Learning planning method and device

Abstract

The invention discloses a learning planning method. The method comprises the following steps: acquiring the correct rate of each evaluation dimension of a knowledge point corresponding to an nth review test event; according to the importance of each evaluation dimension, fusing each correct rate to obtain a comprehensive mastering degree P corresponding to the nth review test event; calling a time interval tn; performing memory ability analysis processing based on the comprehensive mastering degree P and the time interval tn to obtain memory intensity S corresponding to the nth review test event; acquiring a preset memory retention rate R; and carrying out time information conversion processing based on a preset memory retention rate R and the memory intensity S corresponding to the nth review test event to obtain a suggested interval duration of the (n + 1) th review test event. According to the method, the problem that the review effect is gradually reduced due to the fact that the current learning plan deviates from the memory condition of the user can be solved, and the requirements of partial emphasized dimensions are also considered while efficient review is carried out on each dimension according to the memory condition of the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of education, in particular to a learning planning method and a planning device. BACKGROUND

[0002] Learning is very important, however, students need to learn a lot of knowledge points, and it is easy to forget the previous knowledge after learning the latter. For this problem, people first use the forgetting curve to arrange the review time more scientifically to achieve more efficient review effect, especially in the education industry. Now more and more psychologists have put forward more mathematical models for fitting the forgetting curve. These mathematical models are often associated with memory strength S. In the current multiple forgetting curve models, memory strength S is often fixed as a constant. However, in fact, memory strength S is a constant that needs to be defined according to individual memory ability. It has individual differences, and the memory strength S of different users is different. With the increase of review frequency, people become more familiar with knowledge points, and at this time, the memory ability for related knowledge points also changes. That is, even for the same user, if only a fixed memory strength S value is used for review, the review effect will gradually decrease due to the deviation from the memory situation.

[0003] In addition, the learning and application of a knowledge point or the same batch of knowledge points are complex and multi-faceted, which can form different aspects of ability or different degrees of ability. However, for each person, not all multi-faceted learning can be balanced development, such as better or weaker directions, and corresponding different development needs, such as directions that want to be emphasized and directions that want to make progress. Therefore, how to efficiently review in multiple aspects according to the user's memory situation while considering the needs of the biased direction is a problem to be solved. SUMMARY

[0004] Therefore, the embodiments of the present application provide a learning planning method, which can efficiently review in multiple aspects according to the user's memory situation while considering the needs of the biased direction.

[0005] In a first aspect, the embodiments of the present application provide a learning planning method, which comprises:

[0006] obtaining the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event, wherein n is a positive integer greater than or equal to two;

[0007] fusing each correct rate according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P corresponding to the nth review test event;

[0008] retrieving the time interval t n , wherein the time interval t nis a time interval between an end time corresponding to the n-1th review test event and a start time corresponding to the nth review test event;

[0009] based on the comprehensive mastery degree P and the time interval t n performing a memory ability analysis process to obtain a memory strength S corresponding to the nth review test event;

[0010] obtaining a preset memory retention rate R, wherein the preset memory retention rate R is a memory retention rate target value set by the user;

[0011] based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event, performing a time information conversion process to obtain a recommended interval duration of the (n+1)th review test event.

[0012] Optionally, the step of obtaining the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event comprises:

[0013] obtaining a current evaluation item, wherein each evaluation item contains a respective evaluation dimension;

[0014] based on the current evaluation item, obtaining a corresponding evaluation dimension as a current evaluation dimension;

[0015] according to the current evaluation dimension, classifying and extracting the result of the nth review test event to obtain a correct rate corresponding to each evaluation dimension.

[0016] Optionally, the evaluation item includes a skill modal item and / or a difficulty level item.

[0017] Optionally, when the evaluation item includes a skill modal item, the skill modal item contains evaluation dimensions of listening, speaking, reading, and writing; and the step of obtaining the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event comprises:

[0018] obtaining a respective correct rate of the knowledge point corresponding to the nth review test event in the evaluation dimensions of listening, speaking, reading, and writing;

[0019] the step of fusing each correct rate according to the importance of each evaluation dimension to obtain a comprehensive mastery degree P corresponding to the nth review test event comprises:

[0020] fusing each correct rate according to the importance of each evaluation dimension of listening, speaking, reading, and writing to obtain a comprehensive mastery degree P corresponding to the nth review test event.

[0021] Optionally, when the evaluation items include hierarchical items, the hierarchical items include evaluation dimensions of difficult questions, medium questions and easy questions; the step of obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the nth review test event includes:

[0022] obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the nth review test event;

[0023] the step of fusing each correct rate according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P corresponding to the nth review test event includes:

[0024] fusing each correct rate according to the importance of each evaluation dimension of difficult questions, medium questions and easy questions to obtain the comprehensive mastery degree P corresponding to the nth review test event.

[0025] Optionally, the nth review test event includes an initial test stage and a wrong question correction stage; the step of obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the nth review test event includes:

[0026] obtaining the total number of questions in the initial test stage, the number of correct questions in the initial test stage and the number of correct questions in the wrong question correction stage corresponding to each evaluation dimension in the nth review test event;

[0027] in the same evaluation dimension, fusing the number of correct questions in the wrong question correction stage and the number of correct questions in the initial test stage to obtain the comprehensive number of correct questions, and obtaining the correct rate of the corresponding evaluation dimension based on the ratio of the comprehensive number of correct questions to the total number of questions in the initial test stage;

[0028] summarizing the calculation results of each evaluation dimension to obtain the correct rate of each evaluation dimension.

[0029] Optionally, before the step of fusing each correct rate according to the importance of each evaluation dimension, it includes:

[0030] accepting the weight distribution coefficient confirmed by the user for each evaluation dimension respectively;

[0031] taking each weight distribution coefficient as the importance of the corresponding evaluation dimension.

[0032] Optionally, the step of obtaining the memory strength S corresponding to the nth review test event based on the comprehensive mastery degree P and the time interval t n performing memory capacity analysis processing to obtain the memory strength S corresponding to the nth review test event includes:

[0033] calling a memory curve model, the memory curve model being a function of associative memory retention rate, memory strength and time;

[0034] The comprehensive mastery degree P and the time interval t are taken as inputs to perform memory capacity analysis in the memory curve model to obtain a memory strength S corresponding to the nth review test event; wherein the comprehensive mastery degree P represents a current memory retention rate in the memory curve model.

[0035] Optionally, the step of performing time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event to obtain a recommended interval duration of an (n+1)th review test event, comprises:

[0036] The preset memory retention rate R and the memory strength S corresponding to the nth review test event are taken as inputs to perform time information analysis in the memory curve model to obtain a recommended interval duration of an (n+1)th review test event.

[0037] In a second aspect, the embodiments of the present application provide a learning planning device, which comprises:

[0038] A first obtaining module is configured to obtain a correct rate of each evaluation dimension of a knowledge point corresponding to an nth review test event, wherein n is a positive integer greater than or equal to 2;

[0039] A fusion module is configured to fuse each correct rate according to an importance of each evaluation dimension to obtain a comprehensive mastery degree P corresponding to the nth review test event;

[0040] A calling module is configured to call a time interval t n , wherein the time interval t n is a time difference between an end time of an (n-1)th review test event and a start time of the nth review test event;

[0041] An analysis module is configured to perform memory capacity analysis processing based on the comprehensive mastery degree P and the time interval t n to obtain a memory strength S corresponding to the nth review test event;

[0042] A second obtaining module is configured to obtain a preset memory retention rate R, wherein the preset memory retention rate R is a memory retention rate target value set by a user;

[0043] A conversion module is configured to perform time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event to obtain a recommended interval duration of an (n+1)th review test event.

[0044] The learning planning method provided in this application embodiment has the following technical effects: After the nth review test event, by introducing the accuracy rate of each evaluation dimension of the knowledge points in the nth review test event, and integrating multiple accuracy rates according to the importance of each evaluation dimension, the comprehensive mastery level P corresponding to the nth review test event is obtained. Then, based on the comprehensive mastery level P and the corresponding time interval t, memory ability is analyzed to analyze the user's current memory status and obtain the memory intensity S corresponding to the nth review test event, realizing adaptive updating of memory intensity S. Then, based on the updated memory intensity S and the user's pre-set memory retention rate R, time information is converted to obtain the time limit corresponding to achieving / maintaining the user's expected memory retention rate R in the (n+1)th review test event under the memory intensity S possessed in the nth review test event, that is, the interval from the end of the nth review test event to the start of the (n+1)th review test event. Thus, this solution uses the overall mastery level P to update the memory strength S, and based on the updated memory strength S and the user's expected memory retention rate R, obtains a learning time plan that matches the user's new memory ability and memory effect expectations. This improves the problem of the current learning plan deviating from the user's actual memory situation, resulting in a gradual decline in review effectiveness. In addition, since the different importance of each assessment dimension can be set based on the user's bias towards the knowledge point dimension, the overall mastery level P obtained in this way not only includes the overall mastery results of each assessment dimension, but also emphasizes the user's mastery of the target dimension. The memory strength S and the interval time for further calculation are actually the result of comprehensively considering the situation of each assessment dimension while emphasizing the target dimension, realizing the need for efficient review of each dimension according to the user's own memory situation while taking into account some of the more emphasized dimensions. Attached Figure Description

[0045] Figure 1 This is a flowchart of a learning planning method provided in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the structure of a learning planning device provided in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] As Figure 1 shown, Figure 1 is a flowchart of a learning planning method provided by an embodiment of the present application. The learning planning method comprises the following steps:

[0050] S101: Obtain the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event, wherein, n is a positive integer greater than or equal to two.

[0051] In this embodiment, multiple review test events can be included. Through multiple review tests, the knowledge points are repeatedly used / reviewed to achieve memory review of the knowledge points, and further memory reinforcement.

[0052] In one embodiment, the first review test event, the second review test event, the third review test event, and the like are sequentially performed, and there is a certain time interval between each event, which constitutes a review test event series. In a preferred embodiment, there is a first learning knowledge event before the first review test event, and then the review test events are sequentially performed. At this time, it can be understood that a review test event series about the learning knowledge event is constituted. For example, when the user starts to learn new knowledge events, or reviews the old knowledge events, the current review test event series is exited, and a new review test event series is prepared to be started.

[0053] In this embodiment, at least two review test events have occurred, that is, n is a positive integer greater than or equal to two. For example, the first review test event and the second review test event are events that have occurred and ended, and the third review test event can be an event that is expected to occur in the future or an event that is triggered at the moment (such as opening the app for testing).

[0054] The knowledge point content of the review test event can be a targeted test event for a single knowledge point, such as a test of different levels / degrees of difficulty for a knowledge point, or a test of different question types for a knowledge point, or a test of listening, speaking, reading, and writing for a knowledge point, and the like. Of course, it can also be an event for testing all knowledge points in a section / chapter, and the dimensions are as above. The difference here is only the size of the knowledge point range, and the present scheme does not limit the number of knowledge point objects.

[0055] It can be understood that the content range of the knowledge points involved in the multiple review test events in the same series is the same. For example, the content range of the knowledge points of the review test events mentioned in steps S101-S106 in the embodiment is the same. If the content of the knowledge points of the first review test event is the content of the knowledge points of a section, the content of the knowledge points of the second review test event, the third review test event, and the nth review test event is the content of the knowledge points of the section. If the chapter is changed, it is another series of review test events.

[0056] As for each evaluation dimension and the accuracy of each evaluation dimension, a few examples are given here:

[0057] For example, from the perspective of skill modalities, there can be four dimensions of listening, speaking, reading, and writing, or three dimensions of listening, speaking, and writing, or other number of dimensions, which are not limited here; suppose that in the nth review test event, there are the above-mentioned four dimensions of listening, speaking, reading, and writing, and the correct rates of the four dimensions are A, B, C, and D respectively, then S101 is to extract the correct rate values of A, B, C, and D respectively in the nth review test event for subsequent steps.

[0058] If the difficulty level is considered, there can be three dimensions of difficult, medium, and easy, or two dimensions of difficult and easy, or four dimensions of very difficult, difficult, medium, and easy, etc., which are not limited here; suppose that in the nth review test event, there are the above-mentioned three dimensions of difficult, medium, and easy, and the correct rates of the three dimensions are A, B, and C respectively, then S101 is to extract the correct rate values of A, B, and C respectively in the nth review test event for subsequent steps.

[0059] If different types of questions are considered, there can be three dimensions of multiple-choice questions, fill-in-the-blank questions, and reasoning questions, or three dimensions of multiple-choice questions, fill-in-the-blank questions, and reading comprehension questions, or two dimensions of multiple-choice questions and fill-in-the-blank questions, etc., which are not limited here; suppose that in the nth review test event, there are the above-mentioned three dimensions of multiple-choice questions, fill-in-the-blank questions, and reasoning questions, and the correct rates of the three dimensions are A, B, and C respectively, then S101 is to extract the correct rate values of A, B, and C respectively in the nth review test event for subsequent steps.

[0060] As can be seen, from different evaluation project perspectives, there can be different evaluation dimensions. Once an evaluation project perspective is selected, there will be a corresponding series of evaluation dimensions. This step needs to extract the corresponding correct rate data based on each evaluation dimension in the test event.

[0061] S102: Fuse the respective correct rates according to the importance of each evaluation dimension to obtain a comprehensive mastery degree P corresponding to the nth review test event.

[0062] In this step, the respective correct rates extracted based on each evaluation dimension in S101 are fused according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P.

[0063] The importance of each evaluation dimension represents the weight proportion of each evaluation dimension in the process of constructing the comprehensive mastery degree P. The correct rate of each evaluation dimension and the importance of each evaluation dimension together affect the result of the comprehensive mastery degree P. The correct rate of each evaluation dimension is a factual value, while the importance of each evaluation dimension is an important influencing element of the fusion result bias, which can help to amplify / reduce the influence of one / part of the evaluation dimension result on the fusion result, so as to adjust the presentation of the comprehensive mastery result according to the actual demand / weight demand of the user, and use this value for subsequent memory strength update and time value conversion, thereby affecting the final time interval value.

[0064] It is worth mentioning that the embodiment does not directly extract the correct rate of the entire test result from the nth review test event, but first divides the evaluation dimensions, extracts the correct rate of each evaluation dimension, and then fuses the results of each evaluation dimension based on the user's bias towards the target evaluation dimension to obtain the target comprehensive mastery degree P. This better meets the user's refined development needs, especially the development needs of some target dimension capabilities. That is, from the data processing, physical meaning, and influence on subsequent results, the comprehensive mastery degree P in the embodiment is a further optimization and improvement of the direct acquisition of the entire test event correct rate.

[0065] For example, when the user is weak in a certain dimension (such as listening / medium questions / reasoning questions), or simply wants to strengthen the ability of a certain dimension, the weight proportion of the evaluation dimension can be adjusted to achieve this, especially to increase the development of the target dimension. After such adjustment, the comprehensive mastery degree P not only contains the fusion result of each evaluation dimension, but also particularly reflects the mastery result of the target dimension / target dimension group.

[0066] S103: Retrieve the time interval t n , wherein the time interval t n is the time difference between the end time corresponding to the (n-1)th review test event and the start time corresponding to the nth review test event.

[0067] There is a time interval between the two review test events: the time interval can be 0.5 days, 1 day, etc., and here it is extracted according to the actual time interval between the n-1th review test event and the n th review test event.

[0068] S104: Based on the comprehensive mastery degree P and the time interval t n The memory capacity analysis process is performed to obtain the memory strength S corresponding to the n th review test event.

[0069] Considering that the memory strength S is an element defined by individual memory capacity, and for the same person, the memory strength S will also change; and the review test result can change with the user's knowledge point mastery and memory, which is an information that can reflect the user's individual knowledge point mastery, and also reflects the change of individual user's knowledge point mastery and current memory. Therefore, based on the comprehensive mastery degree P of the knowledge point in the n th review test event, the memory strength S of the individual user in the current review event is analyzed.

[0070] It is worth mentioning that the result of the comprehensive mastery degree P will be affected by the importance of the user setting for each evaluation dimension, but it is still based on the fact value of each evaluation dimension in the n th review test event, and the importance only adjusts the bias of some evaluation dimensions. Therefore, after the user has set the importance of each evaluation dimension, the dynamic change of the comprehensive mastery degree P with each different knowledge point mastery and memory degree still reflects the user's current memory retention rate of the target knowledge point, and the current memory strength S is obtained through the memory retention rate.

[0071] It should be noted that since the comprehensive mastery degree P is based on the importance of each evaluation dimension to fuse each correct rate, it emphasizes the mastery degree of the biased dimension / target dimension, so the memory strength S obtained based on the comprehensive mastery degree P is actually also based on the importance of each evaluation dimension, and also emphasizes the memory situation of the biased dimension / target dimension.

[0072] In addition, after experiencing a review test event, the memory of the knowledge point will be consolidated / strengthened once, which can slow down the forgetting rate, and then with the passage of time, the memory will still show a certain forgetting trend until the review test event is experienced again to form a memory stimulus. That is, in the time interval between the two review test events, the memory itself will change, and the re-stimulation of the subsequent review test event will also affect the memory strength S again, which together forms the latest memory retention of the knowledge point. Therefore, the actual implementation of the present embodiment is to take every two adjacent review test events as a group, and analyze the memory strength of the subsequent review test event based on the time interval t n to obtain the memory retention of the knowledge point when experiencing the passage of time and the re-stimulation event, that is, the current memory strength S.

[0073] S105: Obtain a preset memory retention rate R, wherein the preset memory retention rate R is a memory retention target value set by the user.

[0074] In the present embodiment, the preset memory retention rate R is a memory retention target value set by the user, which can also be understood as an expected value. For example, the user expects the memory retention rate to reach 85% or 60%, and then the subsequent scheme will combine the expected value set by the user for learning time planning. Of course, in some schemes, the preset memory retention rate R can also be data set by the user through trial, and in the product use aspect, these data are the current memory retention target value.

[0075] It is worth mentioning that the preset memory retention rate R can be a constant value in multiple review test event cycles, or can be adjusted after any review test event, which is not limited here. If the preset memory retention rate R is adjusted, the scheme in the present embodiment will re-plan the learning time according to the adjusted memory retention rate R.

[0076] S106: Perform time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event to obtain a recommended interval duration of the (n+1)th review test event.

[0077] In the present embodiment, according to the foregoing steps, at this step, the memory strength S of the nth review test event and the preset memory retention rate R have been obtained. In order to achieve / maintain the set memory retention target value with the memory ability of the nth review test event in the (n+1)th review test event, this step will convert the memory strength S of the user in the nth review test event and the preset memory retention rate R to the optimal interval duration of the (n+1)th review test event, that is, the recommended interval duration here.

[0078] In this step, the starting time of the n+1 review test event can be planned based on the end time corresponding to the n review test event and the recommended interval length obtained in the above steps.

[0079] It is worth mentioning that, based on the description of S104, since the memory strength S at this time is actually formed based on the importance of each evaluation dimension, and the memory of the biased dimension / target dimension is emphasized, therefore, the interval length converted based on the memory strength S is actually formed based on the importance of each evaluation dimension, and the time interval required by the biased dimension / target dimension is emphasized.

[0080] In the embodiment of the application, after the n review test event, the correct rates of each evaluation dimension of the knowledge points in the n review test event are introduced, the plurality of correct rates are fused according to the importance of each evaluation dimension, the comprehensive mastery degree P corresponding to the n review test event is obtained, and the memory ability is analyzed based on the comprehensive mastery degree P and the corresponding time interval t to analyze the current memory of the user, and the memory strength S corresponding to the n review test event is obtained, thereby realizing the adaptive update of the memory strength S. Then, based on the updated memory strength S and the memory retention rate R set by the user in advance, the time information is converted to obtain the time limit corresponding to the memory strength S possessed at the n review test event, that is, the interval length from the end of the n review test event to the start of the n+1 review test event, when the memory retention rate R expected by the user is reached / maintained at the n+1 review test event. In this way, the comprehensive mastery degree P is used to update the memory strength S, and based on the updated memory strength S and the memory retention rate R expected by the user, the learning time planning conforming to the new memory ability and memory effect expected value of the user is obtained, thereby improving the problem that the current learning planning deviates from the memory of the user and gradually reduces the review effect. In addition, since the importance of each evaluation dimension can be set based on the user's bias to the knowledge point dimension, the comprehensive mastery degree P obtained by fusion not only contains the comprehensive mastery result of each evaluation dimension, but also emphasizes the mastery of the target dimension of the user. Therefore, the memory strength S analyzed and the interval length further calculated are actually the result of considering the situation of each evaluation dimension and emphasizing the target dimension direction, thereby realizing efficient review of each dimension according to the memory of the user and taking into account the needs of the biased dimension.

[0081] Optionally, the step of obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the n-th review test event comprises: obtaining a current evaluation item, wherein each evaluation item contains a respective evaluation dimension; obtaining a corresponding evaluation dimension as a current evaluation dimension based on the current evaluation item; and classifying and extracting the result of the n-th review test event according to the current evaluation dimension to obtain the correct rate corresponding to each evaluation dimension.

[0082] As described in the foregoing embodiment in step S101, the review test event can have different evaluation item angles, and different evaluation items can contain multiple different evaluation dimensions. The specific evaluation item and the corresponding evaluation dimension are divided by subject (such as English, mathematics, Chinese, etc.) and general cognitive classification, or can be defined by the user, which is not limited here.

[0083] In order to better extract the evaluation dimension information, the current evaluation item needs to be confirmed first, and then the corresponding evaluation dimension is obtained according to the specific evaluation item, and then the result of the n-th review test event is analyzed and extracted according to the corresponding evaluation dimension.

[0084] Specifically, the evaluation item can include a skill modal item and / or a difficulty level item. The skill modal item can include dimensions related to listening, speaking, reading, and writing, or dimensions related to different question types (such as multiple choice questions, fill-in-the-blank questions, and true or false questions), which are not limited here. The difficulty level item can include dimensions related to difficult questions, medium questions, and easy questions, and the like, which are not exhaustively listed here.

[0085] Preferably, when the evaluation item includes a skill modal item, the skill modal item includes evaluation dimensions of listening, speaking, reading, and writing. The step of obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the n-th review test event comprises: obtaining the respective correct rate of the n-th review test event corresponding to the knowledge point in the evaluation dimensions of listening, speaking, reading, and writing. The step of fusing the correct rates according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P of the n-th review test event comprises: fusing the correct rates according to the importance of the evaluation dimensions of listening, speaking, reading, and writing to obtain the comprehensive mastery degree P of the n-th review test event.

[0086] The skill modal item is applicable to multiple subjects. In terms of language subjects, it can be divided into dimensions related to listening, speaking, reading, and writing, such as Chinese and English subjects.

[0087] Here, take the English subject as an example: in the English subject, listening is often the user's weak point, and its performance may lag behind speaking, reading, and writing. In order to amplify the listening part in the overall mastery degree, the weight of the listening dimension can be increased. For example, the correct rates of a knowledge point in the English subject in the n-th review test event in the listening, speaking, reading, and writing dimensions are A, B, C, and D, respectively. After obtaining the correct rates of each evaluation dimension, the correct rates are fused according to the importance of each evaluation dimension by the following formula to obtain the comprehensive mastery degree P:

[0088] P = 40% * A + 20% * B + 20% * C + 20% * D.

[0089] Preferably, when the evaluation project includes a difficulty level project, the difficulty level project includes evaluation dimensions of difficult questions, medium questions, and easy questions; the step of obtaining the correct rates of each evaluation dimension of the knowledge point corresponding to the n-th review test event includes obtaining the respective correct rates of the knowledge point corresponding to the n-th review test event in the evaluation dimensions of difficult questions, medium questions, and easy questions; and the step of fusing each correct rate according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P of the n-th review test event includes fusing each correct rate according to the importance of the evaluation dimensions of difficult questions, medium questions, and easy questions to obtain the comprehensive mastery degree P of the n-th review test event.

[0090] The difficulty level project is suitable for most subjects, as almost every subject has knowledge points classified into difficult questions, medium questions, and easy questions. From one perspective, the process of understanding to application itself involves a progressive process, and the transition from easy questions to difficult questions may be involved. Reasonable question dimension allocation can help the process to be smoothly passed, or even faster. For example, in the initial review test stage, the weight of easy questions is increased, in the intensive review test stage, the weight of medium questions is increased, and in the knowledge point high-level learning review test stage, the weight of difficult questions is increased. This can adjust different review test series according to the actual needs of users. From another perspective, different users have different abilities and goals, so different users have different training needs for difficult questions, medium questions, and easy questions, but multi-dimensional training is still necessary. For example, easy questions are used as a basis and confidence building, medium questions are used as advanced exercises and perception training, and difficult questions are used as a challenge goal or ultimate purpose. In general, regardless of the perspective, users can adjust the allocation of each evaluation dimension according to their actual situation / needs / stage position, that is, different weights are allocated to difficult questions, medium questions, and easy questions in different learning stages.

[0091] In order to successfully implement the above difficulty level project, the correct rate of each evaluation dimension corresponding to the knowledge point of the nth review test event in the difficult question, the medium question and the easy question is obtained in each review test series, and the correct rates are fused according to the importance of each evaluation dimension of the difficult question, the medium question and the easy question set in the current stage / current review test series, to obtain the comprehensive mastery degree P corresponding to the nth review test event.

[0092] Preferably, the nth review test event includes an initial test stage and a wrong question correction stage; the step of obtaining the correct rate of each evaluation dimension corresponding to the nth review test event includes: obtaining the total number of questions, the number of correct questions in the initial test stage and the number of correct questions in the wrong question correction stage of each evaluation dimension in the nth review test event; in the same evaluation dimension, the number of correct questions in the wrong question correction stage and the number of correct questions in the initial test stage are fused to obtain the comprehensive number of correct questions, and the correct rate of the corresponding evaluation dimension is obtained based on the ratio of the comprehensive number of correct questions to the total number of questions in the initial test stage; the calculation results of each evaluation dimension are summarized to obtain the correct rate of each evaluation dimension.

[0093] In some embodiments, the correct rate can be obtained based on the number of correct questions divided by the total number of questions, and the correct rate of each evaluation dimension can be obtained according to the corresponding number of correct questions in each evaluation dimension divided by the total number of questions in the evaluation dimension. In the present embodiment, in addition to the memory strength of the knowledge point when initially doing the question, the memory strength is actually deepened when correcting the wrong question, so the nth review test event is divided into two stages of initial test stage and wrong question correction stage, and the correct rate of the nth review test event is fused from the data of the two stages, so that the memory strength in the whole event is more comprehensively and systematically considered.

[0094] The following is an example of an English test event:

[0095] AR i , BR i , CR i , DR i is the number of correct questions of A (listen), B (speak), C (read), and D (write) for knowledge point i in the initial test. i is the knowledge point number.

[0096] AR i ', BR i ', CR i ', DR i ' is the number of wrong questions (same questions) of A (listen), B (speak), C (read), and D (write) for knowledge point i in the wrong question correction stage.

[0097] A i , B i , C i , D i respectively are the total number of A (listening), B (speaking), C (reading), D (writing) questions of knowledge point i.

[0098] Here, the correct rates of knowledge point i in A (listening), B (speaking), C (reading), D (writing) dimensions are respectively: (AR i + AR i ') / A i , (BR i + BR i ') / B i , (CR i + CR i ') / C i , (DR i + DR i ') / D i .

[0099] And the further obtained comprehensive mastery degree P can be expressed as:

[0100] P = a% * (AR i + AR i ') / A i + b% * (BR i + BR i ') / B i + c% * (CR i + CR i ') / C i + d% * (DR i + DR i ') / D i .

[0101] Wherein, a%, b%, c%, d% are the weight proportions of A (listening), B (speaking), C (reading), D (writing) dimensions, which can be 40%, 20%, 20%, 20% specifically.

[0102] Preferably, before the step of fusing each of the correct rates according to the importance of each evaluation dimension, it includes: accepting the weight distribution coefficients respectively confirmed by the user for each evaluation dimension; taking each of the weight distribution coefficients as the importance of the corresponding evaluation dimension.

[0103] In the embodiment, the importance of each evaluation dimension can be obtained according to the weight distribution coefficients confirmed by the user, which is set and confirmed in advance according to the specific needs of the user. The weight proportion after setting actually expresses the biased needs of the user for each evaluation dimension.

[0104] For example, when the user's hearing ability is weak or the user wants to strengthen the hearing ability, the weight of the hearing ability in the comprehensive mastery degree can be increased, for example, the four weight values are set as 40%, 20%, 20%, and 20%. When the corresponding ability of an evaluation dimension is good or the influence of the evaluation dimension is to be weakened, the weight ratio value can be appropriately reduced.

[0105] In addition, in the embodiment, preferably, the sum of the coefficients of the plurality of evaluation dimensions is 1.

[0106] Preferably, the memory strength S is calculated based on the comprehensive mastery degree P and the time interval t according to a memory curve model. n The step of performing the memory ability analysis processing to obtain the memory strength S corresponding to the nth review test event includes: calling a memory curve model, the memory curve model being a function of the memory retention rate, the memory strength, and the time; inputting the comprehensive mastery degree P and the time interval t into the memory curve model to perform the memory ability analysis and obtain the memory strength S corresponding to the nth review test event; and using the comprehensive mastery degree P to represent the current memory retention rate in the memory curve model.

[0107] In the embodiment, there are a plurality of memory curve models available, and a step function model is used in the embodiment. The memory curve model is:

[0108]

[0109] wherein R(t) is the memory retention rate after experiencing the learning event, i.e., the proportion of memory; t is the time, which can be in units of hours or days; and S is the memory strength, which is a constant related to the memory material and the individual memory ability, and is usually referred to as the memory strength or the memory stability.

[0110] wherein the comprehensive mastery degree P is used to represent the current memory retention rate in the memory curve model, and the comprehensive mastery degree P and the corresponding time interval t are input into the above model to calculate the memory strength S.

[0111] Here, the memory strength S at the ith review test event is taken as an example. i For example, the output of the memory strength is:

[0112] S i = -t i / ln(P i ); wherein i is the ith review test event, and i is a positive integer greater than or equal to 2; S i is the memory strength corresponding to the ith review test event; P i is the comprehensive mastery degree of the ith review test event; and t iThe time interval from the end of the i-1th review test event to the start of the ith review test event.

[0113] Regarding the above formula, for example, when i = 3, S3 = -t3 / ln(P3), that is, the memory strength of the third review test event is determined by the comprehensive mastery degree P at the third review test event and the time interval t3 between the second review test event and the third review test event.

[0114] Preferably, the step of performing time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event to obtain the recommended interval length of the (n+1)th review test event comprises:

[0115] Based on the memory curve model, the preset memory retention rate R and the memory strength S corresponding to the nth review test event are taken as inputs, and time information analysis is performed in the memory curve model to obtain the recommended interval length of the (n+1)th review test event.

[0116] It can be understood that, regarding the memory curve model, the same memory curve model as in the above scheme can be used, or another memory curve model can be used according to the scene needs. In the present embodiment, the same memory curve model as in the foregoing scheme is preferably used, that is:

[0117]

[0118] The preset memory retention rate R and the current memory strength S obtained according to the foregoing scheme are taken as inputs and substituted into the above memory curve model to obtain the output of the recommended interval length of the next review test event. Here, the ith learning event is still taken as an example to explain that the above S i = -t i / ln(P i ) and the preset memory retention rate R are input into the above model formula to obtain the following output:

[0119]

[0120] Wherein: t i is the time interval from the i-1th review test event to the ith review test event; t i+1 is the time interval from the ith review test event to the (i+1)th review test event; R is the preset memory retention rate; P i is the comprehensive mastery degree of the ith review test event.

[0121] It is worth mentioning that in the embodiment, an initial learning event is further included before the start of the review test event. After the completion of the initial learning event, the time node of learning the relevant knowledge point is recorded, which is assumed to be represented by q. By using the memory curve model mentioned above and assuming that R1=50% and S1=2, the interval time t1=1.3862 from the end of the initial learning event to the start of the first review test event can be obtained, that is, the time node of the first review test event can be obtained as q+t1.

[0122] As shown in Figure 2 , the embodiment of the present application further provides a learning planning device, which comprises:

[0123] The first acquisition module 101 is configured to acquire the correct rates of the knowledge points in each evaluation dimension corresponding to the nth review test event, wherein n is a positive integer greater than or equal to 2.

[0124] The fusion module 102 is configured to fuse the correct rates according to the importance of each evaluation dimension to obtain a comprehensive mastery degree P corresponding to the nth review test event.

[0125] The calling module 103 is configured to call a time interval t n , wherein the time interval t n is the time difference between the end time corresponding to the (n-1)th review test event and the start time corresponding to the nth review test event.

[0126] The analysis module 104 is configured to perform memory capacity analysis processing based on the comprehensive mastery degree P and the time interval t n to obtain a memory strength S corresponding to the nth review test event.

[0127] The second acquisition module 105 is configured to acquire a preset memory retention rate R, wherein the preset memory retention rate R is a memory retention rate target value set by the user.

[0128] The conversion module 106 is configured to perform time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event to obtain a recommended interval duration of the (n+1)th review test event.

[0129] Optionally, the first acquisition module 101 comprises:

[0130] The first acquisition sub-module is configured to acquire the current evaluation items, wherein each evaluation item contains a respective evaluation dimension.

[0131] The second acquisition sub-module is configured to acquire the corresponding evaluation dimension based on the current evaluation items as the current evaluation dimension.

[0132] The third obtaining sub-module is configured to classify and extract the result of the nth review test event according to the current evaluation dimension, and obtain the correct rate corresponding to each evaluation dimension.

[0133] Optionally, in the device, the evaluation items include skill modal items and / or difficulty level items.

[0134] Optionally, in the device, when the evaluation items include skill modal items, the first obtaining module 101 includes:

[0135] The fourth obtaining sub-module is configured to obtain the correct rate corresponding to each evaluation dimension of the knowledge point in the nth review test event in listening, speaking, reading and writing;

[0136] The fusion module 102 includes:

[0137] The first fusion sub-module is configured to fuse the correct rates according to the importance of each evaluation dimension of listening, speaking, reading and writing, and obtain the comprehensive mastery degree P corresponding to the nth review test event.

[0138] Optionally, in the device, when the evaluation items include difficulty level items, the difficulty level items include evaluation dimensions of difficult questions, medium questions and easy questions; the first obtaining module 101 includes:

[0139] The fifth obtaining sub-module is configured to obtain the correct rate corresponding to each evaluation dimension of the knowledge point in the nth review test event in difficult questions, medium questions and easy questions;

[0140] The fusion module 102 includes:

[0141] The second fusion sub-module is configured to fuse the correct rates according to the importance of each evaluation dimension of difficult questions, medium questions and easy questions, and obtain the comprehensive mastery degree P corresponding to the nth review test event.

[0142] Optionally, in the device, the nth review test event includes an initial test stage and a wrong question correction stage; the first obtaining module 101 includes:

[0143] The sixth obtaining sub-module is configured to obtain the total number of questions in the initial test stage, the number of correct questions in the initial test stage and the number of correct questions in the wrong question correction stage corresponding to each evaluation dimension in the nth review test event.

[0144] The seventh obtaining sub-module is configured to fuse the number of correct questions in the wrong question correction stage and the number of correct questions in the initial test stage in the same evaluation dimension to obtain the comprehensive number of correct questions, and obtain the correct rate of the corresponding evaluation dimension based on the ratio of the comprehensive number of correct questions to the total number of questions in the initial test stage.

[0145] a summary module configured to summarize the calculation results of the respective evaluation dimensions to obtain the accuracy rates of the respective evaluation dimensions.

[0146] Optionally, the device further comprises:

[0147] an input module configured to accept the weight distribution coefficients respectively confirmed by the user for the respective evaluation dimensions;

[0148] a weighting module configured to take the respective weight distribution coefficients as the importance of the corresponding evaluation dimensions.

[0149] Optionally, the analysis module 104 comprises:

[0150] a calling module configured to call a memory curve model, the memory curve model being a function of the associated memory retention rate, memory strength and time;

[0151] a first processing module configured to take the comprehensive mastery degree P and the time interval t as inputs to perform memory capacity analysis in the memory curve model to obtain the memory strength S corresponding to the nth review test event; wherein the comprehensive mastery degree P represents the current memory retention rate in the memory curve model.

[0152] Optionally, the conversion module 106 comprises:

[0153] a second processing module configured to take the preset memory retention rate R and the memory strength S corresponding to the nth review test event as inputs to perform time information analysis in the memory curve model based on the memory curve model to obtain the recommended interval duration of the (n+1)th review test event.

[0154] The learning planning device provided by the embodiments of the present application can implement the respective processes in the method embodiments and achieve the same technical effects. To avoid repetition, the technical analysis and technical effects will not be described here.

[0155] The embodiments of the present application further provide a computer readable storage medium, and the computer readable storage medium stores a computer program, the computer program is executed by a processor to implement the steps in the learning planning method provided by the embodiments of the present application, and the related steps comprise:

[0156] obtaining the accuracy rates of the respective evaluation dimensions of the knowledge points corresponding to the nth review test event, wherein n is a positive integer greater than or equal to 2;

[0157] fusing the respective accuracy rates according to the importance of the respective evaluation dimensions to obtain the comprehensive mastery degree P corresponding to the nth review test event;

[0158] obtaining the time interval t nwherein the time interval t n is a time difference between an end time corresponding to the (n-1)th review test event and a start time corresponding to the nth review test event;

[0159] based on the comprehensive mastery degree P and the time interval t n performing a memory capacity analysis process to obtain a memory strength S corresponding to the nth review test event;

[0160] obtaining a preset memory retention rate R, wherein the preset memory retention rate R is a memory retention rate target value set by the user;

[0161] based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event, performing a time information conversion process to obtain a recommended interval duration of the (n+1)th review test event.

[0162] Optionally, the step of obtaining the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event comprises:

[0163] obtaining a current evaluation item, wherein each evaluation item contains a respective evaluation dimension;

[0164] based on the current evaluation item, obtaining a corresponding evaluation dimension as a current evaluation dimension;

[0165] according to the current evaluation dimension, classifying and extracting the result of the nth review test event to obtain a correct rate corresponding to each evaluation dimension.

[0166] Optionally, the evaluation item includes a skill modal item and / or a difficulty level item.

[0167] Optionally, when the evaluation item includes a skill modal item, the skill modal item contains evaluation dimensions of listening, speaking, reading, and writing; and the step of obtaining the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event comprises:

[0168] obtaining a respective correct rate of the knowledge point corresponding to the nth review test event in the evaluation dimensions of listening, speaking, reading, and writing;

[0169] The step of fusing each correct rate according to the importance of each evaluation dimension to obtain a comprehensive mastery degree P corresponding to the nth review test event comprises:

[0170] fusing each correct rate according to the importance of each evaluation dimension of listening, speaking, reading, and writing to obtain a comprehensive mastery degree P corresponding to the nth review test event.

[0171] Optionally, when the evaluation items include hierarchical difficulty items, the hierarchical difficulty items include evaluation dimensions of difficult questions, medium questions and easy questions; the step of obtaining the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event includes:

[0172] obtaining the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event;

[0173] The step of fusing each correct rate according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P corresponding to the nth review test event includes:

[0174] fusing each correct rate according to the importance of each evaluation dimension of difficult questions, medium questions and easy questions to obtain the comprehensive mastery degree P corresponding to the nth review test event.

[0175] Optionally, the nth review test event includes an initial test stage and a wrong question correction stage; the step of obtaining the correct rate of each evaluation dimension of the knowledge point corresponding to the nth review test event includes:

[0176] obtaining the total number of questions in the initial test stage, the number of correct questions in the initial test stage and the number of correct questions in the wrong question correction stage of each evaluation dimension in the nth review test event;

[0177] In the same evaluation dimension, fuse the number of correct questions in the wrong question correction stage and the number of correct questions in the initial test stage to obtain the comprehensive number of correct questions, and obtain the correct rate of the corresponding evaluation dimension based on the ratio of the comprehensive number of correct questions to the total number of questions in the initial test stage;

[0178] Summarize the calculation results of each evaluation dimension to obtain the correct rate of each evaluation dimension.

[0179] Optionally, before the step of fusing each correct rate according to the importance of each evaluation dimension, it includes:

[0180] accepting the weight distribution coefficient confirmed by the user for each evaluation dimension respectively;

[0181] use each weight distribution coefficient as the importance of the corresponding evaluation dimension.

[0182] Optionally, the step of obtaining the memory strength S corresponding to the nth review test event based on the comprehensive mastery degree P and the time interval t n performing memory capability analysis processing to obtain the memory strength S corresponding to the nth review test event includes:

[0183] calling a memory curve model, the memory curve model being a function of associative memory retention rate, memory strength and time;

[0184] The comprehensive mastery degree P and the time interval t are taken as inputs, memory capacity analysis is performed in the memory curve model, and the memory strength S corresponding to the nth review test event is obtained; wherein, the comprehensive mastery degree P represents the current memory retention rate in the memory curve model.

[0185] Optionally, the step of performing time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event to obtain the recommended interval duration of the (n+1)th review test event, comprises:

[0186] Based on the memory curve model, the preset memory retention rate R and the memory strength S corresponding to the nth review test event are taken as inputs, time information analysis is performed in the memory curve model, and the recommended interval duration of the (n+1)th review test event is obtained.

[0187] The embodiments of the present application can realize each process in the above-mentioned method embodiments, and can achieve the same technical effects. To avoid repetition, the technical analysis and technical effects will not be described here.

[0188] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The computer readable storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM).

[0189] As shown in Figure 3 The embodiments of the present application also relate to an electronic device 10, which includes a processor 12. The processor 12 can execute any one of the above-mentioned learning planning methods.

[0190] Specifically, the electronic device 10 includes a processor 12, a memory 11, and a computer program of the learning planning method stored in the memory 11 and capable of running on the processor 12. The processor 12 runs the computer program of the learning planning method in the memory 11.

[0191] The above disclosure is only the preferred embodiments of the present application, and of course cannot limit the scope of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope of the present application.

Claims

1. A learning planning method characterized by, The method comprises: obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the nth review test event, wherein n is a positive integer greater than or equal to 2; fusing each correct rate according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P corresponding to the nth review test event; calling the time interval tn, wherein the time interval tn is the time difference between the end time corresponding to the (n-1)th review test event and the start time corresponding to the nth review test event; performing memory capacity analysis processing based on the comprehensive mastery degree P and the time interval tn to obtain the memory strength S corresponding to the nth review test event; obtaining a preset memory retention rate R, wherein the preset memory retention rate R is a memory retention rate target value set by the user; performing time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the nth review test event to obtain the recommended interval duration of the (n+1)th review test event.

2. The learning planning method of claim 1, wherein, The step of obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the nth review test event comprises: obtaining the current evaluation item, wherein each evaluation item contains its own evaluation dimension; obtaining the corresponding evaluation dimension based on the current evaluation item as the current evaluation dimension; classifying and extracting the results of the nth review test event according to the current evaluation dimension to obtain the correct rate corresponding to each evaluation dimension.

3. The learning planning method of claim 2, wherein, The evaluation item includes a skill modal item and / or a difficulty level item.

4. The learning planning method of claim 3, wherein, When the evaluation item includes a skill modal item, the skill modal item contains the evaluation dimensions of listening, speaking, reading, and writing. The step of obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the nth review test event comprises: obtaining the correct rate corresponding to each evaluation dimension of listening, speaking, reading, and writing of the knowledge point corresponding to the nth review test event; The step of fusing each correct rate according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P corresponding to the nth review test event comprises: fusing each correct rate according to the importance of each evaluation dimension of listening, speaking, reading, and writing to obtain the comprehensive mastery degree P corresponding to the nth review test event.

5. The learning planning method of claim 3, wherein, When the evaluation item includes a difficulty level item, the difficulty level item contains the evaluation dimensions of difficult questions, medium questions, and easy questions; the step of obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the nth review test event comprises: obtaining the correct rate corresponding to each evaluation dimension of difficult questions, medium questions, and easy questions of the knowledge point corresponding to the nth review test event; The step of fusing each correct rate according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P corresponding to the nth review test event comprises: fusing each correct rate according to the importance of each evaluation dimension of difficult questions, medium questions, and easy questions to obtain the comprehensive mastery degree P corresponding to the nth review test event.

6. The learning planning method of claim 1, wherein, The n-th review test event includes an initial test stage and a wrong question revision stage; the step of obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the n-th review test event comprises: Obtaining the total number of questions in the initial test stage, the number of correct questions in the initial test stage, and the number of correct questions in the wrong question revision stage corresponding to each evaluation dimension in the n-th review test event; In the same evaluation dimension, the number of correct questions in the wrong question revision stage and the number of correct questions in the initial test stage are fused to obtain the comprehensive number of correct questions, and the correct rate of the corresponding evaluation dimension is obtained based on the ratio of the comprehensive number of correct questions to the total number of questions in the initial test stage; The calculation results of each evaluation dimension are summarized to obtain the correct rate of each evaluation dimension.

7. The learning planning method of claim 1, wherein, Before the step of fusing each correct rate according to the importance of each evaluation dimension, the step comprises: Accepting the weight distribution coefficient confirmed by the user for each evaluation dimension respectively; Each weight distribution coefficient is used as the importance of the corresponding evaluation dimension.

8. The learning planning method according to any one of claims 1 to 7, characterized by, The step of performing memory capacity analysis processing based on the comprehensive mastery degree P and the time interval tn to obtain the memory strength S corresponding to the n-th review test event comprises: Calling a memory curve model, the memory curve model being a function of associated memory retention rate, memory strength, and time; The comprehensive mastery degree P and the time interval t are used as inputs to perform memory capacity analysis in the memory curve model to obtain the memory strength S corresponding to the n-th review test event; wherein the comprehensive mastery degree P represents the current memory retention rate in the memory curve model.

9. The learning planning method of claim 8, wherein, The step of performing time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the n-th review test event to obtain the recommended interval duration of the n+1-th review test event comprises: Based on the memory curve model, the preset memory retention rate R and the memory strength S corresponding to the n-th review test event are used as inputs to perform time information analysis in the memory curve model to obtain the recommended interval duration of the n+1-th review test event.

10. A learning planning apparatus characterized by comprising: The device comprises: A first obtaining module for obtaining the correct rate of each evaluation dimension corresponding to the knowledge point of the n-th review test event, wherein n is a positive integer greater than or equal to two; A fusion module for fusing each correct rate according to the importance of each evaluation dimension to obtain the comprehensive mastery degree P corresponding to the n-th review test event; A calling module for calling the time interval tn, wherein the time interval tn is the time difference between the end time of the n-1-th review test event and the start time of the n-th review test event; An analysis module for performing memory capacity analysis processing based on the comprehensive mastery degree P and the time interval tn to obtain the memory strength S corresponding to the n-th review test event; A second obtaining module for obtaining a preset memory retention rate R, wherein the preset memory retention rate R is a memory retention rate target value set by the user; The conversion module is configured to perform time information conversion processing based on the preset memory retention rate R and the memory strength S corresponding to the n-th review test event, to obtain a recommended interval duration of an (n+1)-th review test event.

Images