Data adjustment method, device, equipment and medium based on Bayesian knowledge tracking

Abstract

The embodiment of the present invention discloses a data adjustment method, device, equipment and medium based on Bayesian knowledge tracking. The method includes: obtaining answer record data of users of each level for knowledge points of each level; obtaining the current achievement rate corresponding to each answer record data based on the achievement standard data of users of each level for knowledge points of each level; when it is determined that each current achievement rate does not meet the reasonable achievement rate conditions for matching the target achievement rate, dynamically adjust each achievement standard data based on the target achievement rate and each answer record data so that each current achievement rate is within the preset expected range of matching the target achievement rate. The embodiment of the present invention can ensure that the learner's achievement rate remains within a reasonable range, realize personalized adjustment of the achievement difficulty, and enhance user stickiness.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular to a data adjustment method, apparatus, device, and medium based on Bayesian knowledge tracing. Background Art

[0002] With the development of artificial intelligence technology, the emergence of adaptive learning platforms has provided users with an autonomous and personalized learning model. Based on the learner's learning performance, the adaptive learning platform system can comprehensively assess and provide feedback on each learner's mastery of knowledge points, providing a basis for learners to independently select learning strategies and conduct self-assessment. In existing technologies, adaptive learning platform systems typically incorporate specific algorithms to provide feedback on the learner's mastery of knowledge points based on their performance in answering questions on each knowledge point.

[0003] However, in the prior art, the achievement standard on which the system makes its judgment is a constant value, that is, the difficulty level of each learner in answering questions on each knowledge point remains consistent. As a result, it is impossible to dynamically plan the achievement standard for learners of different levels and knowledge points of different difficulty levels. As a result, it is too easy for high-level learners to achieve the standard, which cannot accurately and comprehensively reflect the gaps in knowledge learning and easily causes learners to lose the challenge of learning. On the other hand, it is too difficult for low-level learners to achieve the standard, which requires learners to repeatedly study the knowledge points that they find difficult to achieve, thereby undermining their learning enthusiasm. Summary of the Invention

[0004] The embodiments of the present invention provide a data adjustment method, apparatus, device and medium based on Bayesian knowledge tracking to ensure that the learner's achievement rate remains within a reasonable range, achieve personalized adjustment of the difficulty of achieving the goal, and enhance user stickiness.

[0005] In a first aspect, an embodiment of the present invention provides a method for dynamically adjusting data, comprising:

[0006] Obtain the answer record data of users of different levels for each level of knowledge points;

[0007] According to the attainment standard data of the users of each level for the knowledge points of each level, obtaining the current attainment rate corresponding to each answer record data;

[0008] In the event that it is determined that each current achievement rate does not meet the reasonable achievement rate conditions for matching the target achievement rate, dynamically adjusting each achievement standard data based on the target achievement rate and each answer record data so that each current achievement rate is within a preset expected range for matching the target achievement rate;

[0009] Among them, the reasonable conditions for the achievement rate include that the variance of each of the current achievement rates does not exceed the first threshold, and the absolute value of the difference between each of the current achievement rates and the target achievement rate does not exceed the second threshold.

[0010] In a second aspect, an embodiment of the present invention further provides a data dynamic adjustment device, comprising:

[0011] The answer record acquisition module is used to obtain the answer record data of users of different levels for each level of knowledge points;

[0012] A standard-reaching rate acquisition module is configured to acquire the current standard-reaching rate corresponding to each answer record data based on the standard-reaching standard data of each level of users for each level of knowledge point;

[0013] a standard achievement adjustment module for dynamically adjusting each of the standard achievement data based on the target achievement rate and each of the answer record data, if it is determined that each of the current achievement rates does not meet the reasonable conditions for achieving the target achievement rate, so that each of the current achievement rates is within a preset expected range of matching the target achievement rate;

[0014] Among them, the reasonable conditions for the achievement rate include that the variance of each of the current achievement rates does not exceed the first threshold, and the absolute value of the difference between each of the current achievement rates and the target achievement rate does not exceed the second threshold.

[0015] In a third aspect, an embodiment of the present invention further provides a computer device, comprising:

[0016] one or more processors;

[0017] a storage device for storing one or more programs;

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the data dynamic adjustment method provided by any embodiment of the present invention.

[0019] In a fourth aspect, an embodiment of the present invention further provides a computer storage medium on which a computer program is stored. When the program is executed by a processor, the method for dynamic data adjustment provided by any embodiment of the present invention is implemented.

[0020] The embodiment of the present invention obtains the answer record data of users of different levels for knowledge points of different difficulty levels, and obtains the attainment rate of each part of the answer record data based on the current attainment standard. When it is determined that each attainment rate cannot meet the reasonable conditions of the attainment rate that matches the target attainment rate, the current attainment standard is dynamically adjusted to make the attainment rate of each part of the answer record data obtained based on the adjusted attainment standard close to the expected target attainment rate, thereby ensuring that the learner's attainment rate remains within a reasonable range, realizing personalized adjustment of the attainment difficulty, and enhancing user stickiness. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flowchart of a method for dynamic data adjustment provided in Example 1 of the present invention.

[0022] Figure 2 This is a flow chart of a method for dynamic data adjustment provided in Example 2 of the present invention.

[0023] Figure 3 This is a structural diagram of a data dynamic adjustment device provided in Example 3 of the present invention.

[0024] Figure 4 A schematic diagram of the structure of a computer device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] It should also be noted that, for ease of description, only the part relevant to the present invention, rather than all of the content, is shown in the accompanying drawings. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processing or methods depicted as flow charts. Although flow charts describe various operations (or steps) as sequential processing, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. When its operation is completed, the processing can be terminated, but can also have additional steps not included in the accompanying drawings. The processing can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0027] Example 1

[0028] Figure 1This is a flow chart of a data dynamic adjustment method provided by the first embodiment of the present invention. This embodiment is applicable to dynamically adjusting the answering standards for users of different levels and knowledge points of different difficulty levels so that the achievement rate is close to a certain value. This method can be executed by the data dynamic adjustment device provided by 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. Accordingly, if Figure 1 As shown, the method includes the following operations:

[0029] S110 , obtaining answer record data of users of different levels for knowledge points of different levels.

[0030] Specifically, users of each level may include at least one user group divided from all users participating in the quiz, with the learning levels of users within each user group being relatively consistent, and the learning levels of users between different user groups being relatively different. Knowledge points of each level may include at least one knowledge point group divided from all knowledge points, with the difficulty of knowledge points within each knowledge point group being relatively consistent, and the difficulty of knowledge points between different knowledge point groups being relatively different. The answer record data may be data generated by users of each level answering questions corresponding to knowledge points of each level.

[0031] Accordingly, users of different levels can be predetermined, and the specific method is not limited here. For example, the level of each user can be determined based on information such as their previous learning performance or learning background, or based on the administrator's marking of each user's level, so that users with relatively consistent levels can be divided into user groups of the same level, thereby obtaining users of different levels. Knowledge points of different levels can also be predetermined, and the specific method is not limited here. For example, the difficulty of each knowledge point can be determined based on the overall quality of users' previous answers to each knowledge point, or based on the administrator's marking of the difficulty of each knowledge point, so that knowledge points with relatively consistent difficulty can be divided into knowledge point groups of the same level, thereby obtaining knowledge points of different levels.

[0032] Furthermore, when answering questions, any user may answer questions corresponding to any knowledge point. The answer record data generated by the user's answers can then be associated with the user. Furthermore, this portion of the answer record data can also be associated with at least one corresponding knowledge point. Once users of different skill levels and knowledge points of different levels are determined, each portion of the answer record data can be assigned to users of different skill levels and knowledge points of different levels, based on the user's skill level and the difficulty level of each knowledge point.

[0033] Exemplarily, Table 1 provides a schematic table of the correspondence between answer record data and users of various levels and knowledge points of various levels. As shown in Table 1, during the answering process, user A, user B and user C all answered questions corresponding to knowledge point a, knowledge point b and knowledge point c, and generated answer record data respectively. If it is predetermined that user A and user B are high-level users, and user C is a low-level user, and at the same time, knowledge point a and knowledge point b are high-level knowledge points, and knowledge point c is a low-level knowledge point, then the answer record data can be divided into a part of the answer record data generated by high-level users answering questions on high-level knowledge points, including the answer record data Aa of user A answering knowledge point a, the answer record data Ab of user A answering knowledge point b, the answer record data Ba of user B answering knowledge point a, and the answer record data Bb of user B answering knowledge point b; it can also be divided into the answer record data of high-level users answering questions on low-level knowledge points. A part of the answer record data generated by answering questions on knowledge points, including the answer record data Ac of user A's answer to knowledge point c and the answer record data Bc of user B's answer to knowledge point c; a part of the answer record data generated by low-level users' answering questions on high-level knowledge points can also be divided, including the answer record data Ca of user C's answer to knowledge point a and the answer record data Cb of user C's answer to knowledge point b; and a part of the answer record data generated by low-level users' answering questions on low-level knowledge points can also be divided, including the answer record data Cc of user C's answer to knowledge point c.

[0034] Table 1

[0035]

[0036] S120. Obtain the current attainment rate corresponding to each of the answer record data based on the attainment standard data of each level of users for the knowledge points of each level.

[0037] The standard data may be data used to obtain the standard rate of the answer record data. The current standard rate may be data obtained based on the standard data at the current moment and used to describe the quality of the user's answer to the knowledge point represented by the answer record data.

[0038] Accordingly, any feasible method can be used to obtain the current standard-reaching rate of the answer record, such as a specific algorithm, and the standard-reaching data can be set corresponding to the method for obtaining the current standard-reaching rate, which is not limited here. The standard-reaching data for different levels of users for different levels of knowledge points can be the same or different. To obtain the current standard-reaching rate of any part of the answer record data, the standard-reaching data corresponding to the corresponding level of users and the corresponding level of knowledge points of the part of the answer record data can be obtained, and the current standard-reaching rate of the part of the answer record data can be obtained based on the standard-reaching data.

[0039] Optionally, the compliance standard data can be data used to determine whether the user's answers to knowledge points meet the standards, and the current compliance rate of the answer record data can be the proportion of compliance results to all results after judging the answer situation based on the compliance standard data at the current moment.

[0040] Further optionally, a Stop Policy model may be used to determine whether the user has met the requirements for the knowledge points, and the compliance standard data may be the EPS value (specific probability difference threshold) in the model.

[0041] Specifically, the Stop Policy model determines whether a user's mastery of a knowledge point is stable and has been mastered. This model calculates the specific probability difference for each answer record. If the resulting specific probability difference is less than the EPS value, it can be determined that the user has stably mastered the knowledge point. Therefore, based on the preset EPS value, it is possible to determine whether the user corresponding to any answer record has stably mastered the corresponding knowledge point, that is, whether they have met the standard. This allows the proportion of the standard-compliant results corresponding to that answer record to the total number of results to be determined, serving as the current standard-compliant rate.

[0042] For example, in the specific example shown in Table 1, if it is necessary to obtain the current compliance rate corresponding to the answer record data of high-level users for high-level knowledge points, the corresponding compliance standard data set at the current moment can be obtained, and based on the answer record data Aa, Ab, Ba and Bb, the corresponding algorithm is used for judgment. If the judgment result is that user A's answers to knowledge point a and knowledge point b are both up to standard, and user B's answers to knowledge point a are up to standard, but the answers to knowledge point b are not up to standard, then the compliance result appears 3 times, the total result is 4 times, and the compliance rate is 75%.

[0043] For example, Table 2 provides a table showing the corresponding relationship between the current achievement rate and different levels of users and knowledge points. As shown in Table 2, users are divided into high-level users, medium-level users, and low-level users, and knowledge points are divided into high-difficulty knowledge points, medium-difficulty knowledge points, and low-difficulty knowledge points. The corresponding current achievement rates include a%, b%, c%, d%, e%, f%, g%, h%, and i%.

[0044] Table 2

[0045] High difficulty Medium difficulty Low difficulty Low level a％ d％ g％ Intermediate level b％ e％ h％ high level c％ f％ i％

[0046] S130. When it is determined that each of the current achievement rates does not meet the reasonable conditions for achieving the target achievement rate, each of the achievement standard data is dynamically adjusted according to the target achievement rate and each of the answer record data, so that each of the current achievement rates is within the preset expected range of the target achievement rate.

[0047] Among them, the reasonable conditions for the achievement rate include that the variance of each of the current achievement rates does not exceed the first threshold, and the absolute value of the difference between each of the current achievement rates and the target achievement rate does not exceed the second threshold. Specifically, the target achievement rate can be an arbitrarily determined value, which can be pre-set as needed, or obtained according to preset rules, and is not limited here. The first threshold can be pre-set according to the need for the discrete degree of the current achievement rate, indicating the maximum allowable discrete degree of the current achievement rate. The second threshold can be pre-set according to the need for the difference between the current achievement rate and the target achievement rate, indicating the maximum allowable difference between the current achievement rate and the target achievement rate. The preset expectation range can be a pre-set numerical range that is arbitrarily close to the target achievement rate.

[0048] Accordingly, if the current achievement rate does not meet the reasonable achievement rate conditions that match the target achievement rate, it can be explained that the variance of the current achievement rate exceeds the first threshold, or the difference between at least one current achievement rate and the target achievement rate exceeds the second threshold. If the variance of the current achievement rate exceeds the first threshold, it can be explained that the degree of dispersion of each current achievement rate is too large, that is, the difference in the difficulty of achieving the standards for knowledge points of different levels for users of different levels is too large, then the achievement standard data of each level of users for each level of knowledge points can be adjusted to adjust the difficulty of achieving the standards, so that the difficulty of achieving the standards for knowledge points of each level for users of each level, that is, the achievement rate, can be made relatively consistent. If the difference between any current achievement rate and the target achievement rate exceeds the second threshold, it can be explained that the current achievement rate is too large or too small compared to the target achievement rate, that is, the difficulty of achieving the standards for the corresponding level of users for the corresponding level of knowledge points is too small or too large, then the achievement standard data of the knowledge point of the corresponding level for the user of the corresponding level can be adjusted to adjust the corresponding difficulty of achieving the standards to the expected difficulty, that is, the achievement rate can be closer to the target achievement rate.

[0049] An embodiment of the present invention provides a method for dynamically adjusting data, which obtains answer record data of users of different levels for knowledge points of different difficulty levels, and obtains the attainment rate of each part of the answer record data based on the current attainment standard. When it is determined that each attainment rate cannot meet the reasonable conditions of the attainment rate that matches the target attainment rate, the current attainment standard is dynamically adjusted to make the attainment rate of each part of the answer record data obtained based on the adjusted attainment standard close to the expected target attainment rate, thereby ensuring that the learner's attainment rate remains within a reasonable range, realizing personalized adjustment of the attainment difficulty, and enhancing user stickiness.

[0050] Example 2

[0051] Figure 2 A flowchart of a method for dynamically adjusting data provided in Example 2 of the present invention. This embodiment of the present invention is specific based on the above embodiment. In this embodiment of the present invention, a specific optional implementation method for dynamically adjusting each of the target standard data based on the target standard achievement rate and each of the answer record data is provided.

[0052] like Figure 2 As shown, the method of the embodiment of the present invention specifically includes:

[0053] S210: Obtain answer record data of users of different levels for knowledge points of different levels.

[0054] In an optional embodiment of the present invention, before obtaining the answer record data of users of each level for knowledge points of each level, it can also include: obtaining the ratio of the number of correct answers to the total number of answers of each target user in the current level update cycle as user achievement record data; and determining each target user as a user of each level based on the user achievement record data.

[0055] The target user can be any user who answers questions within the current level update cycle. The current level update cycle can be the current level update cycle. The level update cycle can be a preset period of time, and the user's level can be updated every level update cycle based on the user's answering performance within that level update cycle. The number of correct answers can be the number of times the user correctly answers a question within the current level update cycle. The total number of answers can be the total number of times the user answers questions within the current level update cycle. User achievement record data can be data used to describe the user's achievement of the standard.

[0056] Accordingly, the learning level of each target user can change during the learning process. Therefore, a level update cycle can be pre-set to regularly update the level of each target user. The target user's level can be determined based on the ratio of the number of correct answers to the total number of answers during the current level update cycle. Specifically, a higher ratio indicates a higher learning level for the target user; a lower ratio indicates a lower learning level for the target user. After obtaining the target user's achievement record data, all target users can be divided into any number of users of different levels.

[0057] For example, if the level update cycle can be set to 7 days, the ratio of the number of correct answers to the total number of answers for each target user in the last 7 days can be obtained. If all target users need to be divided into three levels of users: high, medium, and low according to preset rules, the first 1 / 3 of the target users after sorting the ratios from high to low can be determined as high-level users, the second 1 / 3 as low-level users, and the remaining middle 1 / 3 as medium-level users. Table 3 exemplifies the level update status for student users A and B. Seven days after this update, the target users can be reclassified.

[0058] Table 3

[0059] student Student level (before update) Student Level (updated) Student A high middle Student B Low Low

[0060] In an optional embodiment of the present invention, before obtaining the answer record data of users of each level for knowledge points of each level, the method may also include: obtaining the user answer record data of all target users for each target knowledge point in the current level update cycle; based on a preset empirical model, obtaining the difficulty parameter data of each target knowledge point according to the user answer record data; and determining each target knowledge point as the knowledge point of each level according to the difficulty parameter data.

[0061] Among them, the target knowledge point can be any knowledge point targeted by the questions answered by the target user within the current level update cycle. The user answer record data can be the data generated by all target users answering questions for each target knowledge point. The current level update cycle can be the level update cycle at the current moment, and the level update cycle can be a preset period of time. The difficulty level of the knowledge point can be updated every level update cycle based on the user's answer performance within the level update cycle. The preset experience model can be a calculation model for obtaining corresponding difficulty parameter data based on the user answer record data corresponding to each target knowledge point. The difficulty parameter data can be data used to describe the difficulty of a knowledge point.

[0062] Accordingly, since the learning level of each target user can change during the learning process, the difficulty of the same knowledge point for the target user will also change accordingly. For example, if within the current level update cycle, the target users have practiced a large number of questions on a certain target knowledge point, thereby improving the overall mastery of the target knowledge point, the difficulty level of the target knowledge point can be updated to a lower difficulty level. Based on a preset empirical model, the difficulty parameter data of each target knowledge point can be determined according to the user answer record data corresponding to each target knowledge point. The current difficulty level of each target knowledge point can be determined based on the difficulty parameter data, and then all target knowledge points can be divided into any number of knowledge points of each level.

[0063] Exemplarily, if the level update cycle can be set to 7 days, the user answer record data of each target user in the last 7 days can be obtained respectively, and the difficulty parameter data of each target knowledge point can be obtained according to the preset experience model, and the higher the value of the difficulty parameter data, the higher the difficulty of the knowledge point; the lower the value of the difficulty parameter data, the lower the difficulty of the knowledge point. If all target knowledge points need to be divided into knowledge point groups of three difficulty levels: high, medium, and low according to the preset rules, the first 1 / 3 target knowledge points after the difficulty parameter data is arranged from high to low can be determined as high difficulty level knowledge points, the second 1 / 3 knowledge points can be determined as low difficulty level knowledge points, and the remaining middle 1 / 3 knowledge points can be determined as medium difficulty level knowledge points. Table 4 exemplarily provides the difficulty level update situation for knowledge point a and knowledge point b. 7 days after this update, the target knowledge points can be re-divided.

[0064] Table 4

[0065] Knowledge Points Difficulty (before update) Difficulty (after update) Knowledge point a middle high Knowledge point b high high

[0066] Optionally, the preset empirical model may be an EP (Empirical Probabilities) model, and the difficulty parameter data may be an L0 parameter in a BKT (Bayesian Knowledge Tracing) parameter that is used to describe the probability that the learner has mastered the knowledge point before starting to do the questions.

[0067] Specifically, the EP model uses empirical methods to generate Back-Known Test (BKT) parameters. This approach involves two steps: the first step is to label student performance data as determined by the EP model using a simple heuristic method; the second step is to empirically derive BKT parameters from this labeled data. The EP model assumes that students will not forget knowledge points after learning them; that is, a correct state will not be followed by an incorrect state. BKT parameters can include the L0 parameter, the G parameter, the S parameter, and the T parameter. The L0 parameter represents the probability that a learner has mastered the knowledge point before starting to work on the problem. It can be used as a parameter for the difficulty of the knowledge point. A higher value (P(L)) indicates a lower difficulty level, while a lower value (P(L)) indicates a higher difficulty level.

[0068] For example, the BKT parameters for each target knowledge point can be updated every 24 hours. Table 5 provides an example of the BKT parameter update for knowledge point a shown in Table 4. As shown in Table 5, the L0 parameter value P(L) of knowledge point a is updated from 0.35 to 0.28, which indicates that the difficulty of knowledge point a has increased, and it has been updated from a medium-difficulty knowledge point to a high-difficulty knowledge point.

[0069] Table 5

[0070] P(S) P(G) P(L) P(T) Before update 0.24 0.46 0.35 0.42 After update 0.17 0.42 0.28 0.38

[0071] S220. According to the attainment standard data of the users at each level for the knowledge points at each level, obtain the current attainment rate corresponding to each of the answer record data.

[0072] S230: Determine whether each current compliance rate satisfies a reasonable compliance rate condition that matches the target compliance rate. If so, execute S240; otherwise, execute S250.

[0073] In an optional embodiment of the present invention, before determining whether each of the current achievement rates meets the reasonable conditions for the achievement rate that matches the target achievement rate, it may also include: obtaining the target achievement rate set by the user; or, obtaining the average achievement rate of each of the current achievement rates, and determining the average achievement rate as the target achievement rate.

[0074] Accordingly, under a permitted situation, the target achievement rate can be pre-set by any authorized user as needed. For example, if the administrator wishes that the achievement rate of each level of users for each level of knowledge points can be maintained at 80% or fluctuate within a range close to 80%, the target achievement rate can be set to 80%. The user-set target achievement rate can be pre-received and stored in a designated location of the current adaptive learning system.

[0075] In another permitted situation, when the user has no specific requirements for the target achievement rate, the average value of the current achievement rates can be obtained as the target achievement rate, that is, it is hoped that each current achievement rate can be close to the average value of the current achievement rates.

[0076] S240: No dynamic adjustment is made to any compliance standard data.

[0077] Correspondingly, if the current achievement rate meets the reasonable achievement rate conditions that match the target achievement rate, it can be said that each current achievement rate is close enough to the target achievement rate, and the difference between the current achievement rates is not large, that is, the difficulty of achieving different levels of knowledge points for users of different levels is reasonable and relatively consistent. Therefore, there is no need to dynamically adjust any achievement standard data.

[0078] S250: Dynamically adjust each of the achievement standard data based on the target achievement rate and each of the answer record data so that each of the current achievement rates is within a preset expected range of matching the target achievement rate. The reasonable achievement rate conditions include that the variance of each of the current achievement rates does not exceed a first threshold, and the absolute value of the difference between each of the current achievement rates and the target achievement rate does not exceed a second threshold.

[0079] In an optional embodiment of the present invention, S250 may specifically include:

[0080] S251. Obtain each of the current compliance rates in sequence as the current compliance rates to be determined. When it is determined that the current compliance rates to be determined meet the dynamic adjustment conditions, determine the current compliance rates to be determined as the compliance rates to be adjusted.

[0081] The current compliance rate to be determined may be any current compliance rate for which adjustment is to be determined. The dynamic adjustment condition may be the basis for determining whether the current compliance rate needs to be adjusted, or may be a condition describing whether the current compliance rate is not sufficiently close to the target compliance rate. The condition may be pre-set based on the desired degree of closeness between the current compliance rate and the target compliance rate. The compliance rate to be adjusted may be a current compliance rate determined based on the dynamic adjustment condition that is not sufficiently close to the target compliance rate, i.e., a current compliance rate that needs adjustment.

[0082] Accordingly, if the current achievement rate does not meet the reasonable achievement rate conditions for matching the target achievement rate, it can be said that at least one current achievement rate is not close enough to the target achievement rate, or the difference between it and other current achievement rates is large, that is, the difficulty of achieving the standards for different levels of knowledge points for users of different levels is too large or too small, or the difference in difficulty is large. Therefore, the current achievement rates can be obtained in sequence as the current achievement rates to be judged, and whether they are close enough to the target achievement rate can be judged according to the dynamic adjustment conditions. If any current achievement rate to be judged meets the dynamic adjustment conditions, it means that it is not close enough to the target achievement rate, and it can be determined as the achievement rate to be adjusted, that is, it needs to be adjusted to make it close to the target achievement rate.

[0083] In an optional embodiment of the present invention, determining whether the current compliance rate to be determined satisfies the dynamic adjustment condition may include: determining that the current compliance rate to be determined satisfies the dynamic adjustment condition when it is determined that the current compliance rate to be determined is different from the target compliance rate; or calculating the compliance rate deviation value between the current compliance rate to be determined and the target compliance rate; and determining that the current compliance rate to be determined satisfies the dynamic adjustment condition when it is determined that the compliance rate deviation value exceeds a third threshold.

[0084] Accordingly, under a permitted circumstance, if it is determined that the current compliance rate to be determined is different from the target compliance rate, it can be determined that it meets the dynamic adjustment condition, that is, all current compliance rates that are not equal to the target compliance rate can be adjusted to be closer to the target compliance rate. This embodiment ensures that all current compliance rates that do not meet the target compliance rate can be adjusted, ensuring the comprehensiveness of the adjustment range.

[0085] In another permitted case, specifically, the standard-attainment rate deviation value can be the difference between the current standard-attainment rate to be determined and the target standard-attainment rate. The third threshold value can be pre-set according to the need for the closeness between the current standard-attainment rate and the target standard-attainment rate, indicating the maximum difference between the current standard-attainment rate and the target standard-attainment rate that can be allowed. Accordingly, the absolute value of the difference between the current standard-attainment rate to be determined and the target standard-attainment rate, or the absolute value of the difference between the target standard-attainment rate and the current standard-attainment rate to be determined, can be calculated as the standard-attainment rate deviation value. If it is determined that the standard-attainment rate deviation value corresponding to the current standard-attainment rate to be determined exceeds the third threshold value, it is determined that the difference between it and the target standard-attainment rate is too large, and it can be determined that it meets the dynamic adjustment condition, that is, the current standard-attainment rate that is too different from the target standard-attainment rate can be adjusted to make it closer to the target standard-attainment rate; and for the current standard-attainment rate whose standard-attainment rate deviation value does not exceed the third threshold value, it can be determined to be close to the target standard-attainment rate without adjustment. This embodiment can determine the adjustment range of the compliance rate as needed, thereby reasonably reducing the amount of calculation while ensuring the accuracy of the compliance rate and improving the efficiency of dynamic adjustment.

[0086] S252. Obtain target answer record data corresponding to the target achievement rate to be adjusted from the answer record data.

[0087] The target answer record data may be the answer record data of the portion of all answer record data that corresponds to the standard attainment rate to be adjusted.

[0088] Accordingly, each current achievement rate describes the achievement rate of users of different skill levels for knowledge points of different levels. Therefore, any current achievement rate can be associated with the answer record data generated by users of the corresponding skill level answering questions on the corresponding knowledge point. Therefore, after determining at least one achievement rate to be adjusted from each current achievement rate, the target answer record data corresponding to each achievement rate to be adjusted can be obtained from the answer record data.

[0089] For example, in the specific example shown in Table 2, if a% is determined to be the achievement rate to be adjusted, the answer record data generated by low-level users answering questions on high-difficulty knowledge points are obtained as the target answer record data.

[0090] S253. Dynamically adjust the attainment standard data corresponding to the target answer record according to a preset adjustment accuracy.

[0091] The preset adjustment accuracy may be pre-set based on the need for the closeness between the adjusted current compliance rate and the target compliance rate, and may represent the minimum change in the compliance standard data when the compliance standard data is dynamically adjusted.

[0092] Accordingly, the current achievement rate of each target answer record data component is derived from the corresponding achievement standard data. Therefore, if the current achievement rate of any target answer record data component needs to be adjusted, the achievement standard data corresponding to that target answer record data component needs to be dynamically adjusted. Based on the preset adjustment accuracy, the achievement standard data corresponding to each target answer record data component can be adjusted once or multiple times. The achievement rate of each target answer record data component, derived from the adjusted achievement standard data component, will also be adjusted accordingly.

[0093] In an optional embodiment of the present invention, the dynamic adjustment of the attainment standard data corresponding to the target answer record according to a preset adjustment accuracy may include: selecting test attainment data in sequence within the target value range of the attainment standard data according to the preset adjustment accuracy, and obtaining the test attainment rate corresponding to the target answer record according to each test attainment data; obtaining the test difference between each test attainment rate and the target attainment rate; determining the target test difference from each test difference; and updating the attainment standard data according to the test attainment data corresponding to the target test difference.

[0094] Among them, the target value range can be a range that includes all possible numerical values ​​of the standard data. The test standard data can be a numerical value obtained within the target value range of the standard data, and the test standard data is taken once every preset adjustment accuracy. The test standard rate can be the standard rate of each target answer record data obtained by taking each test standard data as the standard data, and each part of the target answer record data corresponds to the same number of test standard data. The test difference can be the difference between the test standard rate and the target standard rate. The target test difference can be a test difference that is sufficiently small and determined according to a preset rule, and the target test difference is obtained from the test differences corresponding to the test standard rates corresponding to each part of the target answer record data.

[0095] Accordingly, the target value range can correspond to the specific content of the standard data, for example, it can be a closed interval [0, 1]. According to the preset adjustment precision, the test standard data are selected in sequence within the target value range. Then, values ​​can be taken in a certain order from any position in the target value range, and a value is taken every time the preset adjustment precision is set. For example, if the preset adjustment precision is 0.1, a value can be taken starting from 0.1 in the closed interval [0, 1], and then 0.1, 0.2, ..., 1 can be taken in sequence to obtain ten test standard data.

[0096] Furthermore, based on each test achievement data, the test achievement rate of each target answer record data is obtained, and the test difference between each test achievement rate and the target achievement rate is calculated. For the test difference corresponding to any target answer record data, the target test difference and its corresponding test achievement rate can be determined, which means that the test achievement rate is sufficiently close to the target achievement rate. The achievement standard data can then be updated based on the test achievement data corresponding to the target test difference, and the test achievement data can be determined as the achievement standard data corresponding to the target answer record data.

[0097] Optionally, determining the target test difference may include obtaining the test difference with the smallest absolute value among the test differences as the target test difference; or may include obtaining the test difference with an absolute value less than a certain preset threshold among the test differences as the target test difference. If there is no test difference with an absolute value less than a certain preset threshold, the preset adjustment accuracy may be reduced and the above process may be repeated, or the compliance standard data may not be updated.

[0098] The above implementation method realizes fine adjustment of the standard data based on a certain accuracy, and traverses the selectable values ​​of the standard data to obtain all available compliance rates, from which the standard data corresponding to the target compliance rate is determined, and the adjusted target value is determined from more comprehensive data to ensure the accuracy of the adjustment effect.

[0099] For example, Table 6 is a table showing the correspondence between the current achievement rate and students of different levels and knowledge points of different difficulty levels provided by an embodiment of the present invention. In a specific example, if the target achievement rate is determined to be 80%, and it can be determined that the current achievement rates in Table 6 do not meet the reasonable conditions for the matching achievement rate, then based on the rule of determining the current achievement rate that is different from the target deviation rate of 80% as the achievement rate to be adjusted, it can be determined that except for the achievement rate of low-level students for low-difficulty knowledge points and the achievement rate of medium-level students for medium-difficulty knowledge points, the other achievement rates in each current achievement rate are different from 80%, and their corresponding achievement standard data need to be adjusted.

[0100] Table 6

[0101] High difficulty Medium difficulty Low difficulty low-level students 60％ 70％ 80％ Intermediate students 70％ 80％ 90％ High-level students 75％ 90％ 95％

[0102] As a further example, if each current achievement rate is derived based on the Stop Policy model, the EPS value needs to be adjusted to adjust the achievement rate. Specifically, a higher EPS value indicates a looser achievement requirement, which can increase the achievement rate accordingly; a lower EPS value indicates a stricter achievement requirement, which can decrease the achievement rate accordingly. Taking the adjustment of achievement standard data for high-level students on difficult knowledge points as an example, several correct / incorrect answers can be simulated based on the characteristic of an 80% correct answer rate for high-level students on difficult knowledge points. Exemplary results include [0,0,0,1,0,0,1,1,1,0], [0,0,1,1,1,1,0,1,0,0], [0,1,1,1,1,0,0,1,0,1], [0,1,1,1,0,1,1,0,1,1], and [0,1,1,1,0,0,0,0,1,1]. After 100 simulations, the 100 simulation results can be scaled from 0.01 to 0.99 using an RPS value with an accuracy of 0.01, and the achievement rates calculated for each result. For example, if an EPS value of 0.01 is used to determine achievement, 20 of the results will achieve the target, resulting in a 20% achievement rate. If an EPS value of 0.02 is used to determine achievement, 23 of the results will achieve the target, resulting in a 23% achievement rate. If an EPS value of 0.03 is used to determine achievement, 25 of the results will achieve the target, resulting in a 25% achievement rate. Similarly, the corresponding relationship between EPS values ​​and achievement rates is shown in Table 7, which provides specific EPS values ​​and achievement rates as examples. Based on a target achievement rate of 80%, Table 7 shows the EPS value closest to 80%, which corresponds to an EPS value of 0.21 for an 81% achievement rate. Therefore, the achievement standard data for high-level students for high-difficulty knowledge points is adjusted to 0.21.

[0103] Table 7

[0104] EPS value Compliance rate 0.01 20％ 0.02 23％ 0.03 25％ … … 0.20 78％ 0.21 81％ 0.22 85％ … … 0.99 100％

[0105] An embodiment of the present invention provides a method for dynamic data adjustment, which obtains answer record data of different levels of difficulty for users of different levels, and obtains the attainment rate of each part of the answer record data based on the current attainment standard. When it is determined that each attainment rate cannot meet the reasonable conditions of the attainment rate that matches the target attainment rate, the current attainment standard is dynamically adjusted to make the attainment rate of each part of the answer record data obtained based on the adjusted attainment standard close to the expected target attainment rate, ensuring that the learner's attainment rate remains within a reasonable range, realizing personalized adjustment of the attainment difficulty, and enhancing user stickiness; further, by judging the attainment rate and attainment standard data corresponding to each part of the answer record data in turn, the attainment rate and attainment standard data that need to be adjusted are obtained, thereby realizing flexibility and comprehensiveness in adjusting the attainment standard data.

[0106] Example 3

[0107] Figure 3 This is a structural diagram of a data dynamic adjustment device provided by the third embodiment of the present invention, such as Figure 3 As shown, the device includes: an answer record acquisition module 310, a standard achievement rate acquisition module 320 and a standard achievement standard adjustment module 330.

[0108] The answer record acquisition module 310 is used to obtain answer record data of users of different levels for knowledge points of different levels.

[0109] The standard attainment rate acquisition module 320 is used to obtain the current standard attainment rate corresponding to each of the answer record data based on the standard attainment standard data of the users of each level for the knowledge points of each level.

[0110] The achievement standard adjustment module 330 is used to dynamically adjust each of the achievement standard data according to the target achievement rate and each of the answer record data when it is determined that each of the current achievement rates does not meet the reasonable achievement rate conditions for matching the target achievement rate, so that each of the current achievement rates is within the preset expected range of matching the target achievement rate; wherein, the reasonable achievement rate conditions include that the variance of each of the current achievement rates does not exceed the first threshold, and the absolute value of the difference between each of the current achievement rates and the target achievement rate does not exceed the second threshold.

[0111] In an optional implementation of an embodiment of the present invention, the standard adjustment module 330 may include: an adjustment condition judgment submodule, used to sequentially obtain each of the current standard-reaching rates as the current standard-reaching rates to be judged, and when it is determined that the current standard-reaching rates to be judged meet the dynamic adjustment conditions, the current standard-reaching rates to be judged are determined as the standard-reaching rates to be adjusted; a target record acquisition submodule, used to obtain target answer record data corresponding to the standard-reaching rates to be adjusted in the answer record data; and a standard adjustment submodule, used to dynamically adjust the standard-reaching data corresponding to the target answer record according to a preset adjustment accuracy.

[0112] In an optional implementation of an embodiment of the present invention, the adjustment condition judgment submodule can be specifically used to: when it is determined that the current compliance rate to be judged is different from the target compliance rate, determine that the current compliance rate to be judged meets the dynamic adjustment condition; or, calculate the compliance rate deviation value between the current compliance rate to be judged and the target compliance rate; when it is determined that the compliance rate deviation value exceeds a third threshold, determine that the current compliance rate to be judged meets the dynamic adjustment condition.

[0113] In an optional implementation of an embodiment of the present invention, the standard adjustment submodule can be specifically used to: select test compliance data in sequence within the target value range of the compliance standard data according to the preset adjustment accuracy, and obtain the test compliance rate corresponding to the target answer record according to each of the test compliance data; obtain the test difference between each of the test compliance rates and the target compliance rate; determine the target test difference from each of the test differences; and update the compliance standard data according to the test compliance data corresponding to the target test difference.

[0114] In an optional implementation of an embodiment of the present invention, the device may also include: a target achievement rate acquisition module, used to obtain the target achievement rate set by the user; or, obtain the average achievement rate of each of the current achievement rates, and determine the average achievement rate as the target achievement rate.

[0115] In an optional implementation of the embodiment of the present invention, the device may also include: a user level update module, used to obtain the ratio of the number of correct answers to the total number of answers of each target user in the current level update cycle as user achievement record data; based on the user achievement record data, each target user is determined as a user of each level.

[0116] In an optional implementation of the embodiment of the present invention, the device may also include: a knowledge point level update module, which is used to obtain user answer record data of all target users for each target knowledge point in the current level update cycle; based on a preset empirical model, obtain difficulty coefficient data of each target knowledge point according to each user answer record data; according to the difficulty coefficient data, determine each target knowledge point as the knowledge point of each level.

[0117] The above-mentioned device can execute the data dynamic adjustment method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the data dynamic adjustment method.

[0118] An embodiment of the present invention provides a data dynamic adjustment device, which obtains answer record data of users of different levels for knowledge points of different difficulty levels, and obtains the attainment rate of each part of the answer record data based on the current attainment standard. When it is determined that each attainment rate cannot meet the reasonable conditions of the attainment rate that matches the target attainment rate, the current attainment standard is dynamically adjusted to make the attainment rate of each part of the answer record data obtained based on the adjusted attainment standard close to the expected target attainment rate, ensuring that the learner's attainment rate remains within a reasonable range, realizing personalized adjustment of the attainment difficulty, and enhancing user stickiness.

[0119] Example 4

[0120] Figure 4A schematic diagram of the structure of a computer device provided in Example 4 of the present invention. Figure 4 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 4 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.

[0121] like Figure 4 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).

[0122] 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.

[0123] 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.

[0124] 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 4 Not shown, often called a "hard drive"). Although Figure 4 Not shown, a magnetic disk drive for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and 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.

[0125] 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 methods of the embodiments described herein.

[0126] 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 4 Not 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.

[0127] The processor 16 executes various functional applications and data processing by running the program stored in the memory 28, thereby realizing the data dynamic adjustment method provided by the embodiment of the present invention: obtaining the answer record data of each level of users for each level of knowledge points; obtaining the current achievement rate corresponding to each answer record data according to the achievement standard data of each level of users for the knowledge points of each level; when it is determined that each current achievement rate does not meet the reasonable achievement rate conditions that match the target achievement rate, dynamically adjust each achievement standard data according to the target achievement rate and each answer record data, so that each current achievement rate is within the preset expected range of the target achievement rate; wherein, the reasonable achievement rate conditions include that the variance of each current achievement rate does not exceed the first threshold, and the absolute value of the difference between each current achievement rate and the target achievement rate does not exceed the second threshold.

[0128] Example 5

[0129] 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 data dynamic adjustment method provided by the embodiment of the present invention is implemented: answer record data of users of each level for knowledge points of each level are obtained; based on the attainment standard data of users of each level for knowledge points of each level, the current attainment rate corresponding to each answer record data is obtained; when it is determined that each current attainment rate does not meet the reasonable attainment rate conditions that match the target attainment rate, each attainment standard data is dynamically adjusted according to the target attainment rate and each answer record data, so that each current attainment rate is within the preset expected range of the target attainment rate; wherein the reasonable attainment rate conditions include that the variance of each current attainment rate does not exceed a first threshold value, and the absolute value of the difference between each current attainment rate and the target attainment rate does not exceed a second threshold value.

[0130] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductors, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with 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 can be any tangible medium containing or storing a program that can be used by an instruction execution system, device or device or used in combination with it.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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 data dynamic adjustment method, characterized in that: include: Obtain the answer record data of users of different levels for each level of knowledge points; According to the standard data of the users of each level for the knowledge points of each level, the current standard rate corresponding to each of the answer record data is obtained; wherein a stopping strategy model is used to determine whether the user has met the standard for the knowledge point, and the standard data is a specific probability difference threshold in the stopping strategy model; In the event that it is determined that each current achievement rate does not meet the reasonable achievement rate conditions for matching the target achievement rate, dynamically adjusting each achievement standard data based on the target achievement rate and each answer record data so that each current achievement rate is within a preset expected range for matching the target achievement rate; The reasonable conditions for the attainment rates include that the variance of each current attainment rate does not exceed a first threshold, and the absolute value of the difference between each current attainment rate and the target attainment rate does not exceed a second threshold; if the variance of the current attainment rate exceeds the first threshold, then the attainment standard data of each level of users for each level of knowledge point is adjusted; if the difference between any current attainment rate and the target attainment rate exceeds the second threshold, then the attainment standard data of the user of that level for the knowledge point of that level is adjusted; The dynamically adjusting each of the attainment standard data according to the target attainment rate and each of the answer record data includes: sequentially acquiring each of the current compliance rates as the current compliance rates to be determined, and determining the current compliance rates to be determined as the compliance rates to be adjusted when it is determined that the current compliance rates to be determined meet the dynamic adjustment conditions; Obtaining target answer record data corresponding to the target achievement rate to be adjusted from the answer record data; The achievement standard data corresponding to the target answer record is dynamically adjusted according to a preset adjustment accuracy.

2. The method according to claim 1, characterized in that The determining that the current compliance rate to be determined satisfies a dynamic adjustment condition includes: In the case where it is determined that the current compliance rate to be determined is different from the target compliance rate, determining that the current compliance rate to be determined meets the dynamic adjustment condition; or Calculating a standard-attainment rate deviation value between the current standard-attainment rate to be determined and the target standard-attainment rate; In the case where it is determined that the standard-reaching rate deviation value exceeds a third threshold, it is determined that the current standard-reaching rate to be determined meets a dynamic adjustment condition.

3. The method according to claim 1 or 2, characterized in that The dynamically adjusting the attainment standard data corresponding to the target answer record according to a preset adjustment accuracy includes: According to the preset adjustment accuracy, test compliance data are sequentially selected within the target value range of the compliance standard data, and the test compliance rate corresponding to the target answer record is obtained based on each test compliance data; Obtaining a test difference between each test compliance rate and the target compliance rate; determining a target test difference from each of the test differences; The compliance standard data is updated according to the test compliance data corresponding to the target test difference.

4. The method according to claim 1, wherein In the case where it is determined that each current achievement rate does not meet the reasonable achievement rate condition for matching the target achievement rate, before dynamically adjusting each achievement standard data according to the target achievement rate and each target answer record data, the method further includes: Get the target achievement rate set by the user; or, An average of the current target achievement rates is obtained, and the average of the target achievement rates is determined as the target target achievement rate.

5. The method according to claim 1, wherein Before obtaining the answer record data of users of different levels for knowledge points of different levels, the method further includes: Obtain the ratio of the number of correct answers to the total number of answers for each target user in the current level update cycle as the user's achievement record data; According to the user achievement record data, the target users are respectively determined as users of each level.

6. The method according to claim 1, characterized in that Before obtaining the answer record data of users of different levels for knowledge points of different levels, the method further includes: Obtain the user answer record data for each target knowledge point of all target users in the current level update cycle; Based on a preset empirical model, obtaining difficulty coefficient data of each target knowledge point according to the answer record data of each user; According to the difficulty coefficient data, the target knowledge points are respectively determined as knowledge points of each level.

7. A data dynamic adjustment device, characterized in that: include: The answer record acquisition module is used to obtain the answer record data of users of different levels for each level of knowledge points; A standard-attainment rate acquisition module is configured to obtain the current standard-attainment rate corresponding to each of the answer record data based on the standard-attainment data of each level of user for each level of knowledge point; wherein a stopping strategy model is used to determine whether the user has met the standard for the knowledge point, and the standard-attainment data is a specific probability difference threshold in the stopping strategy model; a standard achievement adjustment module for dynamically adjusting each of the standard achievement data based on the target achievement rate and each of the answer record data, if it is determined that each of the current achievement rates does not meet the reasonable conditions for achieving the target achievement rate, so that each of the current achievement rates is within a preset expected range of matching the target achievement rate; The reasonable conditions for the attainment rates include that the variance of each current attainment rate does not exceed a first threshold, and the absolute value of the difference between each current attainment rate and the target attainment rate does not exceed a second threshold; if the variance of the current attainment rate exceeds the first threshold, then the attainment standard data of each level of users for each level of knowledge point is adjusted; if the difference between any current attainment rate and the target attainment rate exceeds the second threshold, then the attainment standard data of the user of that level for the knowledge point of that level is adjusted; The achievement standard adjustment module includes: an adjustment condition judgment submodule, which is used to obtain each of the current achievement rates in turn as the current achievement rate to be judged, and when it is determined that the current achievement rate to be judged meets the dynamic adjustment conditions, the current achievement rate to be judged is determined as the achievement rate to be adjusted; a target record acquisition submodule, which is used to obtain the target answer record data corresponding to the achievement rate to be adjusted in the answer record data; and a standard adjustment submodule, which is used to dynamically adjust the achievement standard data corresponding to the target answer record according to a preset adjustment accuracy.

8. 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 data dynamic adjustment method according to any one of claims 1 to 6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the data dynamic adjustment method according to any one of claims 1 to 6 is implemented.

Images