) pass the anti-cheating strategy, w people are identified as cheating users, the number of normal users (i.e., non-cheating users) is x, and the number of cheating users is y.

[0177] Then:

[0178] x + y = z + w (3)

[0179] z = x + hy (4)

[0180] In the above formulas (3) and (4), h is the second probability.

[0181] By integrating the above formulas (3) and (4), the following formulas (5) and (6) can be obtained:

[0182]

[0183]

[0184] In the above process, after the answer results of z people are randomly inspected, the overall accuracy rate is set as q. Then the calculation process of q can be shown as the following formula (7):

[0185]

[0186] In the above formula (7), r represents the answering accuracy rate of the target user.

[0187] After calculating the above formula (7), the following formula (8) can be obtained:

[0188]

[0189] The answering accuracy rate of the target user can be calculated through the above formula (8).

[0190] After calculating the answering accuracy rate of the target user based on the second probability, the first number of people, and the second number of people, execute sub-step S4.

[0191] Sub-step S4: Obtain the third number of people among the target users who select the first option and the fourth number of people who select the second option.

[0192] The third number of people refers to the number of people among the target users who select the first option, and the fourth number of people refers to the number of people among the target users who select the second option.

[0193] After receiving the answers to the question-and-answer questions from the users, according to the answers to the questions to be verified feedback by the target users, the third number of people who select the first option and the fourth number of people who select the second option can be obtained therefrom.

[0194] After obtaining the third number of people and the fourth number of people, execute sub-step S5.

[0195] Sub-step S5: Calculate the confidence level of the first option based on the first probability, the answer accuracy rate, the third number of people, and the fourth number of people.

[0196] Based on the first probability, the answer accuracy rate, the third number of people, and the fourth number of people obtained in the above process, the confidence level of the first option can be calculated.

[0197] In this step, the confidence level of the first option can be calculated in combination with the Bayesian formula, and the Bayesian formula can be as shown in the following formula (9):

[0198]

[0199] In the above formula (9), a is an option in the question (i.e., the first option in the present disclosure), b is the non-a option (i.e., the second option in the present disclosure), A is the event that the user clicks on option a, P(a|A) is the probability that a is the correct option when a user selects a; P(a) is the probability that a is the correct option (i.e., the target answer); P(b) is the probability that the correct option is non-a, P(A|a) is the probability that the user answers correctly, and P(A|b) is the probability that the user answers incorrectly.

[0200] In the embodiments of the present disclosure, referring to the Bayesian formula (the above formula (9)), substituting the first probability, the answer accuracy rate, the third number of people, and the fourth number of people obtained in the above process into the above formula (9) can obtain the following formula (10):

[0201]

[0202] In the above formula (10), a, b,..., t represent the options of a certain question to be verified, P(a) represents the probability that a is the correct option, N a represents the number of people who select a, N b represents the number of people who select b,..., N t represents the number of people who select t, P(N aN b ...N t |a) represents the probability that the total number of people selects a, P(a|N a N b ...N t ) represents the confidence level of the problem to be verified, P(t) represents the probability that t is the correct option, P(N a N b ...N t |t) represents the probability that the total number of people selects t.

[0203] In the above formula (10):

[0204]

[0205]

[0206] Among them, in the above formulas (11) and (12):

[0207]

[0208]

[0209] Through the above formulas (10), (11), (12), (13) and (14), the confidence level of the first option can be calculated.

[0210] After determining the confidence level of the first option based on the second quantity, the third quantity, the first number of people, the second number of people, the first option and the second option, step 210 is executed.

[0211] Step 210: Compare the confidence level of each option in the problem to be verified with the confidence level threshold.

[0212] The confidence level threshold refers to the threshold associated with the confidence level preset by the business personnel. The confidence level threshold can be 0.5, 0.6, 0.9, etc. Specifically, it can be determined according to business requirements, and the embodiments of the present disclosure do not limit this.

[0213] After obtaining the confidence level of each option in the problem to be verified, the confidence level of each option can be compared with the confidence level threshold respectively, and then the comparison result can be obtained.

[0214] After comparing the confidence level of each option in the problem to be verified with the confidence level threshold and obtaining the comparison result, step 211 is executed.

[0215] Step 211: Determine the target answer of each problem to be verified according to the comparison result.

[0216] After obtaining the comparison result, the target answer for each question to be verified can be determined according to the comparison result. For the process of determining the target answer, the following specific implementation manners can be combined for detailed description.

[0217] In a specific implementation of the present disclosure, the above step 211 may include:

[0218] Sub-step N1: Obtain the target option whose confidence level is greater than the confidence level threshold from each option of the question to be verified.

[0219] In the embodiments of the present disclosure, the target option refers to the option whose confidence level in each option of the question to be verified is greater than the confidence level threshold. For example, the question to be verified A includes options a, b, and c, the confidence level threshold is 0.5, the confidence level of option a is 0.4, the confidence level of option b is 0.6, and the confidence level of option c is 0.8. Then the target options in the question to be verified A are option b and option c.

[0220] It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present disclosure, and do not serve as the sole limitation of the embodiments of the present disclosure.

[0221] Of course, for each question to be verified, the number of target options of the question to be verified can be 0, 1, or 2 or more. Specifically, it can be determined according to the actual situation.

[0222] After obtaining the target option whose confidence level is greater than the confidence level threshold from each option of the question to be verified, sub-step N2 is executed.

[0223] Sub-step N2: When the number of the target options is at least one, use the target option with the highest confidence level as the target answer of the question to be verified; or, when the number of the target options is zero, determine that the target answer of the question to be verified is a null value.

[0224] For each question to be verified, the manner of determining the target answer according to the target option can be divided into the following two cases:

[0225] 1. The case where the number of target options of the question to be verified is at least one

[0226] a. When the number of target options of the question to be verified is 1, directly use this target option as the target answer option of the question to be verified;

[0227] b. When the number of target options for the question to be verified is two or more, the confidence levels corresponding to multiple target options can be obtained, and the target option with the highest confidence level can be extracted as the target answer option for the question to be verified. For example, if the target options for question A to be verified include option a and option b, and the confidence level of option a is 0.6 and that of option b is 0.8, then option b is used as the target answer option for A.

[0228] 2. The case where the number of target options for the question to be verified is zero

[0229] When there is no target option among the multiple options of the question to be verified, the target answer of the question to be verified is determined to be a null value, that is, there is no target answer option for this question to be verified.

[0230] By setting a confidence level threshold in the embodiments of the present disclosure, the accuracy of the adoption result of each question and answer can be obtained.

[0231] The answer acquisition method provided by the embodiments of the present disclosure, in addition to having the beneficial effects of the answer acquisition method provided in Embodiment 1, can also pre-set a confidence level threshold, and when the confidence level of the question and answer option is greater than the confidence level threshold, select the option with the highest confidence level as the adoption result, further improving the accuracy of the adoption result of each question and answer.

[0232] Embodiment 3

[0233] Refer to Figure 3 , which shows a schematic structural diagram of an answer acquisition device provided by the embodiments of the present disclosure. As Figure 3 shown, the device may specifically include the following modules:

[0234] The question and answer answer receiving module 310 is used to receive the answers of the first number of questions and answers fed back by multiple users; wherein, the question and answer includes the second number of questions to be verified and the third number of detection questions;

[0235] The target user screening module 320 is used to screen out at least one target user meeting the preset conditions from the multiple users according to the answers of the detection questions fed back by the multiple users;

[0236] The confidence level determination module 330 is used to determine the confidence level of each option in each question to be verified according to the answers of the questions to be verified fed back by the target users; and

[0237] The target answer determination module 340 is used to determine the target answer of each question to be verified according to the confidence level.

[0238] The question-and-answer obtaining device provided by the embodiments of the present disclosure receives the answers to the first number of question-and-answer questions fed back by multiple users. Among them, the question-and-answer questions include the second number of questions to be verified and the third number of detection questions. According to the answers to the detection questions fed back by multiple users, at least one target user meeting the preset conditions is screened out from multiple users. According to the answers to the questions to be verified fed back by the target user, the confidence level of each option in each question to be verified is determined, and according to the confidence level, the target answer of each question to be verified is determined. The embodiments of the present disclosure can effectively identify cheating users according to the detection questions. Moreover, for each option of each question to be verified, the confidence level is used as the final adoption basis, rather than determining the adoption result according to the number of people who choose each option, so that the finally obtained adoption result is more real, accurate, flexible and easy to understand.

[0239] Embodiment 4

[0240] Refer to Figure 4 , which shows the structural schematic diagram of an answer obtaining device provided by the embodiments of the present disclosure. As Figure 4 shown, the device may specifically include the following modules:

[0241] A question obtaining module 410, configured to obtain the questions to be verified and the detection questions;

[0242] A question-and-answer question generating module 420, configured to mix the detection questions into the questions to be verified to generate the question-and-answer questions;

[0243] A question-and-answer question pushing module 430, configured to push the question-and-answer questions to the multiple users;

[0244] A question-and-answer answer receiving module 440, configured to receive the answers to the first number of question-and-answer questions fed back by multiple users; among them, the question-and-answer questions include the second number of questions to be verified and the third number of detection questions;

[0245] A target user screening module 450, configured to screen out at least one target user meeting the preset conditions from the multiple users according to the answers to the detection questions fed back by the multiple users;

[0246] A confidence level determining module 460, configured to determine the confidence level of each option in each question to be verified according to the answers to the questions to be verified fed back by the target user; and

[0247] A target answer determining module 470, configured to determine the target answer of each question to be verified according to the confidence level.

[0248] In a specific implementation of the present disclosure, the target user screening module 450 includes:

[0249] The fourth quantity acquisition sub-module 4501 is configured to, for a single user among the multiple users, acquire a fourth quantity of correct answers of the single user to the detection questions according to the answers of the detection questions fed back by the single user; and

[0250] The target user determination sub-module 4502 is configured to determine that the single user is one of the target users when the fourth quantity is greater than a preset quantity threshold.

[0251] In a specific implementation of the present disclosure, the confidence determination module 460 includes:

[0252] The first and second number acquisition sub-module 4601 is configured to acquire a first number corresponding to the target user and a second number corresponding to a cheating user from the multiple users; the cheating user refers to a user who does not meet the preset conditions;

[0253] The option acquisition sub-module 4602 is configured to, for each of the questions to be verified, acquire a first option from multiple options corresponding to the question to be verified and at least one second option other than the first option; and

[0254] The confidence determination sub-module 4603 is configured to determine the confidence of the first option according to the second quantity, the third quantity, the first number, the second number, the first option and the second option.

[0255] In a specific implementation of the present disclosure, the confidence determination sub-module 4603 includes:

[0256] The first probability calculation sub-module is configured to calculate a first probability that the cheating user selects the first option according to the number of options included in the question to be verified;

[0257] The second probability calculation sub-module is configured to calculate a second probability that the cheating user passes the anti-cheating strategy according to the third quantity and the total number of options included in the detection questions;

[0258] The answering accuracy rate calculation sub-module is configured to calculate the answering accuracy rate of the target user according to the second probability, the first number and the second number;

[0259] The third and fourth number acquisition sub-module is configured to acquire a third number of the target users who select the first option and a fourth number of those who select the second option; and

[0260] The confidence calculation sub-module is configured to calculate the confidence of the first option according to the first probability, the answering accuracy rate, the third number and the fourth number.

[0261] In a specific implementation of the present disclosure, the target answer determination module 470 includes:

[0262] A confidence level comparison sub-module 4701, configured to compare the confidence level of each option in the question to be verified with a confidence level threshold; and

[0263] A target answer determination sub-module 4702, configured to determine the target answer of each question to be verified according to the comparison result.

[0264] In a specific implementation of the present disclosure, the target answer determination sub-module 4702 includes:

[0265] A target option acquisition sub-module, configured to acquire, from each option of the question to be verified, a target option whose confidence level is greater than the confidence level threshold; and

[0266] A target answer acquisition sub-module, configured to, when the number of target options is at least one, use the target option with the highest confidence level as the target answer of the question to be verified; or, when the number of target options is zero, determine that the target answer of the question to be verified is a null value.

[0267] In addition to having the beneficial effects of the answer acquisition device provided in Embodiment 3, the answer acquisition device provided in the embodiments of the present disclosure can also preset a confidence level threshold, and when the confidence level of the options of a question-and-answer question is greater than the confidence level threshold, select the option with the highest confidence level as the adoption result, further improving the accuracy of obtaining the adoption result of each question-and-answer question.

[0268] The embodiments of the present disclosure also provide an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, where the processor implements the answer acquisition method of the foregoing embodiments when executing the program.

[0269] The embodiments of the present disclosure also provide a readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the answer acquisition method of the foregoing embodiments.

[0270] For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, reference may be made to the partial description of the method embodiments.

[0271] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used in conjunction with the teachings based hereon. The structure required to construct such systems will be apparent from the above description. In addition, embodiments of the present disclosure are not directed to any particular programming language. It should be appreciated that the content of the embodiments of the present disclosure described herein can be implemented using various programming languages, and the description of a particular language above is for the purpose of disclosing the best mode of the embodiments of the present disclosure.

[0272] In the specification provided herein, numerous specific details are set forth. However, it can be understood that embodiments of the present disclosure may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0273] Similarly, it should be understood that in order to streamline the present disclosure and assist in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present disclosure, the various features of the embodiments of the present disclosure are sometimes grouped together in a single embodiment, figure, or description thereof. However, the disclosed methods should not be construed as reflecting an intention that the embodiments of the present disclosure as claimed require more features than are expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspects lie in less than all of the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present disclosure.

[0274] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and disposed in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature providing the same, equivalent, or similar purpose.

[0275] Each component embodiment of the embodiments of the present disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the dynamic picture generation device according to the embodiments of the present disclosure. The embodiments of the present disclosure may also be implemented as a device or device program for executing part or all of the methods described herein. Such a program implementing the embodiments of the present disclosure may be stored on a computer-readable medium, or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0276] It should be noted that the above embodiments illustrate the embodiments of the present disclosure rather than limit the embodiments of the present disclosure, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The embodiments of the present disclosure can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words may be interpreted as names.

[0277] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above may refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0278] The above are only the preferred embodiments of the embodiments of the present disclosure and are not intended to limit the embodiments of the present disclosure. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the embodiments of the present disclosure shall be included in the protection scope of the embodiments of the present disclosure.

[0279] The above is only the specific implementation manner of the embodiments of the present disclosure, but the protection scope of the embodiments of the present disclosure is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the embodiments of the present disclosure, and all of them should be covered by the protection scope of the embodiments of the present disclosure. Therefore, the protection scope of the embodiments of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method for obtaining answers, characterized in that, it includes: Receiving answers to a first quantity of question-and-answer questions feedback by multiple users; wherein, the question-and-answer questions include a second quantity of questions to be verified and a third quantity of detection questions; According to the answers to the detection questions feedback by the multiple users, screening out at least one target user meeting a preset condition from the multiple users; According to the answers to the questions to be verified feedback by the target user, determining the confidence level of each option in each of the questions to be verified; and according to the confidence level, determining the target answer of each of the questions to be verified; The step of determining the confidence level of each option in each of the questions to be verified according to the answers to the questions to be verified feedback by the target user includes: Obtaining a first number of people corresponding to the target user and a second number of people corresponding to cheating users from the multiple users; the cheating users refer to users not meeting the preset condition; For each of the questions to be verified, obtaining a first option among multiple options corresponding to the question to be verified, and at least one second option other than the first option; and according to the second quantity, the third quantity, the first number of people, the second number of people, the first option and the second option, determining the confidence level of the first option.

2. The method according to claim 1, characterized in that, before the step of receiving answers to a first quantity of question-and-answer questions feedback by multiple users, it further includes: Obtaining the questions to be verified and the detection questions; Mixing the detection questions into the questions to be verified to generate the question-and-answer questions; and pushing the question-and-answer questions to the multiple users.

3. The method according to claim 1, characterized in that, the step of screening out at least one target user meeting a preset condition from the multiple users according to the answers to the detection questions feedback by the multiple users includes: For a single user among the multiple users, obtaining a fourth quantity of correct answers to the detection questions by the single user according to the answers to the detection questions feedback by the single user; and in the case where the fourth quantity is greater than a preset quantity threshold, determining the single user as one of the target users.

4. The method according to claim 1, characterized in that, the step of determining the confidence level of the first option according to the second quantity, the third quantity, the first number of people, the second number of people, the first option and at least one of the second options includes: Calculating a first probability that the cheating users select the first option according to the number of options included in the question to be verified; Calculating a second probability that the cheating users pass the anti-cheating strategy according to the third quantity and the total number of options included in the detection questions; Calculate the answering accuracy rate of the target user based on the second probability, the first number of people, and the second number of people; obtain the third number of people who select the first option and the fourth number of people who select the second option among the target users; and calculate the confidence level of the first option based on the first probability, the answering accuracy rate, the third number of people, and the fourth number of people.

5. The method according to claim 1, wherein, the step of determining the target answer for each of the to-be-verified questions based on the confidence level includes: comparing the confidence level of each option in the to-be-verified question with a confidence level threshold; and determining the target answer for each of the to-be-verified questions based on the comparison result.

6. The method according to claim 5, wherein, the step of determining the target answer for each of the to-be-verified questions based on the comparison result includes: obtaining, from each option of the to-be-verified question, a target option whose confidence level is greater than the confidence level threshold; and when the number of the target options is at least one, taking the target option with the highest confidence level as the target answer of the to-be-verified question; or when the number of the target options is zero, determining that the target answer of the to-be-verified question is a null value.

7. An answer acquisition device, wherein, comprising: a short-answer question answer receiving module, configured to receive answers to a first number of short-answer questions fed back by a plurality of users; wherein, the short-answer questions include a second number of to-be-verified questions and a third number of detection questions; a target user screening module, configured to screen out at least one target user meeting a preset condition from the plurality of users according to the answers to the detection questions fed back by the plurality of users; a confidence level determination module, configured to determine the confidence level of each option in each of the to-be-verified questions according to the answers to the to-be-verified questions fed back by the target users; and a target answer determination module, configured to determine the target answer for each of the to-be-verified questions based on the confidence level; the step of determining the confidence level of each option in each of the to-be-verified questions according to the answers to the to-be-verified questions fed back by the target users includes: obtaining, from the plurality of users, the first number of people corresponding to the target users and the second number of people corresponding to cheating users; the cheating users refer to users who do not meet the preset condition; for each of the to-be-verified questions, obtaining a first option among a plurality of options corresponding to the to-be-verified question and at least one second option other than the first option; and determining the confidence level of the first option based on the second number, the third number, the first number of people, the second number of people, the first option, and the second option.

8. An electronic device, wherein, comprising: a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, it implements the answer acquisition method according to one or more of claims 1 to 6.

9. A readable storage medium, wherein, When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the answer acquisition method as recited in one or more of method claims 1 to 6.

Images