Mathematical teaching resource acquisition method and system based on knowledge graph

Abstract

The invention relates to the field of resource acquisition, in particular to a mathematical teaching resource acquisition method and system based on a knowledge graph, and the system comprises an operation terminal which is used for providing interface display and interaction; the teaching resource module is used for storing teaching resources, and the teaching resources are classified according to knowledge point types; the exercise module is used for providing an exercise page, a plurality of exercises belonging to different knowledge points are arranged in the exercise page, and the exercises are bound with data of the knowledge points to which the exercises belong; the interest analysis module is used for setting consulting time when the exercise begins, the consulting time is used for consulting all exercises in the exercise page, and the interest analysis module is used for recording the persistence time of the exercises at different knowledge points on the operation terminal interface within the consulting time; interest values for different knowledge points are generated based on the persistence time weights; and the operation terminal pushes the teaching resources based on the interest value proportion. By adopting the technical scheme of the invention, the learning interest of the user can be analyzed based on the interest analysis module, so that the pushing amount in the aspect of user interest is increased.

Description

Technical Field

[0001] The present invention relates to the field of resource acquisition, and in particular to a method and system for acquiring mathematics teaching resources based on a knowledge graph. Background Art

[0002] The knowledge graph is a special graph structure that contains rich semantic knowledge and can greatly improve the accuracy and interpretability of information processing. It presents complex data in a structured form by constructing a relationship network between entities, thereby helping users better understand the intrinsic connection between data. In the knowledge graph, knowledge and its associations constitute triples, that is, in the form of "entity-relationship-entity". Multiple triples are interconnected through node relationships to form a network structure. With the development of educational informatization, mathematics teaching resources are becoming increasingly abundant, but at the same time they are also facing problems such as information overload and data explosion. Learners often need to spend a lot of time and energy to find and screen teaching resources that suit them. In addition, the correlation between different teaching resources is not strong, making it difficult to form a systematic knowledge system, which also affects the learning effect of learners.

[0003] In the prior art, for example, patent publication number CN118114765A discloses a method and system for acquiring mathematics teaching resources based on knowledge graphs, which matches the required content through the semantic coding feature vector of students' questions. However, interest is the best teacher in teaching. By grasping students' interests and expanding their learning, students' learning initiative can be improved.

[0004] In regular exams, each candidate is guaranteed the same time to answer questions. There is a period of time before answering that students can only read the questions. Most students will read the questions in a non-sequential manner, and some students will answer the questions they have read first after starting to answer them. Students may not be able to complete the questions correctly. In this process, students' reading in a non-sequential manner can be seen as an interest-oriented choice. Based on this phenomenon, we can judge students' interest orientation and make the acquisition of mathematics teaching resources focus on students' interests, so as to improve students' learning enthusiasm and complete their knowledge. Summary of the invention

[0005] To solve the above problems, the present invention provides a method and system for acquiring mathematics teaching resources based on knowledge graph, which can analyze user learning interests based on an interest analysis module, thereby increasing the amount of push based on user interests.

[0006] In order to achieve the above object, the technical solution of the present invention is as follows: a mathematics teaching resource acquisition system based on knowledge graph, comprising:

[0007] Operation terminal: used to provide interface display and interaction;

[0008] Teaching resource module: used to store teaching resources, which are classified by knowledge point type;

[0009] Exercise module: used to provide an exercise page, which contains several exercises belonging to different knowledge points, and each exercise is bound to the corresponding knowledge point data;

[0010] Interest analysis module: A review time is set at the beginning of the exercise. The review time is used to review all exercises in the exercise page. The interest analysis module is used to record the temporary stay time of the operation terminal interface at different knowledge points during the review time; the interest value of different knowledge points is generated based on the weight of the temporary stay time;

[0011] The operation terminal pushes teaching resources based on the interest value ratio.

[0012] The above scheme has the following beneficial effects:

[0013] 1. This solution uses the operation terminal for display and interaction, and users can obtain and learn teaching resources through the operation terminal. The teaching resource module is used to store teaching resources and classify teaching resources by knowledge point type. Users can learn a variety of detailed knowledge points to complete overall knowledge learning.

[0014] 2. This solution extracts user interest points through the practice module. Based on the principle that most students will bypass the order of questions to read and answer in regular exams, students will review all the exercises on the exercise page during the review time. Since they cannot answer at this time, students will compare different questions and choose questions that they are more willing to answer to read carefully. By extracting the time students spend on different questions, the user's interest in learning a certain type of knowledge point can be detected. In subsequent user learning, the amount of knowledge points that users are interested in will be increased first, so that users are guided by their interests and strengthen their desire to learn.

[0015] 3. In this solution, during the review process, users tend to focus on more difficult questions first because they just want to take a look but do not need to answer them directly. However, in such questions, a large amount of knowledge points are required and it is difficult for users to fully grasp them. Therefore, making interest recommendations based on the knowledge points of the corresponding questions can often fill in the gaps and improve the user's knowledge.

[0016] Compared with the existing technology, the existing technology often prefers to push knowledge types that users actively ask or have high error rates, and often ignores the fact that users lack knowledge due to low interest in related knowledge. Even if they obtain relevant information, their desire and motivation to learn are still not high. By designing the reference time, we can use the activities of students before answering in regular exams to locate students' interests, thereby extending students' knowledge based on their interests.

[0017] Furthermore, the interest analysis module is also used to bind user information, and the user information is provided with a total interest value, which is the accumulated value of the interest value generated by the user during the browsing time.

[0018] Beneficial effects: The formation and judgment of interest is a long process, so the user's information is imported, and the user's interest orientation is evaluated over a long period of time through multiple interest analyses during the browsing time.

[0019] Furthermore, a timestamp is additionally generated when the total interest value is generated, and each interest value is multiplied by a time decay coefficient when the total interest value is calculated.

[0020] Beneficial effects: The formation and judgment of interest is a long process, which will cause the focus of interest to change with the passage of time and self-improvement. Therefore, when measuring the user's interest, it is necessary to add a time decay coefficient so that the evaluation of the user's interest can change with the passage of time.

[0021] Furthermore, the time attenuation coefficient is a piecewise function, the x-axis of the piecewise function is the time distance, the y-axis of the piecewise function is the multiplier value, the time distance is the current time minus the timestamp, the multiplier value is 1 when the time distance is 0 to 1 month, the multiplier value is 0.6 when the time distance is 1 to 3 months, the multiplier value is 0.3 when the time distance is 3 to 6 months, the multiplier value is 0.1 when the time distance is 6 to 12 months, and the multiplier value is 0 when the time distance is greater than 12 months.

[0022] Beneficial effect: The multi-stage design of the time attenuation coefficient can dilute the original interest value based on the length of time that has passed, thereby better evaluating the current user's knowledge point interest distribution.

[0023] Furthermore, teaching resources are stored in a tree structure, the nodes of the tree structure are all knowledge points, and the parent nodes of the nodes are all the previous knowledge points of the current node.

[0024] Beneficial effects: By storing teaching resources in a tree structure, the retrieval of teaching resources can be distributed along the learning progress, and relevant knowledge points can be quickly located through the location of the corresponding knowledge points.

[0025] Furthermore, the operation terminal is used to record the user's learning time at different knowledge points, and when the learning time exceeds a preset value, the knowledge point is marked as learned.

[0026] Beneficial effects: The operation terminal can record the user's learning time on different knowledge points, evaluate the user's mastery of different knowledge points, and facilitate the expansion of intelligent push.

[0027] Furthermore, when the parent node of the knowledge point node is not marked as learned, recording the learning time of the current node is invalid.

[0028] Beneficial effect: Learning needs to be gradual, so learning across knowledge points cannot guarantee that users can truly master the knowledge. Therefore, when the parent node of the knowledge point node is not marked as learned, the user's learning is not considered to have acquired knowledge.

[0029] Furthermore, the practice module is used to collect user practice results and generate the accuracy of exercises on different knowledge points. The accuracy is calculated based on the time decay coefficient and the accuracy is marked on the knowledge point.

[0030] Beneficial effect: The mere existence of learning time does not mean that the user has mastered the corresponding knowledge. The exercises provided by the practice module can monitor whether the user has fully mastered the corresponding knowledge points, thereby more accurately judging the user's learning status. The accuracy is also calculated based on the time decay coefficient, thus reflecting the current user's knowledge level.

[0031] Furthermore, when a high-interest value knowledge point node has a parent node set with low accuracy or not learned, the parent node set with low accuracy or not learned and the high-interest value knowledge point node are bundled and pushed.

[0032] Beneficial effect: Since user interests are located only by looking up time, the knowledge points that users are interested in may not be learned by the users at this time. Therefore, when the user's high-interest knowledge point nodes have low accuracy or unlearned parent node sets, the low accuracy or unlearned parent node sets and high-interest knowledge point nodes are bundled to complete the user's knowledge, and the user's uninterested content can be bundled into it with interest as an inducement, thereby driving the user to learn and understand other knowledge points.

[0033] The method for acquiring mathematics teaching resources based on knowledge graph includes the following steps:

[0034] Step 1: Study through the teaching resources pushed by the operation terminal. The operation terminal will record the user's learning time on different knowledge points;

[0035] Step 2: Practice through the operating terminal. At the beginning of the practice, there is a review time. During the review time, only questions can be read. The interest analysis module calculates the user's interest value for different knowledge points based on the user's stay time on different knowledge point exercises during the review time;

[0036] Step 3: Retrieve high-interest value nodes based on the tree structure of teaching resources, and bundle the high-interest value nodes with their low-accuracy or unlearned parent node set content.

[0037] Step 4: The operating terminal pushes teaching resources based on the interest value ratio, so that users have a high probability of obtaining the knowledge points that complement their interests.

[0038] Beneficial effects: Users can acquire and learn teaching resources based on the operating terminal, and push corresponding interest content through the collection and detection of user interests, and use the interest content to drive the learning of other content that has not been mastered proficiently. It enables users to be guided by their interests and gradually extend their knowledge mastery.

[0039] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of an embodiment of a mathematics teaching resource acquisition system based on a knowledge graph of the present invention;

[0041] Figure 2 It is a schematic diagram of an embodiment of a method for acquiring mathematics teaching resources based on knowledge graph of the present invention. DETAILED DESCRIPTION

[0042] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0044] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0045] The following is further described in detail through specific implementation methods:

[0046] As attached Figure 1 To Attachment Figure 2 As shown: A method and system for acquiring mathematics teaching resources based on knowledge graph, including:

[0047] Operation terminal: used to provide interface display and interaction. The operation terminal can be a conventional storage and interaction device, such as a mobile phone and a computer.

[0048] Teaching resource module: used to store teaching resources. Teaching resources are classified by knowledge point type. Teaching resources can be texts, pictures, audios and videos mainly including mathematical concepts, theorems, formulas, example explanations and logical analysis. Teaching resources are stored in a tree structure. The nodes of the tree structure are all knowledge points, and the parent nodes of the nodes are all the prerequisite knowledge points for learning the current node.

[0049] Exercise module: used to provide an exercise page, which contains several exercises belonging to different knowledge points, and each exercise is bound to the corresponding knowledge point data.

[0050] Interest analysis module: A review time is set at the beginning of the exercise, and the review time lasts for 1 to 5 minutes. The review time is used to review all exercises in the exercise page. The interest analysis module is used to record the time the terminal interface stays on exercises of different knowledge points during the review time; and the interest value for different knowledge points is generated based on the weight of the stay time.

[0051] The operation terminal pushes teaching resources based on the interest value ratio.

[0052] Users can obtain and learn teaching resources through the operating terminal. The teaching resource module is used to store teaching resources and classify them by knowledge point type. Users can learn a variety of detailed knowledge points to complete overall knowledge learning. By storing teaching resources in a tree structure, the retrieval of teaching resources can be distributed along the learning progress, and the relevant knowledge points can be quickly located by the location of the corresponding knowledge points.

[0053] The practice module can generate exercise pages. The exercises in the exercise pages are generated from multiple knowledge points and contain different difficulty levels. A single exercise can correspond to multiple knowledge points. Before users practice exercises, there will be a review time. The review time is for users to flip through the exercise pages. During the review time, since users do not need to answer, they will skip the order of questions and select questions that they are interested in from all questions to read, and there is a tendency to challenge the difficulty. The interest analysis module captures the user's behavior during the review time and analyzes the user's interests. By capturing the user's stay time on exercises at different knowledge points, the user's interest in different knowledge points is analyzed. Therefore, the interest value for different knowledge points is generated based on the stay time weight.

[0054] The operating terminal pushes teaching resources based on the interest value ratio, so that users can obtain more information related to their own interests, which is convenient for improving users' learning initiative by catering to their interests.

[0055] The interest analysis module is also used to bind user information. The user information has a total interest value, which is the cumulative value of the interest value generated by the user during the query time. When the total interest value is generated, a timestamp is additionally generated. When the total interest value is calculated, each interest value is multiplied by the time decay coefficient. The time decay coefficient is a piecewise function. The x-axis of the piecewise function is the time distance, and the y-axis of the piecewise function is the multiplier value. The time distance is the current time minus the timestamp. When the time distance is 0 to 1 month, the multiplier value is 1, when the time distance is 1 to 3 months, the multiplier value is 0.6, when the time distance is 3 to 6 months, the multiplier value is 0.3, when the time distance is 6 to 12 months, the multiplier value is 0.1, and when the time distance is greater than 12 months, the multiplier value is 0.

[0056] The formation and judgment of interest is a long process, so we import user information and evaluate the user's interest orientation over a long period of time through multiple interest analyses during the reading time. As time goes by and as the user improves, their interests and focus will change. Therefore, when measuring the user's interest, it is necessary to add a time decay coefficient so that the evaluation of the user's interest can change with the passage of time. The multi-stage design of the time decay coefficient can dilute the original interest value based on the length of time that has passed, thereby better evaluating the current user's knowledge point interest distribution.

[0057] The operation terminal is used to record the user's learning time at different knowledge points. When the learning time exceeds the preset value, the knowledge point is marked as learned. When the parent node of the knowledge point node is not marked as learned, recording the learning time of the current node is invalid.

[0058] The operation terminal can record the user's learning time at different knowledge points, evaluate the user's mastery of different knowledge points, and facilitate the expansion of intelligent push. Learning needs to be gradual, so learning across knowledge points cannot guarantee that users can truly master the knowledge. Therefore, when the parent node of the knowledge point node is not marked as learned, the user's learning is not considered to have acquired knowledge.

[0059] The practice module is used to collect user practice results and generate the accuracy of exercises for different knowledge points. The accuracy is calculated based on the time decay coefficient and the accuracy is marked on the knowledge point.

[0060] The mere existence of learning time does not mean that the user has mastered the corresponding knowledge. The exercises provided by the practice module can monitor whether the user has fully mastered the corresponding knowledge points, thereby more accurately judging the user's learning status. The accuracy rate is also calculated based on the time decay coefficient. The high error rate in the past is difficult to measure the current knowledge level. Therefore, it is necessary to use the time decay coefficient to reduce the reference ratio of the past time to evaluate the current user's knowledge level.

[0061] When a high-interest knowledge point node has a low-accuracy or unlearned parent node set, the low-accuracy or unlearned parent node set and the high-interest knowledge point node are bundled and pushed.

[0062] Since user interests are located only by looking up the time, the knowledge points that users are interested in may not have the corresponding learning ability at this time. The parent node set is a set of low-accuracy or unlearned parent nodes, as well as low-accuracy or unlearned parent nodes of their parent nodes. This set can cover the knowledge required to improve the mastery of the current high-interest value knowledge point nodes. Therefore, when the user's high-interest value knowledge point nodes have a low-accuracy or unlearned parent node set, bundling the low-accuracy or unlearned parent node set with the high-interest value knowledge point node can complement the user's knowledge, and can use interest as an inducement to bundle the content that the user is not interested in, thereby driving the user's learning and understanding of other knowledge points.

[0063] The method for acquiring mathematics teaching resources based on knowledge graph includes the following steps:

[0064] Step 1: Study through the teaching resources pushed by the operation terminal. The operation terminal will record the user's learning time on different knowledge points;

[0065] Step 2: Practice through the operating terminal. At the beginning of the practice, there is a review time. During the review time, only questions can be read. The interest analysis module calculates the user's interest value for different knowledge points based on the user's stay time on different knowledge point exercises during the review time;

[0066] Step 3: Retrieve high-interest value nodes based on the tree structure of teaching resources, and bundle the high-interest value nodes with their low-accuracy or unlearned parent node set content.

[0067] Step 4: The operating terminal pushes teaching resources based on the interest value ratio, so that users have a high probability of obtaining the knowledge points that complement their interests.

[0068] Beneficial effects: Users can acquire and learn teaching resources based on the operating terminal, and push corresponding interest content through the collection and detection of user interests, and use the interest content to drive the learning of other content that has not been mastered proficiently. It enables users to be guided by their interests and gradually extend their knowledge mastery.

[0069] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the present invention.

Claims

1. The mathematics teaching resource acquisition system based on knowledge graph is characterized by: include: Operation terminal: used to provide interface display and interaction; Teaching resource module: used to store teaching resources, which are classified by knowledge point type; Exercise module: used to provide an exercise page, which contains several exercises belonging to different knowledge points, and each exercise is bound to the corresponding knowledge point data; Interest analysis module: A review time is set at the beginning of the exercise. The review time is used to review all exercises in the exercise page. The interest analysis module is used to record the temporary stay time of the operation terminal interface at different knowledge points during the review time; the interest value of different knowledge points is generated based on the weight of the temporary stay time; The operation terminal pushes teaching resources based on the interest value ratio.

2. According to the knowledge graph-based mathematics teaching resource acquisition system of claim 1, it is characterized in that: The interest analysis module is also used to bind user information. The user information is provided with a total interest value, which is the accumulated value of the interest value generated by the user during the browsing time.

3. The mathematics teaching resource acquisition system based on knowledge graph according to claim 2 is characterized in that: When the total interest value is generated, a timestamp is additionally generated. When the total interest value is calculated, each interest value is multiplied by the time decay coefficient.

4. The mathematics teaching resource acquisition system based on knowledge graph according to claim 3 is characterized in that: The time attenuation coefficient is a piecewise function. The x-axis of the piecewise function is the time distance, and the y-axis of the piecewise function is the multiplier value. The time distance is the current time minus the timestamp. When the time distance is 0 to 1 month, the multiplier value is 1. When the time distance is 1 to 3 months, the multiplier value is 0.

6. When the time distance is 3 to 6 months, the multiplier value is 0.

3. When the time distance is 6 to 12 months, the multiplier value is 0.

1. When the time distance is greater than 12 months, the multiplier value is 0.

5. The mathematics teaching resource acquisition system based on knowledge graph according to claim 4 is characterized in that: Teaching resources are stored in a tree structure. The nodes of the tree structure are all knowledge points, and the parent nodes of the nodes are all the prerequisite knowledge points for learning the current node.

6. The mathematics teaching resource acquisition system based on knowledge graph according to claim 5 is characterized in that: The operation terminal is used to record the user's learning time at different knowledge points. When the learning time exceeds a preset value, the knowledge point is marked as learned.

7. The mathematics teaching resource acquisition system based on knowledge graph according to claim 6 is characterized in that: When the parent node of a knowledge point node is not marked as learned, recording the learning time of the current node is invalid.

8. The mathematics teaching resource acquisition system based on knowledge graph according to claim 7 is characterized in that: The practice module is used to collect user practice results and generate the accuracy of exercises for different knowledge points. The accuracy is calculated based on the time decay coefficient and the accuracy is marked on the knowledge point.

9. The mathematics teaching resource acquisition system based on knowledge graph according to claim 8 is characterized in that: When a high-interest knowledge point node has a low-accuracy or unlearned parent node set, the low-accuracy or unlearned parent node set and the high-interest knowledge point node are bundled and pushed.

10. The method for acquiring mathematics teaching resources based on knowledge graph based on the mathematics teaching resource acquisition system based on knowledge graph according to claim 9 is characterized in that: The following steps are involved: Step 1: Study through the teaching resources pushed by the operation terminal. The operation terminal will record the user's learning time on different knowledge points; Step 2: Practice through the operating terminal. At the beginning of the practice, there is a review time. During the review time, only questions can be read. The interest analysis module calculates the user's interest value for different knowledge points based on the user's stay time on different knowledge point exercises during the review time; Step 3: Retrieve high-interest value nodes based on the tree structure of teaching resources, and bundle high-interest value nodes with their low-correctness or unlearned parent node set content; Step 4: The operating terminal pushes teaching resources based on the interest value ratio, so that users have a high probability of obtaining the knowledge points that complement their interests.

Images