Review data recommendation method and device, storage medium and electronic equipment

Abstract

The invention discloses a review data recommendation method and device, a storage medium and electronic equipment, and relates to the technical field of education, and the method comprises the steps: obtaining a teaching material text and a historical question bank, extracting and combining teaching material knowledge points to form a basic knowledge point cluster, screening out an important knowledge point cluster through a preset model, and generating target question banks with different difficulty levels. And mapping the data to a learning map, generating a learning track of the student, and recommending adaptive review data. The review data suitable for the current learning stage of the student can be recommended to the student according to the learning progress and the knowledge mastering degree of the student, and the problem that the review data is lack of coherence so that the review data can be matched with the learning state of the student is effectively solved.

Description

Technical Field

[0001] The present application relates to the field of educational technology, and in particular to a method, device, storage medium and electronic device for recommending review materials. Background Art

[0002] In the context of the era of intelligent education, online education platforms have enabled more and more students to practice test questions due to the richness of their question banks. In order to help students consolidate the test questions they have practiced, it is necessary to recommend review materials to students.

[0003] In the related technology of recommending review materials, review materials related to the students' practiced test questions are usually recommended to students. Since students jump across chapters in the process of practicing questions, there is a lack of connectivity between the practiced test questions, resulting in a lack of connectivity in the review materials recommended to students. Summary of the invention

[0004] The present application provides a method, device, storage medium and electronic device for recommending review materials. The main purpose is to solve the problem that the review materials recommended to students lack coherence due to the fact that students jump across chapters in the process of practicing questions and lack coherence between the practiced questions.

[0005] According to a first aspect of the present application, a method for recommending review materials is provided, which comprises: Get textbook texts and history question banks; Extracting textbook knowledge points contained in the textbook text, and combining the textbook knowledge points according to the difficulty level, to obtain a plurality of textbook knowledge point sets with different difficulty levels to form a basic knowledge point cluster; Using a preset knowledge point screening model, all the test question knowledge points in the history question bank are screened for test question knowledge points whose difficulty level is greater than a preset level threshold, to obtain an important knowledge point cluster; Based on the basic knowledge point cluster and the important knowledge point cluster, test questions of different difficulty levels are generated to form a target question bank, and the target question bank is used to map on a learning map, so as to generate a target learning trajectory of the student in the process through the learning map, and recommend target review materials suitable for the student to the student based on the target learning trajectory.

[0006] Optionally, extracting textbook knowledge points contained in the textbook text and combining the textbook knowledge points according to their difficulty levels to obtain a plurality of textbook knowledge point sets with different difficulty levels to form a basic knowledge point cluster includes: Extracting all the teaching material knowledge points in the teaching material text; Conducting difficulty level evaluation on each of the textbook knowledge points in all the textbook knowledge points to obtain the difficulty level of each textbook knowledge point; Respectively combining the textbook knowledge points of different difficulty levels among all the textbook knowledge points into different basic knowledge point sets; the textbook knowledge points in the same basic knowledge point set have the same difficulty level; All basic knowledge point sets are combined into the basic knowledge point cluster.

[0007] Optionally, the method of using a preset knowledge point screening model to screen out test knowledge points with a difficulty level greater than a preset level threshold from all test knowledge points in the history test bank to obtain an important knowledge point cluster includes: Obtain the examination frequency of each of the test question knowledge points in the history question bank, the test question answering accuracy rate corresponding to each of the test question knowledge points uploaded by the student, and the correlation between each of the test question knowledge points and other knowledge points in the test question knowledge points, and obtain the weights corresponding to the examination frequency, the test question answering accuracy rate, and the correlation; the difficulty level is a comprehensive indicator of the examination frequency, the test question answering accuracy rate, and the correlation; Calculate the difficulty level of each test question knowledge point according to the examination frequency of each test question knowledge point, the test question answer accuracy rate, the correlation degree and the respective corresponding weights; The test question knowledge points whose difficulty levels are greater than the preset level threshold among all the test question knowledge points are constructed as the important knowledge point cluster.

[0008] Optionally, calculating the difficulty level of each test question knowledge point according to the examination frequency of each test question knowledge point, the test question answer accuracy, the correlation degree and the respective corresponding weights includes: According to the preset difficulty level evaluation algorithm, the difficulty level of each knowledge point of the test question is calculated respectively. ; The calculation formula of the preset difficulty level evaluation algorithm is:

[0009] in, The test frequency of each test knowledge point in the history question bank, the accuracy rate of the test answers corresponding to each test knowledge point uploaded by the student, and the correlation between each test knowledge point and other knowledge points in all test knowledge points are respectively are the weights corresponding to the examination frequency, the test question answering accuracy and the correlation degree respectively.

[0010] Optionally, mapping on a learning map to generate a target learning trajectory in a student process through the learning map includes: Constructing the test questions of different difficulty levels in the target test bank into a learning map; the learning map includes the same number of learning grids as the test questions in the target test bank, and each learning grid corresponds to a test question in the target test bank; Marking the learning grid corresponding to the practiced test questions of the student in the learning map; The learning grids corresponding to the practiced test questions are connected to obtain the target learning trajectory.

[0011] Optionally, constructing the test questions of different difficulty levels in the target question bank into a learning map includes: Performing correlation analysis on the test questions of different difficulty levels to obtain correlations between the test questions of different difficulty levels; Arranging the test questions of different difficulty levels according to the correlation between the test questions of different difficulty levels to obtain arranged test questions of different difficulty levels; The learning map is generated based on the arranged test questions of different difficulty levels.

[0012] Optionally, the recommending to the student target review materials adapted to the student based on the target learning trajectory includes: According to the pre-established mapping relationship between the learning track and the review materials, searching for the target review materials corresponding to the target learning track; The target review material is recommended to the student.

[0013] According to a second aspect of the present application, a device for recommending review materials is provided, comprising: An acquisition unit is used to acquire textbook texts and history question banks; A combination unit, used to extract the textbook knowledge points contained in the textbook text, and combine the textbook knowledge points according to the difficulty level, so as to obtain a set of textbook knowledge points with different difficulty levels to form a basic knowledge point cluster; A screening unit, configured to screen out test knowledge points whose difficulty level is greater than a preset level threshold from all test knowledge points in the history test bank using a preset knowledge point screening model, to obtain an important knowledge point cluster; A generating unit, for generating test questions of different difficulty levels to form a target question bank based on the basic knowledge point cluster and the important knowledge point cluster, wherein the target question bank is used for mapping on a learning map to generate a target learning trajectory of a student in the learning process through the learning map; A recommendation unit is used to recommend target review materials suitable for the students to the students based on the target learning trajectory.

[0014] Optionally, the combination unit includes: An extraction module, used to extract all the teaching material knowledge points in the teaching material text; An evaluation module, used to evaluate the difficulty level of each of the textbook knowledge points in all the textbook knowledge points, to obtain the difficulty level of each textbook knowledge point; A combination module, used to respectively combine the textbook knowledge points of different difficulty levels among all the textbook knowledge points into different basic knowledge point sets; the textbook knowledge points in the same basic knowledge point set have the same difficulty level; The combination module is also used to combine all basic knowledge point sets into the basic knowledge point cluster.

[0015] Optionally, the screening unit includes: An acquisition module is used to acquire the examination frequency of each of the test question knowledge points in the history question bank, the test question answering accuracy rate corresponding to each of the test question knowledge points uploaded by the student, the correlation between each of the test question knowledge points and other knowledge points in the test question knowledge points, and to acquire the weights corresponding to the examination frequency, the test question answering accuracy rate, and the correlation rate; the difficulty level is a comprehensive indicator of the examination frequency, the test question answering accuracy rate, and the correlation rate; A calculation module, for calculating the difficulty level of each test question knowledge point according to the examination frequency of each test question knowledge point, the test question answer accuracy, the correlation degree and the respective corresponding weights; The first construction module is used to construct the test question knowledge points whose difficulty levels are greater than the preset level threshold among all the test question knowledge points into the important knowledge point cluster.

[0016] Optionally, the calculation module is further used for: According to the preset difficulty level evaluation algorithm, the difficulty level of each knowledge point of the test question is calculated respectively. ; The calculation formula of the preset difficulty level evaluation algorithm is:

[0017] in, The test frequency of each test knowledge point in the history question bank, the accuracy rate of the test answers corresponding to each test knowledge point uploaded by the student, and the correlation between each test knowledge point and other knowledge points in all test knowledge points are respectively are the weights corresponding to the examination frequency, the test question answering accuracy and the correlation degree respectively.

[0018] Optionally, the generating unit includes: A second construction module is used to construct the test questions of different difficulty levels in the target test bank into a learning map; the learning map includes the same number of learning grids as the test questions in the target test bank, and each learning grid corresponds to a test question in the target test bank; A marking module, used for marking the learning grids corresponding to the practiced test questions of the student in the learning map; The connection module is used to connect the learning grids corresponding to the practiced test questions to obtain the target learning trajectory.

[0019] Optionally, the second building block is further used for: Performing correlation analysis on the test questions of different difficulty levels to obtain correlations between the test questions of different difficulty levels; Arranging the test questions of different difficulty levels according to the correlation between the test questions of different difficulty levels to obtain arranged test questions of different difficulty levels; The learning map is generated based on the arranged test questions of different difficulty levels.

[0020] Optionally, the recommendation unit is further used for: According to the pre-established mapping relationship between the learning track and the review materials, searching for the target review materials corresponding to the target learning track; The target review material is recommended to the student.

[0021] According to a third aspect of the present application, an electronic device is provided, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0022] According to a fourth aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect above.

[0023] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method according to the first aspect is implemented.

[0024] The review material recommendation method, device, storage medium and electronic device provided by this application obtain the textbook text and historical question bank, extract and combine the textbook knowledge points to form basic knowledge point clusters, use the preset model to screen out the important knowledge point clusters, and then generate target question banks of different difficulty levels, and map them to the learning map to generate the student's learning trajectory and recommend suitable review materials. It can recommend review materials suitable for the student's current learning stage according to the student's learning progress and knowledge mastery, effectively solving the lack of cohesion of the review materials and matching the review materials with the student's learning status.

[0025] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application. Figure 1 A flowchart of a method for recommending review materials provided in an embodiment of the present application; Figure 2 A structural diagram of a learning map provided in an embodiment of the present application; Figure 3 A schematic diagram of a process for generating basic knowledge points provided in an embodiment of the present application; Figure 4 A schematic diagram of a knowledge graph of a basic knowledge point cluster provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of a device for recommending review materials provided in an embodiment of the present application; Figure 6 A schematic diagram of the structure of another device for recommending review materials provided in an embodiment of the present application; Figure 7 A schematic block diagram of an example electronic device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0028] The following describes a method, device, storage medium, and electronic device for recommending review materials according to an embodiment of the present application with reference to the accompanying drawings.

[0029] Figure 1 A flowchart of a method for recommending review materials provided in an embodiment of the present application.

[0030] like Figure 1 As shown, the method is applied in a server, and the method comprises the following steps: Step 101, obtain the textbook text and history question bank.

[0031] Textbook text refers to electronic textbook content, including but not limited to textbooks, syllabi, lesson plans, course handouts and other structured text data. Textbook text covers a complete description of subject knowledge points, for example, trigonometric functions, calculus, chapter divisions, and knowledge point hierarchical relationships in mathematics.

[0032] The history question bank refers to the collection of test questions accumulated in the past by the online education platform, which includes practice questions and test questions for various subjects, grades, and knowledge points. It records information such as the test knowledge points, difficulty, and students' answers. For example, a middle school's mathematics history question bank contains monthly exams, midterm and final exam questions from the past five years.

[0033] The textbook text can be obtained through the electronic textbook interface directly provided by educational institutions, publishers or third-party platforms. Secondly, if the textbook is a paper version, it can be scanned and converted into an editable text format. When obtaining the textbook text, the text content also needs to be classified and marked. The title, subtitle, knowledge point, formula, chart, etc. of each chapter should be extracted and classified into specific knowledge points or modules. The textbook content can also be structured according to the teaching plan and syllabus to ensure that the textbook content is consistent with the course objectives and syllabus.

[0034] The way to obtain the history question bank is to obtain it through the data interface provided by educational institutions or question bank service providers. These question banks usually include various types of test questions (multiple-choice questions, fill-in-the-blank questions, short-answer questions, etc.), and are accompanied by the answer, analysis, and knowledge point annotations of each question. The obtained history question bank should contain a large number of past real questions, simulation questions, and questions of different difficulty levels and knowledge points. The question bank should be closely related to the content of the textbook, covering all important knowledge points and chapters in the textbook. When obtaining the history question bank, it is also necessary to label the knowledge points of the test questions, indicate the specific knowledge points involved in each question, and classify them according to their difficulty level, examination frequency and other attributes.

[0035] We collect a wide range of textbook texts and history question banks, build a rich learning resource library, meet the personalized learning needs of different students, and broaden their learning horizons.

[0036] Step 102, extracting textbook knowledge points contained in the textbook text, and combining the textbook knowledge points according to their difficulty levels, to obtain a plurality of textbook knowledge point sets with different difficulty levels to form a basic knowledge point cluster.

[0037] A textbook knowledge point refers to an independent unit of teaching content in the textbook text, and is the smallest logical unit of subject knowledge, such as the Pythagorean theorem in mathematics, the properties of quadratic function graphs, metaphors in Chinese, and the usage of function words in classical Chinese. A textbook knowledge point has clear semantic boundaries and can be defined by the textbook catalog or knowledge point labels; a textbook knowledge point includes a knowledge point description text, related examples, exercises, and dependencies with other knowledge points.

[0038] Difficulty refers to the quantitative rating of the cognitive ability required to master a knowledge point, which is divided into multiple levels (such as elementary, intermediate, and advanced). The rating criteria include the abstractness of the knowledge point, logical complexity, and the amount of related knowledge.

[0039] The textbook knowledge point set is a subset of textbook knowledge points of the same difficulty level. For example, the primary set contains all knowledge points of difficulty level 1, and the intermediate set contains knowledge points of difficulty level 2. The basic knowledge point cluster is a complete cluster composed of multiple textbook knowledge point sets of different difficulty levels, which is used to cover the full difficulty spectrum of the subject knowledge system.

[0040] The textbook text is preprocessed using natural language processing technology. This process includes removing irrelevant content and segmenting and tokenizing each chapter, paragraph, and sentence in the textbook. Through in-depth analysis of the text semantics, all relevant textbook knowledge points are extracted. A machine learning model is used to combine the contextual information of the knowledge points in the textbook to classify the difficulty of each extracted knowledge point and label each knowledge point with a difficulty label. According to the difficulty of the assessment, the knowledge points are divided into multiple categories, such as simple, medium, difficult, etc. Each category contains a group of knowledge points, representing the textbook content of that difficulty level. The knowledge points of the same category are combined by chapter or module to form a basic knowledge point cluster. The knowledge points in each basic knowledge point cluster can be arranged step by step according to the progress of the course, the relevance of the topic, and the difficulty of the knowledge points, ensuring that students can start with simple knowledge points and gradually transition to more complex and profound knowledge content.

[0041] Reasonably grouping knowledge points according to difficulty can help students start from the basics and gradually accumulate knowledge, so that they will not be confused or frustrated by being exposed to knowledge points that are too difficult too early. This gradual advancement method helps students better understand and digest the content of the textbook, thereby improving learning effects.

[0042] Step 103, using a preset knowledge point screening model, screen out the test question knowledge points whose difficulty level is greater than a preset level threshold from all the test question knowledge points in the history question bank to obtain an important knowledge point cluster.

[0043] The preset knowledge point screening model refers to an algorithm model pre-built in the system for evaluating the difficulty of test knowledge points. This model is usually trained based on a large amount of historical data (such as past test questions, student answers, etc.), and can automatically evaluate the difficulty of the knowledge points involved in the test questions. The preset knowledge point screening model can be adjusted according to the students' learning ability, subject characteristics and specific difficulty standards. Test knowledge points: refers to the specific knowledge areas or content points involved in each test question. Each test knowledge point represents the core concept, formula, theorem or method of a subject, and usually appears in the test questions in the form of concepts, formulas, theorems, etc.

[0044] The difficulty level refers to the difficulty level of each test knowledge point according to its application in the test question. Usually, there are multiple difficulty levels, and the basis for the division includes the complexity of the knowledge point, the scope of application, and the requirements of related prior knowledge. The preset level threshold is a pre-set standard value used to define the difficulty of the knowledge point. The embodiment of the present application does not limit the specific value of the preset level threshold.

[0045] By screening out important knowledge points, students can focus on learning key content, avoid blindly learning a large number of knowledge points, and improve their learning efficiency.

[0046] Step 104, based on the basic knowledge point cluster and the important knowledge point cluster, generate test questions of different difficulty levels to form a target question bank, the target question bank is used to map on the learning map, so as to generate the target learning trajectory of the student in the process through the learning map, and recommend target review materials suitable for the student to the student based on the target learning trajectory.

[0047] The learning map is a visual learning path planning tool that presents the relationship between learning content, knowledge points and learning order in the form of a map to help students better understand and plan the learning process. Target learning trajectory: During the learning process, students form a specific learning path on the learning map based on their learning progress, mastery and learning goals, which reflects the students' learning direction and focus. Target review materials: Based on the students' target learning trajectory, the review materials recommended for them are designed to help students consolidate their knowledge and improve their learning effects.

[0048] Each test question in the target question bank is mapped to a learning grid. The grid attributes include the test question ID, knowledge point, difficulty level, and the list of related grids. The knowledge points can be arranged in the order of the chapters they belong to, or in ascending order of difficulty under the same knowledge point. According to the student's answer record, the grid corresponding to the completed test question is marked as learned: the grids are connected according to the practice time sequence or the knowledge point dependency relationship to form a learning track.

[0049] To facilitate understanding, an example is provided: the order of student practice is: G1 (Basics of the Pythagorean Theorem) → G5 (Basics of Trigonometric Functions) → G8 (Application Questions of the Pythagorean Theorem); the generated trajectory is: G1-G5-G8 (the dotted line connecting G5→G8 represents jump learning; the system detects that G5→G8 lacks the intermediate knowledge point G6, and prompts for additional practice).

[0050] In order to better understand the learning map, Figure 2 As shown, Figure 2 A structural diagram of a learning map provided in an embodiment of the present application is shown in FIG. Figure 2 Each rectangle in the figure represents a test question, where the unfilled rectangles represent test questions that students have not practiced, and the black filled rectangles represent test questions that students have practiced.

[0051] The learning map intuitively displays the relationship between learning paths and knowledge points, helping students better plan the learning process and improve learning efficiency.

[0052] The review material recommendation method provided by this application obtains textbook texts and history question banks, extracts and combines textbook knowledge points to form basic knowledge point clusters, uses preset models to screen out important knowledge point clusters, and then generates target question banks of different difficulty levels, and maps them to learning maps to generate students' learning trajectories and recommend appropriate review materials. It can recommend review materials suitable for students' current learning stage based on their learning progress and knowledge mastery, effectively solving the lack of connectivity in review materials and matching them with students' learning status.

[0053] As a refinement of step 102, when extracting the textbook knowledge points contained in the textbook text and combining the textbook knowledge points according to the difficulty level to obtain a plurality of textbook knowledge point sets with different difficulty levels to form a basic knowledge point cluster, the following methods may be used but are not limited to: Figure 3 As shown, Figure 3 A schematic diagram of a process for generating a basic knowledge point provided in an embodiment of the present application includes: Step 201, extracting all the teaching material knowledge points in the teaching material text.

[0054] Extracting all the knowledge points in the textbook is usually done through text preprocessing, word segmentation, and stop word removal, and then using natural language processing techniques such as named entity recognition, dependency syntax analysis, and keyword extraction to identify the textbook knowledge points.

[0055] Step 202, respectively evaluate the difficulty level of each of the textbook knowledge points in all the textbook knowledge points to obtain the difficulty level of each textbook knowledge point.

[0056] Use natural language processing technology to evaluate the language difficulty of each knowledge point, such as vocabulary complexity, sentence structure complexity, etc. Secondly, combine the knowledge of the subject area to evaluate the theoretical depth and application difficulty of the knowledge point. Finally, a machine learning model can be used to train a difficulty prediction model based on historical data and expert ratings to automatically divide the difficulty level of each knowledge point.

[0057] Step 203, respectively combining the textbook knowledge points of different difficulty levels among all the textbook knowledge points into different basic knowledge point sets; the textbook knowledge points in the same basic knowledge point set have the same difficulty level.

[0058] According to students' learning progress and comprehension ability, we can provide different students with a collection of knowledge points suitable for them, so as to make personalized learning arrangements and help students master knowledge step by step from basic to in-depth.

[0059] Step 204: combine all basic knowledge point sets into the basic knowledge point cluster.

[0060] In order to better understand the basic knowledge point clusters, such as Figure 4 As shown, Figure 4 A schematic diagram of a knowledge graph of a basic knowledge point cluster provided in an embodiment of the present application, wherein A is a set of basic knowledge points with the highest difficulty level, which can be classified by chapter, b1 and b2 are a set of basic knowledge points with the next highest difficulty level, b1 and b2 are slave nodes of A, which can be classified by section, c1, c2, and c3 are a set of basic knowledge points with the lowest difficulty level, c1, c2, and c3 are slave nodes of b1 and b2, which can be classified by unit results.

[0061] As a refinement of step 103, when executing the method of using the preset knowledge point screening model to screen out the test knowledge points whose difficulty level is greater than the preset level threshold from all the test knowledge points in the history question bank to obtain the important knowledge point cluster, it can be implemented in but not limited to the following ways, including: obtaining the examination frequency of each test knowledge point in all the test knowledge points in the history question bank, the test answer accuracy rate corresponding to each test knowledge point uploaded by the student, the correlation between each test knowledge point and other knowledge points in all the test knowledge points, and obtaining the weights corresponding to the examination frequency, the test answer accuracy rate, and the correlation; the difficulty level is a comprehensive indicator of the examination frequency, the test answer accuracy rate, and the correlation; the difficulty level of each test knowledge point is calculated according to the examination frequency, the test answer accuracy rate, the correlation rate, and the corresponding weights of each test knowledge point; and the test knowledge points in all the test knowledge points whose difficulty level is greater than the preset level threshold are constructed as the important knowledge point cluster.

[0062] The embodiment of the present application does not limit the specific value of the preset level threshold. The degree of correlation between each test question knowledge point and other knowledge points in all test question knowledge points can be the number of branches connecting the test question knowledge point center and other knowledge points. The more branches there are, the higher the degree of correlation between the test question knowledge point and other knowledge points, indicating that the difficulty level of the test question knowledge point is higher.

[0063] As a refinement of the above embodiment, when calculating the difficulty level of each test question knowledge point according to the examination frequency of each test question knowledge point, the test question answer accuracy, the correlation degree and the respective corresponding weights, it can be implemented in the following ways but not limited to, including: According to the preset difficulty level evaluation algorithm, the difficulty level of each knowledge point of the test question is calculated respectively. ; The calculation formula of the preset difficulty level evaluation algorithm is:

[0064] in, The test frequency of each test knowledge point in the history question bank, the accuracy rate of the test answers corresponding to each test knowledge point uploaded by the student, and the correlation between each test knowledge point and other knowledge points in all test knowledge points are respectively are the weights corresponding to the examination frequency, the test question answering accuracy and the correlation degree respectively.

[0065] Examination frequency refers to the frequency of a certain knowledge point in a test question appearing in the historical question bank, that is, the number of times this knowledge point has been examined in past test questions. The examination frequency in the college entrance examination indicates that this knowledge point is often examined and may be a basic or important knowledge point. The answer accuracy rate refers to the correct answer rate of students to questions related to a certain knowledge point during the answering process, usually refers to the success rate of students when they encounter questions related to this knowledge point. A higher accuracy rate indicates that the student has a better grasp of this knowledge point. Correlation refers to the correlation between a certain knowledge point in a test question and other knowledge points. This correlation reflects the degree of connection between different knowledge points, for example, whether the mastery of a certain knowledge point affects the understanding of other knowledge points, or whether they often appear together in the same type of test questions. A high correlation indicates that these knowledge points have a strong mutual connection in learning and examinations.

[0066] As a refinement of step 104, when performing the mapping on the learning map to generate the target learning trajectory of the student process through the learning map, it can be implemented in but not limited to the following ways, including: constructing the test questions of different difficulty levels in the target question bank into a learning map; the learning map includes the same number of learning grids as the test questions in the target question bank, each learning grid corresponds to a test question in the target question bank; marking the learning grids corresponding to the student's practiced test questions in the learning map; connecting the learning grids corresponding to the practiced test questions to obtain the target learning trajectory.

[0067] Learning grids refer to small cells or nodes on the learning map. Each learning grid corresponds to a test question in the target question bank. The learning map is constructed according to the number and difficulty level of the test questions in the target question bank. Each test question has a corresponding position on the learning map, which is the learning grid. The learning grid not only represents the position of the test question on the learning map, but also contains relevant information about the test question, such as the difficulty level. When the learning grids corresponding to the students' practiced test questions are marked and connected, the students' learning trajectory can be formed to help understand the students' learning progress and mastery.

[0068] According to the difficulty level of the test questions in the target question bank, the test questions are divided into different groups, such as simple questions, medium difficulty questions and difficult questions. Then, the different groups are arranged according to the difficulty level of the test questions or the degree of correlation of the test questions, and the correlation between different groups is analyzed. A corresponding learning grid is created for each test question. Each learning grid contains detailed information of the test question, such as the test question content, difficulty level, knowledge point label, etc. The learning grid can be in the form of a table or a graph. The rows and columns of the table can represent different knowledge points and difficulty levels respectively, and the graph can more intuitively show the correlation between the test questions. Arrange the learning grids corresponding to the test questions in the same group together, and arrange the learning grids corresponding to the test questions in different groups with correlation together, so as to integrate them into a complete learning map, and ensure that each learning grid has a clear position and mark on the learning map so that students can view and navigate clearly.

[0069] The learning management system collects the records of the practiced questions uploaded by the students' clients in the target question bank, including the question number, practice time, answer status and other information. According to the records of the questions that the students have practiced, find the learning grid of the corresponding questions on the learning map and mark them. The marking method can be color coding, icon identification or text description, for example, green marks are used to indicate the questions that the students have answered correctly, and red marks are used to indicate the questions that the students have answered incorrectly. As students continue to practice new questions, the marking information on the learning map is updated in a timely manner to ensure that it accurately reflects the students' latest learning progress, and the learning grids corresponding to the practiced questions are connected to obtain the target learning trajectory. According to the order of the questions that the students have practiced and the layout of the learning grids on the learning map, a learning path from the starting learning grid to the last learning grid that has been practiced is planned. The learning path can be a straight line connection or a curved path generated according to the shortest path or the closeness of the knowledge point association. Use graphics drawing tools or programming algorithms to draw the planned learning path on the learning map to form the student's learning trajectory. Learning tracks can be presented in different colors, line styles or animation effects so that students can understand their learning progress more intuitively. By analyzing the learning track, we can understand the students' learning habits, knowledge mastery, learning progress and other information. For example, if the learning track shows that the student stays in a certain knowledge point area for a long time or repeatedly practices certain test questions, it means that the student may have difficulties in this knowledge point and needs further review and guidance. At the same time, the learning track can also be used as a basis for recommending target review materials. According to the student's current learning status and track, suitable review materials are recommended to help students better consolidate and improve their knowledge.

[0070] As a refinement of the above embodiment, when executing the construction of the test questions of different difficulty levels in the target question bank into a learning map, it can be implemented in but not limited to the following ways, including: performing correlation analysis on the test questions of different difficulty levels to obtain the correlation between the test questions of different difficulty levels; arranging the test questions of different difficulty levels according to the correlation between the test questions of different difficulty levels to obtain the arranged test questions of different difficulty levels; generating the learning map based on the arranged test questions of different difficulty levels.

[0071] Arranging the test questions according to their relevance and difficulty can help students focus on interrelated knowledge points and avoid repeated and ineffective exercises. Students can master knowledge more efficiently, reduce unnecessary repetitive learning, and improve learning efficiency.

[0072] As a refinement of step 104, when executing the method of recommending target review materials suitable for the student based on the target learning trajectory, it can be implemented in but not limited to the following ways, including: searching for the target review materials corresponding to the target learning trajectory according to a pre-established mapping relationship between the learning trajectory and the review materials; and recommending the target review materials to the student.

[0073] Based on each student's unique learning trajectory and mastery, we provide personalized review material recommendations to meet the learning needs of different students and help students strengthen their weak links in a targeted manner.

[0074] In summary, the embodiments of the present application can achieve the following effects: The embodiment of the present application obtains textbook text and history question bank, extracts and combines textbook knowledge points to form basic knowledge point clusters, uses preset models to screen out important knowledge point clusters, and then generates target question banks of different difficulty levels, maps them to learning maps, generates students' learning trajectories, and recommends suitable review materials. It can recommend review materials suitable for students' current learning stage according to their learning progress and knowledge mastery, effectively solving the lack of cohesion in review materials and matching them with students' learning status.

[0075] Corresponding to the above-mentioned review material recommendation method, the present invention also provides a review material recommendation device. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

[0076] Figure 5 This is a schematic diagram of the structure of a review material recommendation device provided in an embodiment of the present application. The device can be applied to a server, such as Figure 5 As shown, including: An acquisition unit 31 is used to acquire the textbook text and the history question bank; A combining unit 32 is used to extract the textbook knowledge points contained in the textbook text, and combine the textbook knowledge points according to the difficulty level, so as to obtain a plurality of textbook knowledge point sets with different difficulty levels to form a basic knowledge point cluster; A screening unit 33 is used to screen out the test knowledge points with a difficulty level greater than a preset level threshold from all the test knowledge points in the history test database using a preset knowledge point screening model to obtain an important knowledge point cluster; A generating unit 34, configured to generate test questions of different difficulty levels to form a target question bank based on the basic knowledge point cluster and the important knowledge point cluster, wherein the target question bank is used to be mapped on a learning map so as to generate a target learning trajectory of the student in the learning process through the learning map; The recommendation unit 35 is used to recommend target review materials suitable for the students to the students based on the target learning trajectory.

[0077] The review material recommendation device provided by this application obtains textbook texts and history question banks, extracts and combines textbook knowledge points to form basic knowledge point clusters, uses preset models to screen out important knowledge point clusters, and then generates target question banks of different difficulty levels, and maps them to learning maps, generates students' learning trajectories, and recommends suitable review materials. It can recommend review materials suitable for students' current learning stage according to their learning progress and knowledge mastery, effectively solving the lack of cohesion in review materials and matching them with students' learning status.

[0078] Furthermore, in a possible implementation of the embodiment of the present application, as Figure 6 As shown, the combination unit 32 includes: An extraction module 321 is used to extract all the teaching material knowledge points in the teaching material text; An evaluation module 322, for evaluating the difficulty level of each of the textbook knowledge points in all the textbook knowledge points, to obtain the difficulty level of each textbook knowledge point; A combination module 323 is used to respectively combine the teaching material knowledge points of different difficulty levels among all the teaching material knowledge points into different basic knowledge point sets; the teaching material knowledge points in the same basic knowledge point set have the same difficulty level; The combining module 323 is further used to combine all basic knowledge point sets into the basic knowledge point cluster.

[0079] Furthermore, in a possible implementation of the embodiment of the present application, as Figure 6 As shown, the screening unit 33 includes: The acquisition module 331 is used to obtain the examination frequency of each of the test question knowledge points in the history question bank, the test question answering accuracy rate corresponding to each of the test question knowledge points uploaded by the student, the correlation between each of the test question knowledge points and other knowledge points in the test question knowledge points, and obtain the weights corresponding to the examination frequency, the test question answering accuracy rate, and the correlation; the difficulty level is a comprehensive indicator of the examination frequency, the test question answering accuracy rate, and the correlation; A calculation module 332, configured to calculate the difficulty level of each test question knowledge point according to the examination frequency of each test question knowledge point, the test question answer accuracy rate, the correlation degree and the corresponding weights; The first construction module 333 is used to construct the test question knowledge points whose difficulty levels are greater than the preset level threshold among all the test question knowledge points into the important knowledge point cluster.

[0080] Optionally, the calculation module 332 is further used for: According to the preset difficulty level evaluation algorithm, the difficulty level of each knowledge point of the test question is calculated respectively. ; The calculation formula of the preset difficulty level evaluation algorithm is:

[0081] in, The test frequency of each test knowledge point in the history question bank, the accuracy rate of the test answers corresponding to each test knowledge point uploaded by the student, and the correlation between each test knowledge point and other knowledge points in all test knowledge points are respectively are the weights corresponding to the examination frequency, the test question answering accuracy and the correlation degree respectively.

[0082] Furthermore, in a possible implementation of the embodiment of the present application, as Figure 6 As shown, the generating unit 34 includes: A second construction module 341 is used to construct the test questions of different difficulty levels in the target test bank into a learning map; the learning map includes the same number of learning grids as the test questions in the target test bank, and each learning grid corresponds to a test question in the target test bank; A marking module 342, used for marking the learning grids corresponding to the practiced test questions of the student in the learning map; The connection module 343 is used to connect the learning grids corresponding to the practiced test questions to obtain the target learning trajectory.

[0083] Furthermore, in a possible implementation of the embodiment of the present application, as Figure 6As shown, the second building module 341 is also used for: Performing correlation analysis on the test questions of different difficulty levels to obtain correlations between the test questions of different difficulty levels; Arranging the test questions of different difficulty levels according to the correlation between the test questions of different difficulty levels to obtain arranged test questions of different difficulty levels; The learning map is generated based on the arranged test questions of different difficulty levels.

[0084] Furthermore, in a possible implementation of the embodiment of the present application, as Figure 6 As shown, the recommendation unit 35 is also used for: According to the pre-established mapping relationship between the learning track and the review materials, searching for the target review materials corresponding to the target learning track; The target review material is recommended to the student.

[0085] It should be noted that the above explanation of the method embodiment is also applicable to the device of the embodiment of the present application, the principle is the same, and it is no longer limited in the embodiment of the present application.

[0086] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0087] Figure 7 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0088] like Figure 7As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 402 or a computer program loaded from a storage unit 408 to a RAM (Random Access Memory) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An I / O (Input / Output) interface 405 is also connected to the bus 404.

[0089] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0090] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as a method for recommending review materials. For example, in some embodiments, the method for recommending review materials may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute the aforementioned review material recommendation method in any other appropriate manner (eg, by means of firmware).

[0091] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0092] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0093] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage device, magnetic storage device, or any suitable combination of the foregoing.

[0094] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0095] The systems and techniques described herein may be implemented in a computing system that includes a backend component (e.g., as a data server), or a computing system that includes a middleware component (e.g., an application server), or a computing system that includes a frontend component (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0096] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0097] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0098] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0099] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for recommending review materials, characterized in that: include: Get textbook texts and history question banks; Extracting textbook knowledge points contained in the textbook text, and combining the textbook knowledge points according to the difficulty level, to obtain a plurality of textbook knowledge point sets with different difficulty levels to form a basic knowledge point cluster; Using a preset knowledge point screening model, all the test question knowledge points in the history question bank are screened for test question knowledge points whose difficulty level is greater than a preset level threshold, to obtain an important knowledge point cluster; Based on the basic knowledge point cluster and the important knowledge point cluster, test questions of different difficulty levels are generated to form a target question bank, and the target question bank is used to map on a learning map, so as to generate a target learning trajectory of the student in the process through the learning map, and recommend target review materials suitable for the student to the student based on the target learning trajectory.

2. The method for recommending review materials according to claim 1, characterized in that: The extracting of textbook knowledge points contained in the textbook text and combining the textbook knowledge points according to their difficulty levels to obtain a plurality of textbook knowledge point sets with different difficulty levels to form a basic knowledge point cluster includes: Extracting all the teaching material knowledge points in the teaching material text; Conducting difficulty level evaluation on each of the textbook knowledge points in all the textbook knowledge points to obtain the difficulty level of each textbook knowledge point; Respectively combining the textbook knowledge points of different difficulty levels among all the textbook knowledge points into different basic knowledge point sets; the textbook knowledge points in the same basic knowledge point set have the same difficulty level; All basic knowledge point sets are combined into the basic knowledge point cluster.

3. The method for recommending review materials according to claim 1, characterized in that: The preset knowledge point screening model is used to screen out the test knowledge points whose difficulty level is greater than the preset level threshold from all the test knowledge points in the history question bank, and the important knowledge point clusters obtained include: Obtain the examination frequency of each of the test question knowledge points in the history question bank, the test question answering accuracy rate corresponding to each of the test question knowledge points uploaded by the student, and the correlation between each of the test question knowledge points and other knowledge points in the test question knowledge points, and obtain the weights corresponding to the examination frequency, the test question answering accuracy rate, and the correlation; the difficulty level is a comprehensive indicator of the examination frequency, the test question answering accuracy rate, and the correlation; Calculate the difficulty level of each test question knowledge point according to the examination frequency of each test question knowledge point, the test question answer accuracy rate, the correlation degree and the respective corresponding weights; The test question knowledge points whose difficulty levels are greater than the preset level threshold among all the test question knowledge points are constructed as the important knowledge point cluster.

4. The method for recommending review materials according to claim 3, characterized in that: Calculating the difficulty level of each test question knowledge point according to the examination frequency of each test question knowledge point, the test question answer accuracy, the correlation degree and the respective corresponding weights includes: According to the preset difficulty level evaluation algorithm, the difficulty level of each knowledge point of the test question is calculated respectively. ; The calculation formula of the preset difficulty level evaluation algorithm is: in, The test frequency of each test knowledge point in the history question bank, the accuracy rate of the test answers corresponding to each test knowledge point uploaded by the student, and the correlation between each test knowledge point and other knowledge points in all test knowledge points are respectively are the weights corresponding to the examination frequency, the test question answering accuracy and the correlation degree respectively.

5. The method for recommending review materials according to claim 1, characterized in that: The mapping on the learning map to generate the target learning trajectory of the student process through the learning map includes: Constructing the test questions of different difficulty levels in the target test bank into a learning map; the learning map includes the same number of learning grids as the test questions in the target test bank, and each learning grid corresponds to a test question in the target test bank; Marking the learning grid corresponding to the practiced test questions of the student in the learning map; The learning grids corresponding to the practiced test questions are connected to obtain the target learning trajectory.

6. The method for recommending review materials according to claim 5, characterized in that: The step of constructing the test questions of different difficulty levels in the target question bank into a learning map comprises: Performing correlation analysis on the test questions of different difficulty levels to obtain correlations between the test questions of different difficulty levels; Arranging the test questions of different difficulty levels according to the correlation between the test questions of different difficulty levels to obtain arranged test questions of different difficulty levels; The learning map is generated based on the arranged test questions of different difficulty levels.

7. The method for recommending review materials according to claim 1, characterized in that: The recommending to the student target review materials adapted to the student based on the target learning trajectory comprises: According to the pre-established mapping relationship between the learning track and the review materials, searching for the target review materials corresponding to the target learning track; The target review material is recommended to the student.

8. A device for recommending review materials, characterized in that: include: An acquisition unit is used to acquire textbook texts and history question banks; A combination unit, used to extract the textbook knowledge points contained in the textbook text, and combine the textbook knowledge points according to the difficulty level, so as to obtain a set of textbook knowledge points with different difficulty levels to form a basic knowledge point cluster; A screening unit, configured to screen out test knowledge points whose difficulty level is greater than a preset level threshold from all test knowledge points in the history test bank using a preset knowledge point screening model, to obtain an important knowledge point cluster; A generating unit, for generating test questions of different difficulty levels to form a target question bank based on the basic knowledge point cluster and the important knowledge point cluster, wherein the target question bank is used for mapping on a learning map to generate a target learning trajectory of a student in the learning process through the learning map; A recommendation unit is used to recommend target review materials suitable for the students to the students based on the target learning trajectory.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method for recommending review materials according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method for recommending review materials according to any one of claims 1-7.

11. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for recommending review materials according to any one of claims 1 to 7.

Images