Question group updating method, device, computer equipment and storage medium

Abstract

Embodiments of the present invention disclose a method, apparatus, device, and storage medium for updating question groups. The method comprises: obtaining an overall consistency parameter of a question group to be optimized; determining a target question within the question group to be optimized if the overall consistency parameter is less than a preset consistency threshold; obtaining a target question group that matches the target question, and updating the target question from the question group to be optimized to the target question group. Embodiments of the present invention can achieve automated updating of question groups, ensuring the efficiency and accuracy of the question group update process, thereby improving the effective utilization of questions.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular to a method, apparatus, computer device, and storage medium for updating topic groups. Background Art

[0002] In the field of AI-powered online education, the core of personalized learning lies in adaptive recommendation models. This involves recommending learning resources with varying content and sequences based on individual learners' performance and inherent abilities, thereby planning diverse learning paths. Questions are the core learning resource, and the key information that determines whether a question matches a learner's learning profile is the group in which it appears.

[0003] In existing technology, questions are typically grouped based on "knowledge point + difficulty," typically assigned by content developers when they write the questions. A single knowledge point and difficulty level often have multiple questions, and a single question may also relate to multiple knowledge points. This correspondence allows for targeted improvement.

[0004] However, due to the dynamic changes in learners' overall proficiency and the inevitable oversights in manual question grouping, some questions may not fit into their assigned groups. For example, within the same group, questions may appear too easy or too difficult, have low discrimination, or reduce the overall test reliability. A simple approach to this problem is to remove them directly from the question bank. A more detailed but labor-intensive approach is to provide feedback to expert teachers to modify the question grouping and conduct subsequent verification. The former approach is too crude, wastes resources, and increases the burden of question development. The latter approach, while retaining the questions, is labor-intensive and difficult to implement in a large-scale, automated manner. Summary of the Invention

[0005] The embodiments of the present invention provide a method, apparatus, computer device and storage medium for updating question groups, so as to realize automatic updating of question groups, ensure the efficiency and accuracy of the question group updating process, and thus improve the effective utilization rate of questions.

[0006] In a first aspect, an embodiment of the present invention provides a method for updating topic groups, comprising:

[0007] Obtain the overall consistency parameters of the problem set to be optimized;

[0008] When it is determined that the overall consistency parameter is less than a preset consistency threshold, determining a target question in the set of questions to be optimized;

[0009] Obtain a target question group that matches the target question, and update the target question from the question group to be optimized to the target question group.

[0010] In a second aspect, an embodiment of the present invention further provides a topic grouping updating device, comprising:

[0011] The overall consistency acquisition module is used to obtain the overall consistency parameters of the problem set to be optimized;

[0012] a target question determination module, configured to determine a target question in the set of questions to be optimized if it is determined that the overall consistency parameter is less than a preset consistency threshold;

[0013] The target question group updating module is used to obtain a target question group that matches the target question, and update the target question from the question group to be optimized to the target question group.

[0014] In a third aspect, an embodiment of the present invention further provides a computer device, comprising:

[0015] one or more processors;

[0016] a storage device for storing one or more programs;

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the topic grouping updating method provided by any embodiment of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the topic grouping updating method provided by any embodiment of the present invention.

[0019] The embodiment of the present invention obtains the consistency parameters of the question group to be optimized, and determines that there are mismatched questions in the question group to be optimized based on the fact that its consistency parameters are less than a preset threshold, and determines the mismatched target questions from them, and then determines a more matching grouping for the target questions, thereby realizing the optimization and update of the question grouping, solving the technical problems in the prior art of waste of question resources or excessively high cost of regrouping questions due to inappropriate question grouping, realizing the automatic update of question grouping, ensuring the efficiency and accuracy of the question grouping update process, and thereby improving the effective utilization rate of questions. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flowchart of a method for updating topic groups provided in Example 1 of the present invention.

[0021] Figure 2 This is a flowchart of a method for updating topic groups provided in the second embodiment of the present invention.

[0022] Figure 3 This is a flow chart of a method for updating topic groups provided in the second embodiment of the present invention.

[0023] Figure 4 This is a schematic diagram of an Excel interface for recording the scoring results of the question set to be optimized, provided in Example 2 of the present invention.

[0024] Figure 5 A schematic diagram of an Excel interface for calculating and recording overall consistency parameters provided in Example 2 of the present invention.

[0025] Figure 6 A schematic diagram of an Excel interface for calculating and recording residual consistency parameters provided in Example 2 of the present invention.

[0026] Figure 7 This is a schematic diagram of an Excel interface for calculating and recording target question discrimination parameters provided in Example 2 of the present invention.

[0027] Figure 8 This is a schematic diagram of an Excel interface for calculating and recording question score rate parameters provided in Example 2 of the present invention.

[0028] Figure 9 This is a schematic diagram of an Excel interface for recording the scoring results of associated low-difficulty question groups provided in Example 2 of the present invention.

[0029] Figure 10 A schematic diagram of an Excel interface for calculating and recording independent consistency parameters and combined consistency parameters provided in Example 2 of the present invention.

[0030] Figure 11 This is a structural diagram of a question grouping and updating device provided in the third embodiment of the present invention.

[0031] Figure 12 A schematic diagram of the structure of a computer device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0032] The present invention will be further described in detail below 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 invention, rather than to limit the present invention.

[0033] It should also be noted that, for ease of description, only portions relevant to the present invention are shown in the accompanying drawings, rather than all of the contents. Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the various operations (or steps) as sequential processes, many of the operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of the various operations can be rearranged. The process can be terminated when its operations are completed, but may also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0034] Example 1

[0035] Figure 1 This is a flowchart of a method for updating topic groups provided in the first embodiment of the present invention. This embodiment is applicable to the case of automatically updating topic groups. This method can be executed by the topic group updating device provided in the embodiment of the present invention. The device can be implemented by software and / or hardware and can generally be integrated into a computer device. Figure 1 As shown, the method includes the following operations:

[0036] S110: Obtain the overall consistency parameter of the problem set to be optimized.

[0037] The set of questions to be optimized may be a collection of questions with the same or similar features, and the overall consistency parameter may be data positively correlated with the degree of similarity in features between the questions in the set of questions to be optimized.

[0038] Accordingly, the specific features of each question can be evaluated, so that all questions that need to be grouped can be divided according to the degree of similarity between the features of each question, and questions with the same or similar features can be divided into the same question group. Specifically, the features used for grouping questions can be any features that can describe the quality of the question, for example, they can include the knowledge points tested by the question and the difficulty of the question. The strictness of the similarity requirements for the features between each question in the same question group can be determined as needed. The feature evaluation and grouping of the questions can be achieved through manual evaluation and marking methods, or through automated methods.

[0039] Furthermore, after determining the problem groupings, due to the dynamic changes in learners' overall proficiency and potential errors in automatic or manual problem grouping, each problem group can be tested and optimized to ensure high consistency across all problems within the same problem group. The problem group to be optimized can be any problem group that requires testing, and its overall consistency parameter can be obtained to determine the degree of feature similarity between all problems currently included in the problem group to be optimized. This degree of feature similarity can then be used to determine whether there are any mismatched problems within the problem group to be optimized.

[0040] Optionally, obtaining the overall consistency parameter of the problem set to be optimized may include: obtaining the total number of problems in the problem set to be optimized, the scores of individual problems and the total score obtained by the learners in answering the problems in the problem set to be optimized; calculating the Cronbach's square root of the problem set to be optimized based on the total number of problems, the scores of individual problems and the total score. Coefficient, as the overall consistency parameter of the problem set to be optimized.

[0041] Specifically, the Cronbach's equation corresponding to the problem set to be optimized can be calculated according to the following formula: coefficient:

[0042]

[0043] Among them, n is the total number of questions in the question group to be optimized, is the variance of the single-question scores obtained by learners when answering questions in the optimization question set. is the variance of the total scores obtained by learners in answering the questions in the optimization question set. For example, Table 1 is a commonly used Cronbach's Correspondence table between coefficients and internal consistency evaluation of question sets. Cronbach The higher the coefficient value, the higher the feature similarity between the questions in the question set to be optimized.

[0044] Table 1

[0045]

[0046] S120: When it is determined that the overall consistency parameter is less than a preset consistency threshold, a target question is determined in the set of questions to be optimized.

[0047] The preset consistency threshold can be the lowest value that the overall consistency parameter of the same set of questions can reach when all questions in the same set have the same or similar characteristics. The target question can be a question in the set of questions to be optimized that has different or similar characteristics from other questions.

[0048] Accordingly, the preset consistency threshold can be predetermined based on the value range of the overall consistency parameter and the requirements for the similarity of features between each question within each question group, that is, the higher the requirements for the similarity of features between each question within each question group, the higher the preset consistency threshold can be within the value range of the overall consistency parameter. Therefore, if the overall consistency parameter of the question group to be optimized is less than the preset consistency threshold, it can be explained that the feature similarity between each question in the question group to be optimized does not meet the grouping requirements, and the feature similarity between the target question and other questions in the question group to be optimized is relatively low, that is, according to the grouping requirements, the target question does not match the question group to be optimized to which it currently belongs. Further, in the case of determining that there is a target question in the question group to be optimized that does not match the group, the target question can be determined in the question group to be optimized.

[0049] S130: Obtain a target question group that matches the target question, and update the target question from the question group to be optimized to the target question group.

[0050] The target question group may be a question group that matches the target question, and the feature similarity between each question in the target question group and the target question may meet the grouping requirements.

[0051] Correspondingly, after determining the target question in the question group to be optimized, the most matching target question group can be determined for it based on its characteristics, and then the target question can be removed from the question group to be optimized to which it currently belongs and added to the target question group to ensure that the questions in the question group to be optimized that do not match it are removed. At the same time, the removed questions can be regrouped into a more matching question group.

[0052] An embodiment of the present invention provides a method for updating question groups. By obtaining the consistency parameters of the question group to be optimized, and based on the fact that its consistency parameters are less than a preset threshold, it is determined that there are questions in the question group to be optimized that do not match it, and the unmatched target question is determined therefrom, and then a more matching group is determined for the target question, thereby realizing the optimization and update of the question grouping. This solves the technical problems in the prior art of waste of question resources or excessively high cost of regrouping questions due to inappropriate question grouping, realizes the automatic update of question grouping, ensures the efficiency and accuracy of the question grouping update process, and thereby improves the effective utilization rate of questions.

[0053] Example 2

[0054] Figure 2 This is a flow chart of a method for updating question groups provided in the second embodiment of the present invention. This embodiment of the present invention is specific based on the above embodiment, and provides a specific optional implementation method for determining the target question in the group of questions to be optimized.

[0055] like Figure 2As shown, the method of the embodiment of the present invention specifically includes:

[0056] S210: Obtain the overall consistency parameter of the problem set to be optimized.

[0057] S220: Determine whether the overall consistency parameter is less than a preset consistency threshold. If so, execute steps S230 to S240; otherwise, execute S250.

[0058] S230: Determine a target question in the set of questions to be optimized.

[0059] In an optional embodiment of the present invention, S230 may specifically include:

[0060] S231 , determining the questions in the group of questions to be optimized as pending questions in sequence, and obtaining the remaining consistency parameters of the remaining questions in the group of questions to be optimized except the pending questions.

[0061] The pending questions may be any questions in the set of questions to be optimized that need to be determined to be compatible with the set of questions to be optimized. The remaining questions may be all questions in the set of questions to be optimized except the pending questions. The remaining consistency parameter may be data positively correlated with the degree of feature similarity between the remaining questions in the same set of questions, and may be obtained using a method for obtaining an overall consistency parameter.

[0062] Correspondingly, if the overall consistency parameter of the question group to be optimized is less than the preset consistency threshold, it can be determined that there are target questions in the question group to be optimized that do not match it, and the questions in the question group to be optimized can be determined as pending questions in turn to determine whether each question in the question group to be optimized matches it.

[0063] Furthermore, after determining any pending problem, the remaining consistency parameters of the remaining problems in the set of problems to be optimized, excluding the pending problem, can be obtained. Based on the remaining overall consistency parameters, the feature similarity between the remaining problems can be determined. By sequentially treating the problems in the set of problems to be optimized as pending problems and obtaining the corresponding remaining consistency parameters, multiple groups of remaining problems, equal in number to the total number of problems in the set of problems to be optimized, and the corresponding remaining consistency parameters can be obtained.

[0064] S232: When it is determined that any of the remaining consistency parameters is greater than the overall consistency parameter, determine a target consistency parameter according to the remaining consistency parameter.

[0065] The target consistency parameter may be at least one remaining consistency parameter with the highest value among the remaining consistency parameters that are greater than the overall consistency parameter.

[0066] Correspondingly, if any residual consistency parameter is greater than the overall consistency parameter, it indicates that at least one question in the set of questions to be optimized, after being removed, can increase the feature similarity of the questions within the set of questions to be optimized to a higher level than the original feature similarity. A higher residual consistency parameter indicates a higher feature similarity between the corresponding remaining questions, and the set of questions composed of these remaining questions has a higher accuracy in question grouping.

[0067] Furthermore, a target consistency parameter can be determined from the remaining consistency parameters that are greater than the overall consistency parameter. The number of target consistency parameters can be determined as needed. For example, the difference between each remaining consistency parameter and the overall consistency parameter can be obtained, and the remaining consistency parameter with the largest positive difference can be determined as the target consistency parameter. Alternatively, one or more remaining consistency parameters with a difference greater than a certain threshold can be determined as the target consistency parameter.

[0068] S233. Acquire the pending topic corresponding to the target consistency parameter as the target topic.

[0069] Correspondingly, if the remaining consistency parameters of the remaining questions corresponding to any pending question are determined as the target consistency parameters, it can be said that after the pending question is removed from the group of questions to be optimized, the feature similarity of the questions within the group of questions to be optimized can be improved to the greatest extent, so the pending question can be determined as the target question.

[0070] S240: Obtain a target question group that matches the target question, and update the target question from the question group to be optimized to the target question group.

[0071] In an optional embodiment of the present invention, obtaining a target question group that matches the target question may include: obtaining a discrimination parameter of the target question; when determining that the discrimination parameter is less than or equal to a preset discrimination threshold, obtaining a knowledge point question group associated with the question group to be optimized, and determining the target question group in the associated knowledge point question group.

[0072] Among them, the discrimination parameter can be data that is positively correlated with the discrimination of the target question for the knowledge point tested by the set of questions to be optimized. The discrimination of a question is used to describe the degree of correlation between the scores obtained by learners with different levels of mastery of a specific knowledge point and their level of mastery of the knowledge point; if learners with higher levels of mastery of the knowledge point get higher scores for answering the question, the correlation is higher and the discrimination of the question is higher. The preset discrimination threshold can be the minimum value that any question can have for the discrimination of the knowledge point it tests. The set of questions with related knowledge points can be a set of questions in which the knowledge points tested belong to the same parent knowledge point as the knowledge points tested by the set of questions to be optimized.

[0073] Accordingly, when grouping questions, the knowledge points tested by the questions can be taken into consideration, and questions that test the same knowledge point can be divided into the same question group. Then, the questions in the same question group are all used to test the same knowledge point, that is, the discrimination for the same knowledge point is the same or similar. If the discrimination parameter of the target question is less than or equal to the preset discrimination threshold, it can be said that the discrimination of the target question for the knowledge point tested by the question group to be optimized is small, that is, the score obtained by any learner in answering the target question cannot accurately reflect the learner's level of mastery of the knowledge point. Therefore, when it is determined that the discrimination parameter of the target question is less than or equal to the preset discrimination threshold, it can be determined that the group that better matches the target question may be the associated knowledge point question group of the question group to be optimized, and then each associated knowledge point question group can be obtained to determine the target question group in each associated knowledge point question group.

[0074] Optionally, obtaining the discrimination parameter of the target question may include: obtaining the target question score obtained by each learner for answering the target question, the total score obtained by each learner for answering all questions in the optimized question set, and the total number of learners; and calculating the Pearson correlation coefficient of the target question based on the target question score, the total score, and the total number of learners as the discrimination parameter of the target question.

[0075] Specifically, the Pearson correlation coefficient of the target question can be calculated according to the following formula: :

[0076]

[0077] in, is the covariance between the target question score sequence and the total score sequence, is the standard deviation of the target question scores, is the standard deviation of the total score. Further, the covariance can be calculated according to the following formula :

[0078]

[0079] Where x is the score of the target question of the individual student, is the average score of the target questions of the students, y is the total score of the individual students, is the average total score of students, and m is the total number of students.

[0080] For example, Table 2 shows a commonly used correspondence table between the Pearson correlation coefficient and the evaluation of question discrimination. The higher the value of the Pearson correlation coefficient, the better the discrimination of the question for the knowledge point.

[0081] Table 2

[0082]

[0083] The above implementation method is based on the discrimination degree of questions for knowledge points, and realizes the elimination of questions with grouping deviations in the question group based on the knowledge points tested by each question, thereby ensuring that questions in the same question group all test the same knowledge point and optimizing the consistency of questions within the question group.

[0084] In an optional embodiment of the present invention, obtaining a target question group that matches the target question may include: obtaining a discrimination parameter of the target question; when it is determined that the discrimination parameter is greater than a preset discrimination threshold, obtaining a difficulty question group associated with the question group to be optimized, and determining the target question group in the difficulty question group associated.

[0085] Among them, the related difficulty question group can be a question group that tests the same knowledge point as the question group to be optimized but has a different difficulty level.

[0086] Correspondingly, if the discrimination parameter of the target question is greater than the preset discrimination threshold, it can be said that the discrimination of the target question for the knowledge point tested by the question group to be optimized is large enough, that is, the score obtained by any learner in answering the target question can accurately reflect the learner's mastery level of the knowledge point.

[0087] Furthermore, question difficulty can be considered when grouping questions, so that questions within the same question group have the same or similar difficulty. Different question groups examining the same knowledge point can then correspond to different difficulty levels. Therefore, if the discrimination parameter of the target question is determined to be greater than a preset discrimination threshold, it can be determined that the group that better matches the target question is likely a question group of related difficulty levels of the question group to be optimized. The related difficulty question groups can then be obtained to determine the target question group within the related difficulty question groups.

[0088] In an optional embodiment of the present invention, obtaining the difficulty question group associated with the question group to be optimized may include: obtaining the scoring rate parameter of the target question and the average scoring rate of the remaining questions in the question group to be optimized except the target question; when it is determined that the scoring rate parameter is less than the average scoring rate, obtaining the high-difficulty question group associated with the question group to be optimized; when it is determined that the scoring rate parameter is greater than the average scoring rate, obtaining the low-difficulty question group associated with the question group to be optimized.

[0089] The scoring rate parameter may be data that is negatively correlated with the difficulty of the question. The average scoring rate may be the average of the scoring rate parameters of the remaining questions. The associated high-difficulty question group may be a question group that tests the same knowledge point as the question group to be optimized, but is more difficult than the question group to be optimized. The associated low-difficulty question group may be a question group that tests the same knowledge point as the question group to be optimized, but is less difficult than the question group to be optimized.

[0090] Correspondingly, if the score rate parameter of the target question is less than the average score rate of the remaining questions, it can be said that the difficulty of the target question is higher than the average difficulty of the remaining questions. In this case, it is determined that the group that better matches the target question may be the associated high-difficulty question group of the question group to be optimized. Then, each associated high-difficulty question group can be obtained to determine the target question group among each associated high-difficulty question group. If the score rate parameter of the target question is greater than the average score rate of the remaining questions, it can be said that the difficulty of the target question is lower than the average difficulty of the remaining questions. In this case, it is determined that the group that better matches the target question may be the associated low-difficulty question group of the question group to be optimized. Then, each associated low-difficulty question group can be obtained to determine the target question group among each associated low-difficulty question group.

[0091] Specifically, the scoring rate parameter of a question may be the average value of the ratio of the score obtained by the learner for answering the question to the total score of the question, or may be the passing rate or correct rate of the learner's answer to the question.

[0092] Optionally, obtaining the score rate parameter of the target question or any remaining questions may include: obtaining the average score of each learner's answers to the target question or the remaining questions, and the total score of the questions answered by the learner; and calculating the score rate of the question based on the average score and the total score.

[0093] Specifically, the scoring rate parameter of the question can be calculated according to the following formula:

[0094]

[0095] in, is the scoring rate parameter of question i, i=1,2,3,...,n, is the mean score of m students on question i, j=1,2,3,...,m, is the total score of question i. The value of the scoring rate parameter ranges from 0 to 1. The smaller the value, the more difficult the question; the larger the value, the easier the question.

[0096] In an optional embodiment of the present invention, determining a target question group from associated knowledge point question groups or associated difficulty question groups may include: respectively obtaining independent consistency parameters of each associated knowledge point question group or each associated difficulty question group, and combined consistency parameters of all questions in each associated knowledge point question group or each associated difficulty question group and the target question; when it is determined that the combined consistency parameter corresponding to any of the associated knowledge point question groups or the associated difficulty question groups is greater than or equal to the independent consistency parameter, determining a target combined consistency parameter based on the combined consistency parameter; and obtaining the associated knowledge point question group or the associated difficulty question group corresponding to the target combined consistency parameter as the target question group.

[0097] The independent consistency parameter may be data positively correlated with the feature similarity between each question in the associated knowledge point question group or associated difficulty question group. The combined consistency parameter may be data positively correlated with the feature similarity between each question, including questions within the associated knowledge point question group or associated difficulty question group and the target question, and may be obtained using the independent consistency parameter acquisition method. The target combined consistency parameter may be the combined consistency parameter with the highest value among the combined consistency parameters that are greater than the independent consistency parameter.

[0098] Correspondingly, if the combined consistency parameter is greater than or equal to the independent consistency parameter, it means that if the target question is added to the associated knowledge point question group or associated difficulty question group corresponding to the combined consistency parameter, the feature similarity of the questions within the new question group obtained will increase or remain unchanged. Furthermore, the higher the combined consistency parameter, the higher the feature similarity between the target question and the original questions in the corresponding associated knowledge point question group or associated difficulty question group, and the new question group obtained by regrouping the target question into the question group has a higher question grouping accuracy. Therefore, among the combined consistency parameters that are greater than the independent consistency parameter, the combined consistency parameter with the highest value can be obtained as the target combined consistency parameter.

[0099] In an optional embodiment of the present invention, after obtaining the independent consistency parameters of each related knowledge point question group or each related difficulty question group, and the combined consistency parameters of all questions in each related knowledge point question group or each related difficulty question group and the target question, it may also include: when it is determined that the combined consistency parameters are all smaller than the independent consistency parameters, stopping obtaining the target question group that matches the target question; or determining the target launch status of the target question.

[0100] The target push state may be a state describing the process of obtaining a target question group that matches the target question.

[0101] Correspondingly, if the combined consistency parameters are all smaller than the independent consistency parameters, it can be explained that no matter whether the target question is added to any associated knowledge point question group or associated difficulty question group, the feature similarity of the questions within the newly generated question group will decrease, that is, the grouping accuracy of the original associated knowledge point question group or associated difficulty question group will be destroyed. Therefore, it is possible to stop obtaining the target question group that matches the target question.

[0102] Furthermore, the target launch status of the target question can also be determined as temporarily unable to obtain its matching target question group, so that the target question can be marked or fed back to the backend administrator to indicate that the target question needs to be further modified, further updated or deleted.

[0103] S250. Determine that the problem group to be optimized does not need to be optimized.

[0104] Correspondingly, if the overall consistency parameter of the question group to be optimized is greater than or equal to the preset consistency threshold, it means that the feature similarity between the internal questions is high enough, and according to the grouping requirements, it can be determined that each question matches the question group to be optimized.

[0105] For example, Figure 3 : is a flowchart of a method for updating topic groups provided by the second embodiment of the present invention. In a specific example, Figure 3 As shown, if there are 3 questions in the knowledge point K difficulty D question group, namely q1, q2 and q3, you can use Indicates this question group. At the same time, 3 students have scored on these 3 questions. You can use Excel software to record the scores and perform subsequent calculations. Figure 4 This is a schematic diagram of the Excel interface for recording the score results of the problem group to be optimized, as shown below: Figure 4 As shown, the score values ​​are written into cells B2 to D4.

[0106] In the question group During the detection or optimization process, first, Figure 4 Calculation Problems Cronbach The coefficient serves as the overall consistency parameter. Figure 5 This is a schematic diagram of the Excel interface for calculating and recording overall consistency parameters, as shown in the following figure: Figure 5 As shown, first calculate the total score of each student for the three questions and write them into cells E2 to E4 respectively; then calculate the variance var of each question score column and the total score column and write them into cells B5 to E5; using each variance as input, combined with the Excel formula fx=(1-SUM(B5:D5) / E5)*3 / 2, the total score of the complete set of questions can be calculated. , written into cell B9.

[0107] If the consistency threshold is preset ,at this time , the consistency of the question set does not meet the standard, and it is necessary to calculate the Cronbach's squares of the remaining two questions after deleting q1, q2 and q3 in sequence. coefficient 、 and . Figure 6 This is a schematic diagram of the Excel interface for calculating and recording the remaining consistency parameters, as shown in the following figure: Figure 6 As shown, calculate the individual total score after removing the three questions and write it in cells F2 to H4; calculate the variance of the three new total score columns and write it in cells F5 to H5; use the relevant Excel formula to get the individual total score after removing the three questions. 、 and , written into cells B8~D8. Then we can determine whether there is , and All less than , so q2 is not suitable for this question group, that is, the target question q obj = q2.

[0108] Furthermore, the Pearson correlation coefficient r2 of question q2 is calculated as the discrimination parameter of the target question. Figure 7 This is a diagram of the Excel interface for calculating and recording the discrimination parameters of the target questions, as shown below: Figure 7 As shown, the Pearson correlation coefficient r2 for question q2, calculated using the relevant Excel formula, is written into cell C7. Additionally, cells B7 and D7 contain the Pearson correlation coefficient r1 for question q1 and the Pearson correlation coefficient r3 for question q3, respectively, which are optional calculations.

[0109] If the preset discrimination threshold ,at this time , which means that when this question measures the level of the corresponding knowledge point, it basically conforms to the rule that high-level people get high scores and low-level people get low scores. Better grouping may be in other difficulty groups under the current knowledge point, and then we need to obtain the difficulty of the three questions in the current group. Figure 8 This is a schematic diagram of the Excel interface for calculating and recording the question score rate parameters, as shown in the following figure: Figure 8 As shown, the score rates P1, P2, and P3 of questions q1, q2, and q3 calculated using the relevant Excel formula are written into cells B6 to D6. Since all question scores are normalized to between 0 and 1, the score rate is equivalent to the mean of the corresponding question score column. Therefore, we can get , then the target question q2 may belong to a lower difficulty group of the same knowledge point, and the associated low difficulty question group can be obtained to finally locate the target question group.

[0110] If we take the case where there is only one group of low-difficulty questions associated with the original question group, we need to check the Cronbach's coefficient obtained by putting the target question into this group. Is the coefficient greater than the original Cronbach's The coefficient has decreased. Figure 9 This is a schematic diagram of the Excel interface for recording the score results of the associated low-difficulty question group, as shown in Figure 9 As shown, cells B2 to D4 contain the scores of the three students on the original questions in the associated low-difficulty question set, and cells E2 to E4 contain the scores of the target questions added to the question set. Figure 10 Schematic diagram of the Excel interface for calculating and recording independent consistency parameters and combined consistency parameters, as shown below Figure 10 As shown, the combined consistency parameters of the above 4 complete questions are , the independent consistency parameter after removing the target question , then calculate Therefore, the associated low-difficulty question group is a new grouping of target questions, and the target questions match the knowledge points and difficulty tested by the associated low-difficulty question group.

[0111] An embodiment of the present invention provides a method for updating question grouping, which obtains the consistency parameter of the question group to be optimized, and determines the existence of mismatched questions in the question group to be optimized based on the fact that its consistency parameter is less than a preset threshold value, and determines the mismatched target question therefrom, and then determines a more matching grouping for the target question, thereby realizing the optimization and update of the question grouping, solving the technical problems in the prior art of waste of question resources or excessive cost of regrouping questions due to inappropriate question grouping, realizing the automatic update of question grouping, ensuring the efficiency and accuracy of the question grouping update process, and thereby improving the effective utilization rate of questions; further, based on the judgment of the internal consistency changes of the new question group generated after removing or adding any question, it is possible to accurately locate the inappropriately grouped questions and the question group for which the question is suitable.

[0112] Example 3

[0113] Figure 11 This is a structural diagram of a topic group updating device provided by the third embodiment of the present invention, such as Figure 11 As shown, the apparatus includes: an overall consistency acquisition module 310 , a target topic determination module 320 and a target topic group updating module 330 .

[0114] The overall consistency acquisition module 310 is used to obtain the overall consistency parameters of the question set to be optimized.

[0115] The target topic determination module 320 is configured to determine a target topic in the group of topics to be optimized when it is determined that the overall consistency parameter is less than a preset consistency threshold.

[0116] The target question group updating module 330 is configured to obtain a target question group that matches the target question, and update the target question from the question group to be optimized to the target question group.

[0117] In an optional implementation of an embodiment of the present invention, the target question determination module 320 can be specifically used to: determine the questions in the question group to be optimized as pending questions in turn, and obtain the remaining consistency parameters of the remaining questions in the question group to be optimized except the pending questions; when it is determined that any of the remaining consistency parameters is greater than the overall consistency parameter, determine the target consistency parameter based on the remaining consistency parameter; obtain the pending question corresponding to the target consistency parameter as the target question.

[0118] In an optional implementation of an embodiment of the present invention, the target question group updating module 330 may include: a discrimination acquisition submodule, used to obtain the discrimination parameter of the target question; an associated knowledge point question group acquisition submodule, used to obtain the associated knowledge point question group of the question group to be optimized when it is determined that the discrimination parameter is less than or equal to a preset discrimination threshold, and determine the target question group in the associated knowledge point question group.

[0119] In an optional implementation of the embodiment of the present invention, the target question group updating module 330 may include: a discrimination acquisition submodule, used to obtain the discrimination parameter of the target question; an associated difficulty question group acquisition submodule, used to obtain the associated difficulty question group of the question group to be optimized when it is determined that the discrimination parameter is greater than a preset discrimination threshold, and determine the target question group in the associated difficulty question group.

[0120] In an optional implementation of an embodiment of the present invention, the associated difficulty question group acquisition submodule can be specifically used to: obtain the score rate parameter of the target question and the average score rate of the remaining questions in the question group to be optimized except the target question; when it is determined that the score rate parameter is less than the average score rate, obtain the associated high-difficulty question group of the question group to be optimized; when it is determined that the score rate parameter is greater than the average score rate, obtain the associated low-difficulty question group of the question group to be optimized.

[0121] In an optional implementation of an embodiment of the present invention, the associated knowledge point question group acquisition submodule can be specifically used to: respectively obtain the independent consistency parameters of each associated knowledge point question group, and the combined consistency parameters of all questions in each associated knowledge point question group and the target question; when it is determined that the combined consistency parameter corresponding to any of the associated knowledge point question groups is greater than or equal to the independent consistency parameter, determine the target combined consistency parameter based on the combined consistency parameter; obtain the associated knowledge point question group corresponding to the target combined consistency parameter as the target question group.

[0122] In an optional implementation of an embodiment of the present invention, the associated difficulty question group acquisition submodule can be specifically used to: respectively obtain the independent consistency parameters of each associated difficulty question group, and the combined consistency parameters of all questions in each associated difficulty question group and the target question; when it is determined that the combined consistency parameter corresponding to any of the associated difficulty question groups is greater than or equal to the independent consistency parameter, determine the target combined consistency parameter based on the combined consistency parameter; obtain the associated difficulty question group corresponding to the target combined consistency parameter as the target question group.

[0123] In an optional implementation of an embodiment of the present invention, the associated knowledge point question group acquisition submodule and the associated difficulty question group acquisition submodule can also be used to: stop acquiring the target question group that matches the target question when it is determined that the combined consistency parameters are all smaller than the independent consistency parameters; or, determine the target launch status of the target question.

[0124] The above-mentioned device can execute the topic grouping updating method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the topic grouping updating method.

[0125] An embodiment of the present invention provides a question grouping and updating device, which obtains the consistency parameter of the question group to be optimized, and determines the existence of mismatched questions in the question group to be optimized based on the fact that its consistency parameter is less than a preset threshold value, and determines the mismatched target question from it, and then determines a more matching group for the target question, thereby realizing the optimization and update of the question grouping, solving the technical problems in the prior art of waste of question resources or excessively high cost of regrouping questions due to inappropriate question grouping, realizing the automatic update of question grouping, ensuring the efficiency and accuracy of the question grouping update process, and thereby improving the effective utilization rate of questions.

[0126] Example 4

[0127] Figure 12 A schematic diagram of the structure of a computer device provided in Example 4 of the present invention. Figure 12 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 12 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0128] like Figure 12 As shown, the computer device 12 is implemented as a general-purpose computing device. Components of the computer device 12 may include, but are not limited to, one or more processors 16, a memory 28, and a bus 18 that connects various system components (including the memory 28 and the processor 16).

[0129] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0130] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0131] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 12 Not shown, usually called a "hard drive"). Although Figure 12 Although not shown, a magnetic disk drive for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), as well as an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0132] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally implement the functions and / or methodologies of the embodiments described herein.

[0133] The computer device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, a pointing device, a display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 12Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0134] The processor 16 executes various functional applications and data processing by running the program stored in the memory 28, thereby implementing the question grouping update method provided by the embodiment of the present invention: obtaining the overall consistency parameter of the question group to be optimized; when it is determined that the overall consistency parameter is less than a preset consistency threshold, determining the target question in the question group to be optimized; obtaining the target question group that matches the target question, and updating the target question from the question group to be optimized to the target question group.

[0135] Example 5

[0136] Embodiment 5 of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for updating question groups provided in the embodiment of the present invention is implemented: obtaining the overall consistency parameter of the question group to be optimized; when it is determined that the overall consistency parameter is less than a preset consistency threshold, determining a target question in the question group to be optimized; obtaining a target question group that matches the target question, and updating the target question from the question group to be optimized to the target question group.

[0137] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0138] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0139] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0140] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or computer device. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0141] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for updating topic groups, characterized in that: include: Obtain the overall consistency parameters of the problem set to be optimized; When it is determined that the overall consistency parameter is less than a preset consistency threshold, determining a target question in the set of questions to be optimized; Obtaining a target question group that matches the target question, and updating the target question from the question group to be optimized to the target question group; Obtaining a target question group that matches the target question includes: obtaining a discrimination parameter of the target question; if it is determined that the discrimination parameter is greater than a preset discrimination threshold, obtaining a difficulty question group associated with the question group to be optimized, and determining the target question group within the difficulty question group; if it is determined that the discrimination parameter is less than or equal to the preset discrimination threshold, obtaining a knowledge point question group associated with the question group to be optimized, and determining the target question group within the knowledge point question group; wherein the difficulty question group associated is a question group that tests the same knowledge point as the question group to be optimized but has a different difficulty level; Determining a target question group from the associated knowledge point question groups or associated difficulty question groups includes: respectively obtaining independent consistency parameters for each associated knowledge point question group or each associated difficulty question group, and combined consistency parameters for all questions in each associated knowledge point question group or each associated difficulty question group and the target question; if it is determined that the combined consistency parameter corresponding to any of the associated knowledge point question groups or the associated difficulty question groups is greater than or equal to the independent consistency parameter, determining a target combined consistency parameter based on the combined consistency parameter; and obtaining the associated knowledge point question group or the associated difficulty question group corresponding to the target combined consistency parameter as the target question group; Among them, the independent consistency parameter is data that is positively correlated with the feature similarity between each question in the associated knowledge point question group or the associated difficulty question group; the combined consistency parameter is data that is positively correlated with the feature similarity between each question, including the questions within the associated knowledge point question group or the associated difficulty question group and the target question; the target combined consistency parameter is the combined consistency parameter with the highest value among the combined consistency parameters that are greater than the independent consistency parameter.

2. The method according to claim 1, characterized in that Determining a target question in the set of questions to be optimized includes: sequentially determining the questions in the group of questions to be optimized as pending questions, and obtaining the remaining consistency parameters of the remaining questions in the group of questions to be optimized except the pending questions; In the case where it is determined that any of the remaining consistency parameters is greater than the overall consistency parameter, determining a target consistency parameter according to the remaining consistency parameter; The undetermined topic corresponding to the target consistency parameter is obtained as a target topic.

3. The method according to claim 1, characterized in that The step of obtaining a question group of related difficulty level of the question group to be optimized includes: Obtaining a scoring rate parameter of the target question and an average scoring rate of the remaining questions in the set of questions to be optimized except the target question; When it is determined that the score rate parameter is less than the score rate average, obtaining a high-difficulty question group associated with the question group to be optimized; When it is determined that the score rate parameter is greater than the score rate average value, a low-difficulty question group associated with the question group to be optimized is obtained.

4. The method according to claim 1, wherein After obtaining the independent consistency parameters of each related knowledge point question group or each related difficulty question group, and the combined consistency parameters of all questions in each related knowledge point question group or each related difficulty question group and the target question, the method further includes: When it is determined that the combined consistency parameters are all smaller than the independent consistency parameters, stop acquiring the target question group that matches the target question; or A target launch state of the target topic is determined.

5. A topic grouping updating device, characterized in that: include: The overall consistency acquisition module is used to obtain the overall consistency parameters of the problem set to be optimized; a target question determination module, configured to determine a target question in the set of questions to be optimized if it is determined that the overall consistency parameter is less than a preset consistency threshold; A target question group updating module is used to obtain a target question group that matches the target question, and update the target question from the question group to be optimized to the target question group; The target question group updating module includes: a discrimination acquisition submodule for acquiring a discrimination parameter of the target question; an associated difficulty question group acquisition submodule for acquiring, if it is determined that the discrimination parameter is greater than a preset discrimination threshold, a difficulty question group associated with the question group to be optimized, and determining the target question group from the difficulty question group associated with the difficulty question group; and an associated knowledge point question group acquisition submodule for acquiring, if it is determined that the discrimination parameter is less than or equal to the preset discrimination threshold, a knowledge point question group associated with the question group to be optimized, and determining the target question group from the knowledge point question group associated with the knowledge point question group; wherein the associated difficulty question group is a question group that tests the same knowledge point as the question group to be optimized but has a different difficulty level; The associated difficulty question group acquisition submodule is configured to respectively acquire the independent consistency parameters of each associated difficulty question group, and the combined consistency parameters of all questions in each associated difficulty question group and the target question; if it is determined that the combined consistency parameter corresponding to any associated difficulty question group is greater than or equal to the independent consistency parameter, determine the target combined consistency parameter based on the combined consistency parameter; and acquire the associated difficulty question group corresponding to the target combined consistency parameter as the target question group; The associated knowledge point question group acquisition submodule is used to respectively obtain the independent consistency parameters of each associated knowledge point question group, and the combined consistency parameters of all questions in each associated knowledge point question group and the target question; if it is determined that the combined consistency parameter corresponding to any associated knowledge point question group is greater than or equal to the independent consistency parameter, determine the target combined consistency parameter based on the combined consistency parameter; and obtain the associated knowledge point question group corresponding to the target combined consistency parameter as the target question group; Among them, the independent consistency parameter is data that is positively correlated with the feature similarity between each question in the associated knowledge point question group or the associated difficulty question group; the combined consistency parameter is data that is positively correlated with the feature similarity between each question, including the questions within the associated knowledge point question group or the associated difficulty question group and the target question; the target combined consistency parameter is the combined consistency parameter with the highest value among the combined consistency parameters that are greater than the independent consistency parameter.

6. A computer device, characterized in that: The computer device comprises: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the topic grouping updating method according to any one of claims 1 to 4.

7. A computer storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for updating topic groups as described in any one of claims 1 to 4 is implemented.

Images