A topic recommendation method, device and equipment

Abstract

This application relates to a method, device, and apparatus for recommending questions. The method includes: selecting a first question from candidate questions for a target knowledge point and recommending it for answer; if the first question is answered incorrectly, querying the preceding knowledge points of the target knowledge point; and recommending a second question based on the candidate questions for the preceding knowledge points. The solution provided by this application can effectively recommend personalized practice questions to users, while reducing the cost of creating questions.

Description

Technical Field

[0001] The present application relates to the field of educational technology, and in particular to a method, device and equipment for recommending a topic. Background Art

[0002] In a teacher-led teaching system, question-setting strategies are mainly determined by the syllabus, knowledge system, and the teacher's personal experience and ideas. Currently, there are mainly "one-to-many" and "one-to-one" teaching models.

[0003] In one-to-many instruction, teachers primarily determine their question-setting strategies based on the syllabus and knowledge base. They also regularly review previous knowledge points based on the learning and forgetting patterns of most students. In this teaching model, teachers assign the same exercises to all students, but each student's learning ability and grasp of various knowledge points vary. This prevents each student from conducting targeted practice based on their individual learning situation. In one-on-one instruction, teachers develop personalized question-setting strategies based on students' learning progress, learning ability, and classroom performance. However, this comes at a high cost and relies heavily on the teacher's teaching ability. Summary of the Invention

[0004] In order to overcome the problems existing in the related art, the present application provides a question recommendation method, device and computer equipment, which can automatically push personalized practice questions to users based on their historical behavior performance, and the question setting cost is also effectively reduced.

[0005] The first aspect of the present application provides a topic recommendation method, comprising:

[0006] From the candidate questions for the target knowledge point, select the first question to recommend for answering;

[0007] If there is an incorrect answer to the first question, query the preceding knowledge points of the target knowledge point;

[0008] Based on the candidate questions of the previous knowledge point, a second question is recommended for answering.

[0009] In one embodiment, the number of the preceding knowledge point is at least one, and the step of recommending a second question to answer based on the candidate questions of the preceding knowledge point includes:

[0010] Obtaining the historical answer accuracy rate of each of the preceding knowledge points;

[0011] From each of the preceding knowledge points, searching for associated knowledge points whose historical answer accuracy is less than a first threshold;

[0012] When the associated knowledge point is found, a second question is selected from the candidate questions of the associated knowledge point and the candidate questions of the target knowledge point for recommendation to answer.

[0013] In one embodiment, when the associated knowledge point is found, selecting a second question from the candidate questions of the associated knowledge point and the candidate questions of the target knowledge point for recommendation for answering includes:

[0014] If the number of the related knowledge points found is greater than a second threshold, the related knowledge points found are screened according to a set first priority to obtain retained knowledge points;

[0015] Selecting a first number of second questions from the candidate questions with retained knowledge points;

[0016] A second number of second questions are selected from the candidate questions for the target knowledge point.

[0017] In one embodiment, when the associated knowledge point is found, selecting a second question from the candidate questions of the associated knowledge point and the candidate questions of the target knowledge point for recommendation for answering includes:

[0018] If the number of the related knowledge points found is less than or equal to the second threshold, the values ​​of the third number and the fourth number are determined according to the number of wrong answers and / or the correct answer rate of the first question;

[0019] Selecting the third number of second questions from the candidate questions of the associated knowledge points;

[0020] The fourth number of second questions are selected from the candidate questions for the target knowledge point.

[0021] In one embodiment, after searching for related knowledge points whose historical answer accuracy is less than a first threshold value from each of the preceding knowledge points, the method further includes:

[0022] In the case that the related knowledge point is not found, a second question is selected from the candidate questions of the target knowledge point and recommended for answering.

[0023] In one embodiment, after recommending a second question to answer based on the candidate questions of the preceding knowledge point, the method further includes:

[0024] sorting the target knowledge point and adjacent knowledge points learned before the target knowledge point according to a second priority to obtain a consolidation knowledge point;

[0025] Based on the candidate questions for consolidating the knowledge points, questions are recommended for answering.

[0026] In one embodiment, before selecting a first question from candidate questions for the target knowledge point for recommendation for answering, the method further includes:

[0027] Using the knowledge points that were not answered or not recommended in the first round of question recommendation process as the target knowledge points in the first round of question recommendation process;

[0028] Alternatively, the target knowledge points in the second round of question-pushing process are determined based on the knowledge points answered incorrectly in the first round of question-pushing process;

[0029] Alternatively, the knowledge points that were not answered in the second round of question deduction process are used as the target knowledge points in the second round of question deduction process.

[0030] In one embodiment, there are multiple target knowledge points, and selecting a first question from candidate questions for the target knowledge point for recommendation as an answer includes:

[0031] Grouping the target knowledge points according to the historical correct answer rate of each target knowledge point in the first round of question-pushing process;

[0032] Selecting a group of the first questions from the candidate questions for each target knowledge point in the same group;

[0033] Recommend answers to the first question for each group.

[0034] A second aspect of the present application provides a topic recommendation device, comprising:

[0035] An acquisition module is used to select the first question from the candidate questions of the target knowledge point and recommend it for answering;

[0036] A query module, configured to query the preceding knowledge points of the target knowledge point if there is an incorrect answer to the first question;

[0037] The recommendation module is used to recommend a second question to answer based on the candidate questions of the previous knowledge point.

[0038] In one embodiment, the number of the preceding knowledge point is at least one, and the recommendation module includes:

[0039] A first acquiring unit is used to acquire the historical answer accuracy rate of each of the preceding knowledge points;

[0040] a query unit, configured to query, from each of the preceding knowledge points, related knowledge points whose historical answer accuracy is less than a first threshold;

[0041] The second recommendation unit is used to select the second question from the candidate questions of the associated knowledge point and the candidate questions of the target knowledge point for recommendation for answering when the associated knowledge point is found.

[0042] In one embodiment, the second recommendation unit is configured to:

[0043] If the number of the related knowledge points found is greater than a second threshold, the related knowledge points found are screened according to a set first priority to obtain retained knowledge points;

[0044] Selecting a first number of second questions from the candidate questions with retained knowledge points;

[0045] A second number of second questions are selected from the candidate questions for the target knowledge point.

[0046] In one embodiment, the second recommendation unit is configured to:

[0047] If the number of the related knowledge points found is less than or equal to the second threshold, the values ​​of the third number and the fourth number are determined according to the number of wrong answers and / or the correct answer rate of the first question;

[0048] Selecting the third number of second questions from the candidate questions of the associated knowledge points;

[0049] The fourth number of second questions are selected from the candidate questions for the target knowledge point.

[0050] In one embodiment, the query unit is configured to:

[0051] In the case that the related knowledge point is not found, a second question is selected from the candidate questions of the target knowledge point and recommended for answering.

[0052] In one embodiment, the recommendation module includes:

[0053] A second acquisition unit is configured to sort the target knowledge point and adjacent knowledge points learned before the target knowledge point according to a second priority to obtain a consolidated knowledge point;

[0054] The third recommendation unit is used to recommend questions for answering based on the candidate questions for consolidating the knowledge points.

[0055] In one embodiment, the acquisition module is used to:

[0056] Using the knowledge points that were not answered or not recommended in the first round of question recommendation process as the target knowledge points in the first round of question recommendation process;

[0057] Alternatively, the target knowledge points in the second round of question-pushing process are determined based on the knowledge points answered incorrectly in the first round of question-pushing process;

[0058] Alternatively, the knowledge points that were not answered in the second round of question deduction process are used as the target knowledge points in the second round of question deduction process.

[0059] In one embodiment, there are multiple target knowledge points, and the acquisition module includes:

[0060] A grouping unit, configured to group the target knowledge points according to the historical correct answer rate of each target knowledge point in the first round of question-pushing process;

[0061] a topic selection unit, configured to select a group of the first topics from candidate topics for each of the target knowledge points in the same group;

[0062] The first recommendation unit is used to recommend answers to the first questions in each group respectively.

[0063] A third aspect of the present application provides an electronic device, including:

[0064] processor; and

[0065] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method described above.

[0066] A fourth aspect of the present application provides a non-temporary computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method described above.

[0067] The technical solution provided by this application may have the following beneficial effects:

[0068] The technical solution of this application first selects the first question from the candidate questions of the target knowledge point and recommends it for answering; if there is an error in the answer to the first question, the preceding knowledge point of the target knowledge point is queried; based on the candidate questions of the preceding knowledge point, the second question is recommended for answering. That is, based on the user's answer to the first question recommended for the target knowledge point, if the answer is wrong, the second question is recommended to the user for answering. In this way, the user's mastery of knowledge points can be evaluated and analyzed based on the user's historical learning behavior, and personalized exercises can be recommended to the user based on the user's learning ability, learning progress, and mastery of each knowledge point. This method of recommending questions can not only ensure that the differences between different users are fully considered and teaching students in accordance with their aptitude, but also greatly reduce labor costs, so that personalized review strategies can be applied on a large scale.

[0069] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail the exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0071] Figure 1 1 is a flowchart of a method for recommending a topic according to an embodiment of the present application;

[0072] Figure 2 is another flowchart of the topic recommendation method shown in an embodiment of the present application;

[0073] Figure 3 1 is a flowchart of the first round of topic recommendation method according to an embodiment of the present application;

[0074] Figure 4 This is a flow chart of the wrong question practice part of the question recommendation method shown in the embodiment of the present application;

[0075] Figure 5 1 is a flowchart of the second round of topic recommendation of the topic recommendation method shown in the embodiment of the present application;

[0076] Figure 6 Schematic diagram of the structure of the topic recommendation device shown in an embodiment of the present application;

[0077] Figure 7 is another structural diagram of the topic recommendation device shown in an embodiment of the present application;

[0078] Figure 8 It is a structural diagram of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0079] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to make the present application more thorough and complete and to fully convey the scope of the present application to those skilled in the art.

[0080] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0081] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0082] In the field of educational technology, teachers create exercises for students based on the syllabus, knowledge system, and personal experience and teaching philosophy. In one-to-many teaching, teachers give the same exercises to all students, which fails to take into account individual differences in students' learning abilities and their mastery of various knowledge points. In one-to-one teaching, although teachers can create special exercises based on students' specific situations, the cost of creating exercises is high and depends on the teacher's teaching ability.

[0083] In response to the above problems, an embodiment of the present application provides a question recommendation method that can effectively recommend personalized exercises to users.

[0084] The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0085] Figure 1 It is a flowchart of the topic recommendation method shown in an embodiment of the present application.

[0086] See also Figure 1 , an embodiment of the topic recommendation method in the embodiment of the present application includes:

[0087] Step 101: Select the first question from the candidate questions of the target knowledge point and recommend it for answering.

[0088] Since the present application involves one or more rounds of topic-pushing processes, the steps involved in each round of topic-pushing processes may be the same or different.

[0089] The following uses the two-round problem-solving process as an example to illustrate that the target knowledge points can be obtained in the following possible ways:

[0090] Using the knowledge points that were not answered or not recommended in the first round of question recommendation process as the target knowledge points in the first round of question recommendation process;

[0091] Alternatively, the target knowledge points in the second round of question-pushing process are determined based on the knowledge points answered incorrectly in the first round of question-pushing process;

[0092] Alternatively, the knowledge points that were not answered in the second round of question deduction process are used as the target knowledge points in the second round of question deduction process.

[0093] Here, the candidate questions can be understood as a number of exercises related to the target knowledge point, wherein each knowledge point can be configured with multiple exercises. The first question is a fixed number of questions, for example, 3, randomly selected from the multiple exercises corresponding to the target knowledge point as the exercises for the target knowledge point.

[0094] In this step, when there are multiple target knowledge points, the first question is selected from the candidate questions for the target knowledge points and recommended for answering. Alternatively, the multiple target knowledge points can be grouped according to the historical answer accuracy rate of each target knowledge point in the first round of question recommendation process; a group of the first questions is selected from the candidate questions for each target knowledge point in the same group; and the first questions in each group are recommended for answering.

[0095] Here, when there are multiple target knowledge points, it mainly refers to the second round of question-pushing process. The multiple can be a multiple of a fixed number, and the fixed number is the number of questions contained in each group. For example, if the fixed number is 3, then the multiple can be: 3 questions, 6 questions. After the target knowledge points are grouped, for the knowledge points in each group, each knowledge point selects a question from the candidate questions to form the first question. For example, if there are 3 knowledge points in a group, then 3 questions are selected from the question bank as practice questions.

[0096] In summary, it can be seen that the composition of the first question can include two situations. The first situation: for a certain target knowledge point, a fixed number of practice questions are randomly selected from the candidate questions at one time; the second situation: for a fixed number of knowledge points in a group, one question is randomly selected from the corresponding candidate questions for each knowledge point, and the number of practice questions corresponding to the knowledge points in the group is composed.

[0097] Step 102: If there is an incorrect answer to the first question, query the preceding knowledge points of the target knowledge point.

[0098] In this step, the preceding knowledge points of the target knowledge point can be determined by sorting the knowledge points according to their difficulty level, or can be determined according to the progress of the syllabus. For example, if the target knowledge point is "two-digit calculation problems", then its preceding knowledge point is "one-digit calculation problems".

[0099] Step 103: Recommend a second question to answer based on the candidate questions of the previous knowledge point.

[0100] In this step, the second question is also an exercise question selected from the candidate questions of the relevant knowledge point, and its composition also includes several situations. The first situation is: directly selecting a fixed number of exercise questions from the candidate questions related to the target knowledge point; the second situation is: combining the previous knowledge point and the target knowledge point to determine the second question. According to the ratio of the number of exercise questions selected from the candidate questions corresponding to the previous knowledge point and the target knowledge point, the composition of the second question can include the following three types: (1) previous knowledge point: previous knowledge point: target knowledge point = 1:1:1; (2) previous knowledge point: target knowledge point = 2:1; (3) previous knowledge point: target knowledge point = 1:2.

[0101] It should be noted that the ratio here is the ratio of the number of questions.

[0102] In this step, the specific implementation steps may be:

[0103] S1: Obtain the historical answer accuracy rate of each of the preceding knowledge points;

[0104] S2: From each of the preceding knowledge points, searching for related knowledge points whose historical answer accuracy is less than the first threshold;

[0105] S3: When the associated knowledge point is found, the second question is selected from the candidate questions of the associated knowledge point and the candidate questions of the target knowledge point for recommendation for answering. There are two situations in which the associated knowledge point is found: (1) If the associated knowledge point found is greater than the second threshold, the associated knowledge points found are filtered according to the set first priority to obtain the retained knowledge points; the first number of second questions are selected from the candidate questions of the retained knowledge points; and the second number of second questions are selected from the candidate questions of the target knowledge points. (2) If the number of the associated knowledge points found is less than or equal to the second threshold, the values ​​of the third and fourth numbers are determined based on the number of wrong questions and / or the correct answer rate of the first question; the third number of second questions are selected from the candidate questions of the associated knowledge point; and the fourth number of second questions are selected from the candidate questions of the target knowledge point.

[0106] With respect to step S2, when the related knowledge point is not found, a second question is selected from the candidate questions of the target knowledge point and recommended for answering.

[0107] In the above steps, the historical answer accuracy rate can be the three-star rate of the user's score, that is, the user score includes 1 star, 2 stars and 3 stars. The three-star rate is the ratio of the number of three stars obtained when the user answers the exercises related to the previous knowledge point to the total number of answers. For example, the user has done a total of 10 exercises in the previous knowledge point, and 7 of them have received 3 stars, then the historical answer accuracy rate is 0.7. The first priority set is: absence > low three-star rate > high difficulty, that is, first query the knowledge points where the absence is first, then query the knowledge points with low three-star rate, and finally query the knowledge points with high difficulty.

[0108] In the above steps, the sum of the first quantity and the second quantity is the same as the sum of the third quantity and the fourth quantity.

[0109] After the above step 103, in the case that the target knowledge point is not the first knowledge point in the syllabus, the present application also involves a step of consolidating exercises on relevant knowledge points, and the steps may be: sorting the target knowledge point and the adjacent knowledge points learned before the target knowledge point according to the set first priority to obtain a consolidated knowledge point; and recommending questions for answering based on the candidate questions of the consolidated knowledge point.

[0110] The technical solution of this application first selects the first question from the candidate questions of the target knowledge point and recommends it for answering; if there is an error in the answer to the first question, the preceding knowledge point of the target knowledge point is queried; based on the candidate questions of the preceding knowledge point, the second question is recommended for answering. That is, based on the user's answer to the first question recommended for the target knowledge point, if the answer is wrong, the second question is recommended to the user for answering. In this way, the user's mastery of knowledge points can be evaluated and analyzed based on the user's historical learning behavior, and personalized exercises can be recommended to the user based on the user's learning ability, learning progress, and mastery of each knowledge point. This method of recommending questions can not only ensure that the differences between different users are fully considered and teaching students in accordance with their aptitude, but also greatly reduce labor costs, so that personalized review strategies can be applied on a large scale.

[0111] For ease of understanding, an application example of the topic recommendation method is provided below for illustration.

[0112] Figure 2 This is another flowchart of the topic recommendation method shown in an embodiment of the present application.

[0113] See also Figure 2 , an embodiment of the topic recommendation method in the embodiment of the present application includes:

[0114] Step 201: Use the knowledge points that were not answered or not recommended in the first round of question recommendation process as the target knowledge points in the first round of question recommendation process.

[0115] In this step, the target knowledge point is a knowledge point that the user has not learned yet, and the unanswered questions may include the remedial lessons for the knowledge points before the target knowledge point. The knowledge points for which no questions are recommended are the knowledge points that the user is about to learn. The first round of question recommendation is mainly to enable users to learn all the knowledge points required by the syllabus. Relatively speaking, the second round of question recommendation is to further consolidate and improve the relevant knowledge points based on the user's answers in the first round. In terms of class schedule, each class learns one knowledge point, and each class includes two rounds of question recommendation processes.

[0116] Step 202: Select the first question from the candidate questions for the target knowledge point and recommend it for answering.

[0117] In this step, during the first round of the recommendation process, the learning and tutoring system randomly selects three questions from the candidate questions related to the target knowledge point as the practice questions for the new question practice section. The learning and tutoring system is the application system of the method described in this application, which includes a question bank of candidate questions, a question recommendation program, and related hardware equipment.

[0118] It is worth noting that the above steps 201-202 are mainly new question practice parts.

[0119] Step 203: If there is an incorrect answer to the first question, query the preceding knowledge points of the target knowledge point.

[0120] In this step, the preceding knowledge points of the target knowledge point are searched to take into account the possibility that the user may make mistakes while practicing the target knowledge point, which may indicate a lack of grasp of the preceding knowledge points. Therefore, strengthening the study of the preceding knowledge points will help reduce the error rate when practicing the target knowledge point. If the target knowledge point has no preceding knowledge points, the learning and tutoring system will directly recommend three exercises related to the target knowledge point to the user.

[0121] Step 204: Obtain the historical answer accuracy rate of each of the preceding knowledge points.

[0122] Step 205: From each of the preceding knowledge points, query the associated knowledge points whose historical answer accuracy is less than a first threshold.

[0123] In this step, the first threshold can be 0.8. For example, if the user received three stars on 8 of the 10 practice questions for the previous knowledge point, if the user received fewer than 8 three-star questions, the previous knowledge point will be considered a related knowledge point. If the historical answer accuracy rate for the previous knowledge point is greater than 0.8, it is considered that the previous knowledge point does not need to be re-practiced, and the learning tutoring system will directly recommend 3 practice questions related to the target knowledge point to the user.

[0124] Step 206: When the associated knowledge point is found, the second question is selected from the candidate questions of the associated knowledge point and the candidate questions of the target knowledge point for recommendation as an answer.

[0125] In this step, there are two situations in which the related knowledge points are found:

[0126] (1) When the number of related knowledge points found is greater than one, the related knowledge points found are screened according to the set first priority, with the knowledge points that are absent from the class being selected first, followed by the knowledge points with a low three-star rate, and finally the related knowledge points are selected based on the difficulty and ranking of the knowledge points, and two retained knowledge points are selected; then, one practice question is generated for each of the two retained knowledge points from the candidate questions for the two retained knowledge points; finally, one practice question is selected from the candidate questions for the target knowledge point. Based on the above process, a total of three practice questions are extracted as the second question.

[0127] (2) When the number of the related knowledge points found is less than or equal to 1, then for the target knowledge point, in the first round of question recommendation, if the number of wrong answers for the first question by the user is greater than 1 or the three-star rate is less than 0.8 in the second round, then from the candidate questions for the target knowledge point and the preceding knowledge point, 1 question is given for the target knowledge point and 2 questions are given for the preceding knowledge point. If the number of wrong answers for the first question by the user is less than 1 or the three-star rate is greater than 0.8 in the second round, then 2 questions are given for the target knowledge point and 1 question is given for the preceding knowledge point.

[0128] It is worth noting that the above steps 203-206 are mainly for practicing wrong questions. The specific process of question deduction can be referred to Figure 3. In order to understand the wrong question practice part more intuitively, a specific implementation process is shown below: Step 1. First, determine whether there is a previous knowledge point. If so, proceed to step 2, otherwise proceed to step 3. Step 2. Determine the user's total three-star rate (i.e., the correct rate, the user score is divided into 1 star, 2 stars, and 3 stars) on the previous knowledge point. If there is a previous knowledge point with a three-star rate less than 0.8, proceed to step 4, otherwise proceed to step 3. Step 3. Directly push 3 questions to the knowledge point and end the process. Step 4. If the number of previous knowledge points with a three-star rate less than 0.8 is greater than 1, select two knowledge points from them and ask a question each, giving priority to the knowledge points that are absent, and then choose the ones with a low three-star rate. Finally, select according to the difficulty and ranking of the knowledge points. Finally, ask a question for the current knowledge point Kn. End the process. If the number of previous indication singles (knowledge points) is equal to 1, proceed to step 5. Step 5. For the current knowledge point Kn, if the number of wrong questions is greater than 1 in the first round or the three-star rate is less than 0.8 in the second round, proceed to step 6, otherwise proceed to step 7. Step 6: Give one question for the current knowledge point Kn and two questions for the previous knowledge point, and then the process ends. Step 7: Give two questions for the current knowledge point and one question for the previous knowledge point.

[0129] Step 207: Sort the target knowledge point and adjacent knowledge points learned before the target knowledge point according to the second priority to obtain a consolidation knowledge point, and recommend questions for answering based on the candidate questions of the consolidation knowledge point.

[0130] This step mainly involves the consolidation practice part. If the target knowledge point is not the first knowledge point in the course being studied, then consolidation practice is required for the target knowledge point. Here, first, the target knowledge point and an adjacent knowledge point before the target knowledge point are sorted according to the set second priority of "absenteeism > low three-star rate > high difficulty", and then, based on the sorting results, from the candidate questions for high-priority and low-priority knowledge points, 2 practice questions are given for the high-priority knowledge points, and 1 practice question is given for the low-priority knowledge points. The second priority here may be the same as or different from the first priority in the above steps. In an embodiment of the present application, the second priority is the same as the first priority.

[0131] After the learning tutoring system recommends at least one question for both the target knowledge point and the preceding knowledge points, if the user hasn't answered the corresponding practice questions for a particular knowledge point, the user will need to make up for the missed practice questions. The process for this make-up practice is the same as in steps 201-207 above, but only includes the "New Question Practice" and "Wrong Question Practice" sections, without the "Consolidation Practice" section. After completing the make-up practice for all unanswered knowledge points, the second round of reasoning will begin, regardless of whether the user has answered them.

[0132] The above steps 201-207 can refer to Figure 4 That is, in the first round of question-pushing process, users will go through four parts: new question practice, wrong question practice, consolidation practice and make-up practice.

[0133] Step 208: Group the target knowledge points according to their historical answer accuracy rates in the first round of question-pushing process.

[0134] This step is mainly aimed at the second round of question-pushing process. If the user has answered the wrong knowledge points in the first round of question-pushing process, the learning guidance system will sort the wrongly answered knowledge points according to the historical answer accuracy rate (i.e., three-star rate) from low to high according to the three-star rate. If the wrongly answered knowledge points are less than a multiple of 3, all the knowledge points involved in the first round of question-pushing will be sorted from high to low according to the difficulty, and the wrongly answered knowledge points will be supplemented to meet the multiple of 3. That is, the number of knowledge points that need to be pushed in the second round of question-pushing process is a multiple of 3, among which the knowledge points that need to be pushed can all be the knowledge points with wrong answers in the first round, or they can be the knowledge points with wrong answers in the first round and other knowledge points with high difficulty.

[0135] Step 209: Select a group of the first questions from the candidate questions for each target knowledge point in the same group, and recommend answers to each group of the first questions.

[0136] In this step, the same group contains three knowledge points. The learning tutoring system selects one practice question from each candidate question corresponding to each of the three knowledge points to form a set of pushed practice questions. Users only need to practice one set of pushed practice questions in each class. Since the second round of pushed practice questions may include multiple groups of knowledge points, it may take multiple classes to complete the practice.

[0137] The above steps 208-209 can be found in Figure 5 In the second round of question recommendation, the user is first judged to determine whether they made any mistakes in the first round. Then, the knowledge points related to the wrong questions are ranked from low to high based on their three-star ratings. Knowledge points that did not make mistakes in the first round are excluded from the second round of question recommendation. Furthermore, the number of wrong knowledge points is determined. If the number is less than a multiple of three, additional points are added. Otherwise, the second round of knowledge point generation is terminated.

[0138] In the second round of group exercises, users may also answer incorrectly. Corresponding wrong-question exercises are required for the knowledge points with incorrect answers. The question-pushing process is the same as the wrong-question exercises in the first round, so I will not repeat it here.

[0139] After all the group exercises are completed, for the first round of question pushing, if there are still knowledge points that have not been answered in the new question practice part and the supplementary practice part, another supplementary practice will be required. The question pushing process is the same as the first round.

[0140] In an embodiment of the present application, the learning and tutoring system sets new question exercises, wrong question exercises, consolidation exercises and make-up exercises for the user according to the answer situation of the target knowledge points and the previous knowledge points learned by the user, so that the user can learn all the knowledge points according to his or her own learning situation. In order to enable the user to have a more solid grasp of all knowledge points, the learning and tutoring system also arranges further consolidation and improvement training for the user in case of wrong answers on all knowledge points. Since the entire question-setting process is automatically carried out by the learning and tutoring system, there is no need for the participation of teachers and teaching materials, thereby effectively reducing the cost of question-setting. In an embodiment of the present application, it can fully take into account the differences between different individuals and teach students in accordance with their aptitude, while making personalized review strategies available for large-scale application.

[0141] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a topic recommendation device, an electronic device and corresponding embodiments.

[0142] Figure 6 It is a structural diagram of a topic recommendation device shown in an embodiment of the present application.

[0143] See also Figure 6 The topic recommendation device includes: an acquisition module 61, a query module 62, and a recommendation module 63.

[0144] The acquisition module 61 is used to select a first question from the candidate questions of the target knowledge point and recommend it for answering.

[0145] The acquisition module 61 can use the knowledge points that were not answered or not recommended in the first round of question deduction process as the target knowledge points in the first round of question deduction process; or, determine the target knowledge points in the second round of question deduction process based on the knowledge points that were answered incorrectly in the first round of question deduction process; or, use the knowledge points that were not answered in the second round of question deduction process as the target knowledge points in the second round of question deduction process.

[0146] The query module 62 is used to query the preceding knowledge points of the target knowledge point when there is an incorrect answer to the first question.

[0147] The recommendation module 63 is used to recommend a second question to answer based on the candidate questions of the previous knowledge point.

[0148] The technical solution of this application first selects the first question from the candidate questions of the target knowledge point and recommends it for answering; if there is an error in the answer to the first question, the preceding knowledge point of the target knowledge point is queried; based on the candidate questions of the preceding knowledge point, the second question is recommended for answering. That is, based on the user's answer to the first question recommended for the target knowledge point, if the answer is wrong, the second question is recommended to the user for answering. In this way, the user's mastery of knowledge points can be evaluated and analyzed based on the user's historical learning behavior, and personalized exercises can be recommended to the user based on the user's learning ability, learning progress, and mastery of each knowledge point. This method of recommending questions can not only ensure that the differences between different users are fully considered and teaching students in accordance with their aptitude, but also greatly reduce labor costs, so that personalized review strategies can be applied on a large scale.

[0149] Figure 7 This is another structural diagram of the topic recommendation device shown in an embodiment of the present application.

[0150] See also Figure 7 The title recommendation device includes: an acquisition module 71, a query module 72, and a recommendation module 73. The functions of the acquisition module 71, the query module 72, and the recommendation module 73 are as described above. Figure 6 The corresponding modules will not be described in detail in this embodiment.

[0151] The acquisition module 71 may further include: a grouping unit 711 , a topic selection unit 712 , and a first recommendation unit 713 .

[0152] The grouping unit 711 is used to group the multiple target knowledge points according to the historical answer accuracy rate of each target knowledge point in the first round of question deduction process.

[0153] The topic selection unit 712 is used to select a group of the first topics from the candidate topics of each target knowledge point in the same group.

[0154] The first recommendation unit 713 is configured to recommend answers to the first questions in each group.

[0155] The recommendation module 73 further includes: a first acquisition unit 731 , a second acquisition unit 732 , a query unit 733 , a second recommendation unit 734 and a third recommendation unit 735 .

[0156] The first acquiring unit 731 is used to acquire the historical answer accuracy rate of each of the preceding knowledge points.

[0157] The second acquisition unit 732 is used to sort the target knowledge point and adjacent knowledge points learned before the target knowledge point according to a second priority to obtain a consolidated knowledge point.

[0158] The query unit 733 is used to query the related knowledge points whose historical answer accuracy rate is less than a first threshold from each of the previous knowledge points.

[0159] The second recommendation unit 734 is used to select the second question from the candidate questions of the associated knowledge point and the candidate questions of the target knowledge point for recommendation as an answer when the associated knowledge point is found.

[0160] The third recommendation unit 735 is used to recommend questions for answering based on the candidate questions for consolidating the knowledge points.

[0161] Regarding the apparatus in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments of the relevant methods and will not be elaborated on again here.

[0162] Figure 8 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. The electronic device may be a mobile terminal device or a computer device.

[0163] See also Figure 8 , the electronic device 800 includes a memory 810 and a processor 820.

[0164] The processor 820 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0165] The memory 810 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by the processor 820 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose stored instructions and data even when the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as the permanent storage device. In other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as dynamic random access memory. The system memory may store some or all instructions and data required by the processor during operation. In addition, the memory 810 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and magnetic disks and / or optical disks may also be used. In some embodiments, the memory 810 may include a readable and / or writable removable storage device, such as a compact disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0166] The memory 810 stores executable codes. When the executable codes are processed by the processor 820 , the processor 820 may execute part or all of the above-mentioned methods.

[0167] The above has described the solution of the present application in detail with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own focus. For parts not described in detail in one embodiment, please refer to the relevant description of other embodiments.

[0168] Those skilled in the art should also be aware that the actions and modules involved in the description are not necessarily required for this application.

[0169] In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in sequence, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0170] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0171] Alternatively, the present application can also be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0172] Those skilled in the art will also appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in conjunction with the explanations herein may be implemented as electronic hardware, computer software, or combinations of both.

[0173] The flowcharts and block diagrams in the accompanying drawings show possible architectures, functions and operations of the systems and methods according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of a code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0174] While various embodiments of the present application have been described above, the above descriptions are illustrative, non-exhaustive, and not intended to be limiting of the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A topic recommendation method, characterized in that: The following steps are involved: From the candidate questions for the target knowledge point, select the first question to recommend for answering; If there is an incorrect answer to the first question, query the preceding knowledge points of the target knowledge point; Recommending a second question for answer based on the candidate questions of the preceding knowledge point; wherein, obtaining a historical answer accuracy rate of each preceding knowledge point, searching for related knowledge points whose historical answer accuracy rate is less than a first threshold value from each preceding knowledge point, and when the related knowledge point is found, selecting a second question from the candidate questions of the related knowledge point and the candidate questions of the target knowledge point for recommendation; In the case where the associated knowledge point is found, selecting a second topic from the candidate topics of the associated knowledge point and the candidate topics of the target knowledge point respectively includes: If the number of the associated knowledge points is greater than a second threshold, the associated knowledge points are screened according to a set first priority to obtain retained knowledge points; a first number of second questions are selected from the candidate questions for the retained knowledge points; and a second number of second questions are selected from the candidate questions for the target knowledge points; wherein the first priority is to first search for knowledge points that are absent, then search for knowledge points with a low three-star rate, and finally search for knowledge points with high difficulty; If the number of associated knowledge points is less than or equal to the second threshold, the values ​​of the third and fourth quantities are determined based on the number of wrong questions and / or the correct answer rate of the first question; the second number of questions of the third quantity are selected from the candidate questions of the associated knowledge points; and the second number of questions of the fourth quantity are selected from the candidate questions of the target knowledge points.

2. The topic recommendation method according to claim 1, characterized in that: After searching for related knowledge points whose historical answer accuracy is less than a first threshold value from each of the preceding knowledge points, the method further includes: In the case that the related knowledge point is not found, the second question is selected from the candidate questions of the target knowledge point and recommended for answering.

3. The topic recommendation method according to claim 1 or 2, characterized in that: After recommending a second question to answer based on the candidate questions of the preceding knowledge point, the method further includes: sorting the target knowledge point and adjacent knowledge points learned before the target knowledge point according to a second priority to obtain a consolidation knowledge point; Based on the candidate questions for consolidating the knowledge points, questions are recommended for answering.

4. The topic recommendation method according to claim 1 or 2, characterized in that: Before selecting the first question from the candidate questions for the target knowledge point for recommendation for answering, the method further includes: Using the knowledge points that were not answered or not recommended in the first round of question recommendation process as the target knowledge points in the first round of question recommendation process; Alternatively, the target knowledge points in the second round of question-pushing process are determined based on the knowledge points answered incorrectly in the first round of question-pushing process; Alternatively, the knowledge points that were not answered in the second round of question deduction process are used as the target knowledge points in the second round of question deduction process.

5. The topic recommendation method according to claim 1 or 2, characterized in that: There are multiple target knowledge points, and selecting a first question from candidate questions for the target knowledge point to recommend for answering includes: Grouping the target knowledge points according to the historical correct answer rate of each target knowledge point in the first round of question-pushing process; Selecting a group of the first questions from the candidate questions for each target knowledge point in the same group; Recommend answers to the first question for each group.

6. A topic recommendation device, characterized in that: include: An acquisition module is used to select the first question from the candidate questions of the target knowledge point and recommend it for answering; A query module, configured to query the preceding knowledge points of the target knowledge point if there is an incorrect answer to the first question; A recommendation module is used to recommend a second question to answer based on the candidate questions of the previous knowledge point; wherein: the recommendation module includes: A first acquisition unit is used to obtain the historical answer accuracy rate of each of the preceding knowledge points; a query unit, configured to query, from each of the preceding knowledge points, related knowledge points whose historical answer accuracy is less than a first threshold; a second recommendation unit for selecting a second question from the candidate questions of the associated knowledge point and the candidate questions of the target knowledge point for recommendation for answering when the associated knowledge point is found; The second recommendation unit is specifically configured to: If the number of the associated knowledge points is greater than a second threshold, the associated knowledge points are screened according to a set first priority to obtain retained knowledge points; a first number of second questions are selected from the candidate questions for the retained knowledge points; and a second number of second questions are selected from the candidate questions for the target knowledge points; wherein the first priority is to first search for knowledge points that are absent, then search for knowledge points with a low three-star rate, and finally search for knowledge points with high difficulty; If the number of associated knowledge points is less than or equal to the second threshold, the values ​​of the third and fourth quantities are determined based on the number of wrong questions and / or the correct answer rate of the first question; the second number of questions of the third quantity are selected from the candidate questions of the associated knowledge points; and the second number of questions of the fourth quantity are selected from the candidate questions of the target knowledge points.

7. The topic recommendation device according to claim 6, characterized in that: The query unit is configured to: In the case that the related knowledge point is not found, the second question is selected from the candidate questions of the target knowledge point and recommended for answering.

8. The topic recommendation device according to claim 6 or 7, characterized in that: The recommendation module includes: A second acquisition unit is configured to sort the target knowledge point and adjacent knowledge points learned before the target knowledge point according to a second priority to obtain a consolidated knowledge point; The third recommendation unit is used to recommend questions for answering based on the candidate questions for consolidating the knowledge points.

9. The topic recommendation device according to claim 6 or 7, characterized in that: The acquisition module is used to: Using the knowledge points that were not answered or not recommended in the first round of question recommendation process as the target knowledge points in the first round of question recommendation process; Alternatively, the target knowledge points in the second round of question-pushing process are determined based on the knowledge points answered incorrectly in the first round of question-pushing process; Alternatively, the knowledge points that were not answered in the second round of question deduction process are used as the target knowledge points in the second round of question deduction process.

10. The topic recommendation device according to claim 6 or 7, characterized in that: There are multiple target knowledge points, and the acquisition module includes: A grouping unit, configured to group the target knowledge points according to the historical correct answer rate of each target knowledge point in the first round of question-pushing process; a topic selection unit, configured to select a group of the first topics from candidate topics for each of the target knowledge points in the same group; The first recommendation unit is used to recommend answers to the first questions in each group respectively.

11. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1 to 5.

Images