Knowledge point interaction method, device, electronic device and readable storage medium

Abstract

The present application discloses a knowledge point interaction method, device, electronic device and readable storage medium. In an embodiment of the present application, in response to a learning recommendation trigger event corresponding to the first user, a first learning path recommended for the first user is displayed on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matched with the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, and the knowledge nodes are configured with corresponding knowledge points and learning plans for the knowledge points; in response to a knowledge point trigger operation on the first learning path, at least part of the learning content in the learning plan corresponding to the triggered knowledge node is displayed, which can improve the recommendation effect of learning recommendations for users.

Description

Technical Field

[0001] The present application relates to the technical field of knowledge point interaction, and in particular to a knowledge point interaction method, device, electronic device, and readable storage medium. Background Art

[0002] Under the tide of the Internet, recommending learning to users is an important research direction in the current field of educational technology. At present, a knowledge point association path can be preset to recommend to different users based on the same knowledge point association path. However, due to the different learning situations of different users, if recommendations are made to users based on the same knowledge point association path, it is impossible to take into account the personalized needs of different users, resulting in poor recommendation effects for users' learning. Summary of the Invention

[0003] The embodiments of the present application provide a knowledge point interaction method, device, electronic device and computer-readable storage medium, which can improve the recommendation effect of learning recommendations for users.

[0004] In a first aspect, an embodiment of the present application provides a knowledge point interaction method, the method comprising:

[0005] In response to a learning recommendation trigger event corresponding to a first user, displaying a first learning path recommended for the first user on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matching the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, wherein the knowledge nodes are configured with corresponding knowledge points and learning solutions for the knowledge points;

[0006] In response to a triggering operation on a knowledge point of the first learning path, at least a portion of the learning content in the learning solution corresponding to the triggered knowledge node is displayed.

[0007] In a second aspect, an embodiment of the present application further provides a knowledge point interaction device, the device comprising:

[0008] a path display module, configured to display, in response to a learning recommendation trigger event corresponding to a first user, a first learning path recommended for the first user on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matching the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, wherein the knowledge nodes are configured with corresponding knowledge points and learning solutions for the knowledge points;

[0009] The display module is configured to, in response to a triggering operation on a knowledge point of the first learning path, display at least a portion of the learning content in the learning solution corresponding to the triggered knowledge node.

[0010] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a memory storing a computer program, which, when executed by a processor, enables the processor to execute any one of the knowledge point interaction methods provided in the embodiment of the present application.

[0011] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which includes a computer program. When the computer program runs on an electronic device, the computer program is used to enable the electronic device to execute any knowledge point interaction method provided in the embodiment of the present application.

[0012] In an embodiment of the present application, in response to a learning recommendation trigger event corresponding to the first user, a first learning path recommended for the first user is displayed on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matched with the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, and the knowledge nodes are configured with corresponding knowledge points and learning plans for the knowledge points; in response to a knowledge point trigger operation on the first learning path, at least part of the learning content in the learning plan corresponding to the triggered knowledge node is displayed, so that by matching a reference user for the corresponding user, personalized learning recommendations are made to the corresponding user based on the learning path of the reference user, thereby improving the recommendation effect of learning recommendations for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 This is a flow chart of an embodiment of the method for interacting with knowledge points provided in the embodiments of the present application;

[0015] Figure 2 This is a schematic diagram of a learning map provided in an embodiment of the present application;

[0016] Figure 3 This is a schematic diagram of a starry sky provided in an embodiment of the present application;

[0017] Figure 4 This is a schematic diagram of a shopping scene provided in an embodiment of the present application;

[0018] Figure 5 This is a schematic diagram of an exercise recommendation page provided in an embodiment of the present application;

[0019] Figure 6This is a schematic diagram of the structure of the knowledge point interaction device provided in an embodiment of the present application;

[0020] Figure 7 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0022] Before explaining the embodiments of the present application in detail, some terms involved in the embodiments of the present application are first explained.

[0023] In the description of the embodiments of the present application, the terms "first", "second", etc. may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0024] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for interacting with knowledge points. Specifically, the method for interacting with knowledge points in the embodiments of the present application can be performed by an electronic device, wherein the electronic device can be a terminal or a server. The terminal can be a terminal device such as a smart phone, a tablet computer, a laptop computer, a touch screen, a game console, a personal computer (PC), a personal digital assistant (PDA), etc. The terminal can also include a client, which can be a game application client, a browser client carrying a game program, or an instant messaging client, etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0025] For example, the electronic device is illustrated by taking a terminal as an example. The terminal can display a first learning path recommended for the first user on a graphical user interface in response to a learning recommendation trigger event corresponding to the first user, wherein the first learning path is generated based on the second learning path of a reference user matched with the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, and the knowledge nodes are configured with corresponding knowledge points and learning plans for the knowledge points; in response to a knowledge point trigger operation on the first learning path, at least part of the learning content in the learning plan corresponding to the triggered knowledge node is displayed.

[0026] Based on the above problems, the embodiments of the present application provide a knowledge point interaction method, device, electronic device and computer-readable storage medium, which can improve the recommendation effect of learning recommendations for users.

[0027] The following is a detailed description of each embodiment in conjunction with the accompanying drawings. It should be noted that the order in which the following embodiments are described does not limit the preferred order of the embodiments. Although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be performed in an order different from that shown in the drawings.

[0028] In this embodiment, a terminal is used as an example to illustrate that this embodiment provides a knowledge point interaction method, such as Figure 1 As shown, the specific process of the interaction method of this knowledge point can be as follows:

[0029] 101. In response to a learning recommendation trigger event corresponding to a first user, a first learning path recommended for the first user is displayed on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matching the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, and the knowledge nodes are configured with corresponding knowledge points and learning plans for the knowledge points.

[0030] Among them, the above-mentioned first user is the user who currently needs learning recommendation. The first user is the user to whom the above-mentioned terminal belongs. The above-mentioned first user may be a user with a low learning level, such as a user who has just come into contact with a certain knowledge point, or a user whose progress in mastering a certain knowledge point after a period of time is still lower than a preset threshold, etc. The specific setting can be made according to the actual scenario and is not limited here.

[0031] In this embodiment, in order to enable personalized recommendations to the first user, the terminal can determine a reference user that matches the first user for recommendation based on the first user's learning situation, that is, based on the learning path of the reference user, generate a learning path recommended to the first user, and display the learning path for the first user on the graphical user interface provided by the terminal, so that the first user can refer to the learning path for learning, and assist the first user to more effectively master the knowledge points on the first learning path.

[0032] There is a certain learning order among the knowledge points to which the knowledge nodes in the above-mentioned learning path belong, and the learning order is the order of the knowledge nodes in the learning path.

[0033] The above-mentioned learning plan includes but is not limited to the learning resources corresponding to the knowledge points (such as videos, courseware, exercises and other learning materials), the time distribution when learning the knowledge points (such as the amount of time spent on learning specific learning resources in a preset time period, including resource usage time and exercise completion time, etc.), learning outcomes (such as reference to the user's performance in the exercises, including the accuracy rate of answers and error types, etc.), learning strategies (such as reference to the user's review frequency and review methods, including re-reading or repeated practice, etc.), etc., which can be set according to specific needs and are not limited here.

[0034] It should be noted that since there may or may not be a specific relationship between different knowledge points, the corresponding path can be determined based on the relationship between knowledge points. For example, a user can only learn knowledge point B based on knowledge point A after mastering knowledge point A.

[0035] Among them, the relationship between knowledge points can be modeled through the knowledge graph to form a knowledge network, thereby building structured relationships for knowledge points to assist the user system in learning the content corresponding to each knowledge point in the knowledge graph.

[0036] It is understandable that if the path recommendation for the first user is based solely on the knowledge graph, there is usually a lack of real learning effect verification, and it is difficult to recommend a suitable learning path to the first user. Therefore, by matching a reference user for the first user, the actual learning path of the reference user is used as a reference for personalized learning recommendations, ensuring that the path recommended to the first user can meet the user's personalized needs and fit the user's actual learning situation.

[0037] It should be noted that since the reference user is the user required to recommend a path to the first user, the learning performance of the reference user should be better than that of other users. The learning path of the reference user with excellent performance can be used as a benchmark to provide the first user with a real and effective learning path for the reference user from not mastering at least one knowledge point to mastering at least one knowledge point. Since the learning path of the reference user has achieved good learning results in a real learning situation, the learning path of the reference user can serve as a reliable basis for recommending a path.

[0038] Furthermore, since there may be multiple candidate users with excellent learning performance, in order to select a candidate as a reference user, it is also possible to determine whether the candidate user matches the first user based on the learning data of the candidate user and the first user. For example, it is possible to determine whether the candidate user matches the first user by determining the similarity between the learning data of the candidate user and the first user. That is, the higher the similarity, the higher the degree of match between the candidate user and the first user.

[0039] The learning data of the candidate user and the learning data of the first user should be at the same learning level, that is, the learning data of the candidate user obtained should be the learning data of the candidate user when the candidate user is at the current learning level of the first user, for example, as shown in Table 1 below:

[0040]

[0041] Table 1

[0042] If there are currently multiple knowledge points in a certain order, namely knowledge point A, knowledge point B, knowledge point C and knowledge point D, if the candidate user has currently mastered knowledge point C and needs to continue learning knowledge point D, and the first user is currently at knowledge point B and needs to continue learning knowledge point C, then it is necessary to obtain the learning data between knowledge point A and knowledge point B of the candidate user and compare it with the current learning data of the first user (learning data between knowledge point A and knowledge point B) to determine whether the candidate user can be used as a reference user.

[0043] By analyzing the similarity between the learning data of the first user and the reference user in this way, a learning path that matches the reference user can be recommended based on the first user's current level, thereby providing a highly personalized learning suggestion. This can help the first user find suitable learning content at their current level more efficiently. In addition, by unifying the learning level, by comparing the reference user's learning data with the first user's learning data, it can help identify the knowledge points that the first user is missing or lagging behind in the learning process. This method can help the first user fill in the gaps in basic knowledge, thereby improving the first user's learning effect in a more targeted manner.

[0044] Most importantly, since it has been determined that reference users can achieve the expected learning results based on such a learning path, such as learning knowledge point C, it is more convincing than the learning path derived from the knowledge graph. Because this learning path is a learning path that has been verified to be effective by reference users, the learning path built based on real success cases will be more accurate.

[0045] Furthermore, the first user will be subjectively motivated to learn by seeing similarities between themselves and the reference user at certain academic stages. By observing the reference user's learning trajectory, the first user can directly copy the reference user's experience and methods at a certain stage of learning, thereby reducing the first user's learning time by adopting more beneficial learning methods and techniques.

[0046] In some embodiments, when the first learning path is displayed on a graphical user interface, the starting point and end point of the first learning path can be marked so that the first user or a user associated with the first user can view the learning path more intuitively. The first user may be a student, and the users associated with the first user may be users with a family relationship, users with a teacher-student relationship, etc. The specific settings can be made according to needs and are not limited here.

[0047] In some embodiments, due to the different relationships between different knowledge points, the learning difficulty, learning content, learning time and other corresponding characteristics of the learning plans between different knowledge points are different. Therefore, in order to be able to more intuitively clarify the learning difficulty between knowledge points, the display style of the corresponding path segment in the first learning path can be set, that is, the display style of the path segment in the above-mentioned first learning path includes at least one, wherein the above-mentioned display style is used to indicate the solution characteristics of the learning plan for the knowledge point corresponding to the above-mentioned path segment.

[0048] Among them, the above-mentioned program characteristics include: at least one of learning difficulty, learning time, and learning content.

[0049] The display styles corresponding to different path segments in the first learning path may be the same or different, and may be set according to specific needs, which is not limited here.

[0050] Specifically, the above-mentioned scheme features can be set manually by relevant users, or can be set based on the historical learning data of all users or specific users with the same learning level, or can be set based on the type of knowledge points, etc., and can be set specifically according to needs and is not limited here.

[0051] Among them, the above-mentioned specific user may be a user whose learning similarity with the first user at the same learning level meets the preset similarity conditions. For example, the path segment that the first user currently needs to learn is set to be a path segment composed of the knowledge node corresponding to knowledge point A and the knowledge node corresponding to knowledge point B, which means that the specific user may be a user whose learning similarity with the first user at the level of learning knowledge points before knowledge point A meets the preset similarity conditions. Then, after selecting the specific user that meets the preset similarity conditions, the solution characteristics between knowledge point A and knowledge point B can be determined based on the historical learning data of the specific user between knowledge point A and knowledge point B. For example, the learning difficulty, learning time or learning content between knowledge point A and knowledge point B can be determined based on the historical learning data of the specific user between knowledge point A and knowledge point B.

[0052] In some embodiments, the display style of the path segment includes at least one of the composition structure of the path segment, the length of the path segment, and the curvature of the path segment.

[0053] Among them, the composition structure of the above-mentioned path segments varies according to different application scenarios. For example, if the first learning path is presented on a learning map, the composition structure of the path segments includes but is not limited to traffic sign elements, the above-mentioned geographical environment elements, etc. The traffic sign elements are used to indicate objects set on the path segments, such as traffic lights, driving signs, etc., and the geographical environment elements are used to indicate geographical objects on the path segments, such as hills, bridges, etc., which can be set specifically according to needs and are not limited here.

[0054] Among them, the degree of curvature of the above-mentioned path segment is used to indicate the deformation of the path segment, and can indicate whether the path segment is rugged, that is, the more locations with curvature on the path segment, and / or the greater the curvature of the path segment, the more rugged the path segment is, and the more difficult it is for the user to move on the path segment, that is, the greater the difficulty of learning the knowledge point corresponding to the path segment. Conversely, it means that the path segment is approximately flat, and the less difficult it is for the user to move on the path segment, that is, the less difficult it is to learn the knowledge point corresponding to the path segment.

[0055] It can be understood that since the display style of the above-mentioned path segment can indicate the solution characteristics of the learning solution corresponding to the path segment, the display style of the path segment corresponding to different solution characteristics is also different. For example, if the learning difficulty in the solution characteristics is greater, then the path segment can be controlled to be more rugged. For example, if the learning time in the solution characteristics is longer, then the length of the path segment can be controlled to be longer. For example, if the learning content in the solution characteristics is more, then multiple objects can be set in the composition structure of the path segment, such as traffic sign elements and geographical environment elements in the learning map scene.

[0056] In some embodiments, due to different users' learning plans, the number of path segments between a pair of adjacent knowledge nodes is at least one, and different path segments between the same pair of knowledge nodes correspond to different plan features.

[0057] Exemplarily, if only the learning path of the first user is displayed on the graphical user interface, and / or the learning paths of other users displayed on the graphical user interface are completely different from the learning path of the first user, and / or only one learning plan is generated between the knowledge nodes on the learning path of the first user (such as generating a learning plan based on a reference user), then the number of path segments between a pair of adjacent knowledge nodes is 1.

[0058] Exemplarily, if other users are displayed on the graphical user interface, and the other users have at least one pair of adjacent knowledge nodes that are identical to the learning path of the first user, then the number of path segments between the identical at least one pair of adjacent knowledge nodes is consistent with the number of users with the same user. For example, if three users have at least one pair of adjacent knowledge nodes that are identical to the learning path of the first user, then the number of path segments between the identical at least one pair of adjacent knowledge nodes is three.

[0059] Exemplarily, if at least two learning plans are generated between the knowledge nodes on the learning path of the first user, the number of path segments between a pair of adjacent knowledge nodes can be consistent with the number of generated learning plans. For example, if two learning plans are generated based on two reference users, the number of path segments between a pair of adjacent knowledge nodes is 2.

[0060] In some embodiments, the graphical user interface further includes a first user identifier of the first user, and the first user identifier corresponds to a position on the first learning path, and is used to indicate the learning progress of the first user in the first learning path.

[0061] In this embodiment, the learning path of the first user on the learning path is displayed, wherein the first user may be a student, and the users associated with the first user may be users with a family relationship, users with a teacher-student relationship, etc. The specific settings can be made according to needs and are not limited here.

[0062] It is understandable that as the first user's learning progress in the above-mentioned first learning path improves, the position corresponding to the first user identifier on the above-mentioned first learning path is closer to the end point of the first learning path, that is, the last knowledge point on the first learning path.

[0063] In some embodiments, the above-mentioned graphical user interface also includes a second user identifier, and the above-mentioned second user identifier corresponds to a position on the first path segment of the above-mentioned first learning path, which is used to indicate the learning progress of the second user in the above-mentioned first path segment. The learning path of the above-mentioned second user is at least partially the same as the above-mentioned first learning path, and the same part includes the above-mentioned first path segment.

[0064] In this embodiment, the learning progress of other users on the learning path is synchronously displayed so that the target user can compare the learning progress with his own and understand his own learning situation.

[0065] For example, a preset relationship can be established between the first user and the second user, such as a friend relationship, a classmate relationship, etc. When it is monitored that a certain relationship is satisfied between the first user and the second user, such as a friend relationship, more specifically, a friend relationship with the same academic level, the learning path of the second user corresponding to the second user identifier can be combined with the first learning path of the first user to generate a relationship path network. The relationship path network has the attribute of a friend circle, and the learning situation between the first user and the second user can be viewed by displaying the relationship path network on a graphical user interface.

[0066] Wherein, when the learning path of the second user is at least partially identical to the first learning path, the learning path of the second user corresponding to the second user identifier and the first learning path of the first user are combined and displayed on the same graphical user interface.

[0067] In addition, the learning path of the second user corresponding to the second user identifier may not overlap with the first learning path, that is, the learning path of the second user is different from the first learning path.

[0068] In the case where the learning path of the second user is different from the first learning path, the learning path of the second user may be simply concatenated with the first learning path and then displayed on the graphical user interface.

[0069] Furthermore, because there is no overlapping relationship between the learning path of the second user and the first learning path, the knowledge relationship between the knowledge points corresponding to the knowledge nodes in the learning path of the second user and the knowledge points corresponding to the knowledge nodes in the first learning path can be obtained according to the preset knowledge graph, so as to display the learning path of the second user and the first learning path on the graphical user interface based on the knowledge relationship.

[0070] Specifically, if there is a direct or indirect connection between two knowledge points, for example, one knowledge point is a subsequent knowledge point of another knowledge point, then the two knowledge points can be connected through a certain display form to form a knowledge path. Subsequent knowledge points refer to content that requires the mastery of previous knowledge points in the learning process. For example, the addition and subtraction of fractions depends on students' understanding of fractions and certificate operations. Therefore, students need to master the basic knowledge of fractions before they can understand how to add and subtract fractions. The basic knowledge of fractions can be considered as a previous knowledge point, and the addition and subtraction of fractions can be considered as a subsequent knowledge point.

[0071] Specifically, if there is no direct or indirect connection between two knowledge points, then the two knowledge points can be left unconnected. An indirect relationship means that the learning order and / or dependency between the two knowledge points is weak, and students can master the two knowledge points independently without requiring a specific order.

[0072] In some embodiments, the information indicated by the second user identification includes speed indication information of the second user, and the speed indication information is used to indicate the learning speed of the second user so that the target user can clearly understand the learning speed of other users on the learning path.

[0073] In some embodiments, the graphical user interface further includes learning time identifiers corresponding to adjacent knowledge nodes in the first learning path, and the learning time identifiers are used to indicate the learning time required to complete the path segment between adjacent knowledge nodes.

[0074] Among them, the learning time indicated by the above-mentioned learning time identifier can be the estimated learning time between adjacent knowledge points, or the estimated learning time between all knowledge points in the first learning path, etc. It can be set according to needs and is not limited here.

[0075] For example, Figure 2 、 Figure 3 As shown, Figure 2 and Figure 3 The information arranged in the middle area is the learning time indicator.

[0076] In some embodiments, the method for determining the above-mentioned learning time may include: obtaining knowledge point learning data of multiple historical users between the above-mentioned adjacent knowledge points; clustering the learning time between the above-mentioned adjacent knowledge points based on the above-mentioned knowledge point learning data to obtain at least one clustering result; based on the above-mentioned at least one clustering result, determining the learning time required for the above-mentioned first user to complete the path segment between the above-mentioned adjacent knowledge points.

[0077] The method for obtaining the knowledge point learning data of multiple historical users between the aforementioned adjacent knowledge points can be obtained from an existing database. The knowledge point learning data includes but is not limited to the learning time, learning frequency, learning period, and learning sequence of historical users at different knowledge points. The acquired data should include information on all knowledge points and all learning modules, questions, resources, etc. under the knowledge points as much as possible. By analyzing this data, it is possible to identify key factors affecting learning time and provide a reference for subsequent estimation of learning time.

[0078] Optionally, in order to facilitate a better prediction of the learning time based on the above-mentioned knowledge point learning data, the above-mentioned knowledge point learning data can be preprocessed in advance, for example, the above-mentioned knowledge point learning data can be finely cleaned to delete all incomplete or abnormal records in the knowledge point learning data, such as extreme values and missing values. Then, the knowledge point learning data after deleting some data can be normalized or standardized to ensure that data from different sources and different types are processed on the same scale, thereby improving the stability and prediction accuracy of subsequent predictions of learning time. For example, the Z-score method can be used to standardize the knowledge point learning data to adjust the mean and standard deviation of the data features to ensure that the model does not favor certain features due to differences in data scale.

[0079] Specifically, the above-mentioned clustering of the learning time between the above-mentioned adjacent knowledge points based on the above-mentioned knowledge point learning data to obtain at least one clustering result includes: determining at least one learning indicator of the above-mentioned historical users based on the above-mentioned knowledge point learning data, and the above-mentioned learning indicator is used to indicate the learning participation of the above-mentioned historical users between the above-mentioned adjacent knowledge points; clustering of the learning time between the above-mentioned adjacent knowledge points based on the above-mentioned learning indicators of the above-mentioned historical users to obtain at least one clustering result.

[0080] Among them, the above-mentioned learning indicators include but are not limited to the continuity of learning (i.e. the interval time between learning activities) and the frequency of learning (i.e. the number of learning times per unit time).

[0081] The clustering algorithm used in the above clustering process can be an algorithm such as K-means or hierarchical clustering, which can group time periods with similar learning behaviors into one category, thereby reducing the complexity of the data and providing meaningful classification results for subsequent steps. For example, if a student's knowledge point learning data indicates that they frequently study in a short period of time, then based on this behavioral feature, the knowledge point learning data of other users with similar behavioral features can be clustered into one group. Through clustering, it is possible to help identify student groups with different learning strategies, laying the foundation for customized time estimation.

[0082] Exemplarily, the above-mentioned clustering of the learning time between the above-mentioned adjacent knowledge points based on the above-mentioned knowledge point learning data to obtain at least one clustering result may include: first, collecting and integrating the data of "learning continuity" and "learning frequency" in the knowledge point learning data; second, creating a feature set based on the integrated data to obtain a set of one-dimensional feature vectors, wherein each data point in the feature set contains the values of continuity and frequency; third, using the Z-score method to standardize the data of "learning continuity" and "learning frequency" respectively to ensure that the weight of each factor is appropriate in the clustering process; fourth, using the K-means algorithm to cluster the one-dimensional feature vectors in the feature set, and the algorithm will cluster the learning time into different clustering results based on the combined influence of continuity and frequency.

[0083] Specifically, the above-mentioned method of determining the learning time required for the above-mentioned first user to complete the path segment between the above-mentioned adjacent knowledge points based on the above-mentioned at least one clustering result includes: obtaining the historical learning behavior of the above-mentioned first user; based on the above-mentioned historical learning behavior, determining at least one clustering result matching the above-mentioned first user from the above-mentioned clustering results to obtain a target clustering result; based on the above-mentioned target clustering result, determining the learning time required for the above-mentioned first user to complete the path segment between the above-mentioned adjacent knowledge points.

[0084] In this embodiment, after clustering is completed, based on the first user's historical learning behavior, the clustering results are matched to the group that is most similar to the historical learning behavior. The matching process can take into account the user's past learning experience, such as previous performance in similar learning tasks, time allocation, and learning outcomes.

[0085] Specifically, the matching algorithm can be a cosine similarity calculation algorithm, which can find the group closest to the current learning situation by performing cosine similarity calculation to accurately identify the time group that can reflect the student's current learning mode and ensure the accuracy of subsequent algorithms.

[0086] Exemplarily, based on the above-mentioned historical learning behavior, at least one clustering result matching the above-mentioned first user is determined from the above-mentioned clustering results to obtain the target clustering result, including: first, collecting the historical learning data of the first user, which historical learning data can indicate historical learning behavior, such as learning performance, learning time, time allocation, learning outcomes, etc., among which special attention is paid to data related to "learning continuity" and "learning frequency"; second, the data of at least two dimensions in the historical learning behavior can be integrated to obtain a corresponding vector sequence, for example, the data of the two dimensions of learning continuity and learning frequency are integrated into a multidimensional vector; third, the generated vector sequence is compared with the behavior pattern corresponding to at least one clustering result, and the cosine similarity calculation algorithm is used to calculate the similarity between the vector sequence and the cluster center of each clustering result, and the cluster center with the highest similarity with the first user is selected.

[0087] For example, suppose a student's performance in a learning cycle: the learning continuity is an average interval of 2 days between each learning activity, and the learning frequency is 5 times in a week. Then, through calculation, the vector of the student's current learning cycle is: [2,5]. Compare this vector with at least one clustering result. If the clustering results are set to the following categories: [2.2,5.1], [1.5,6.0], [3.0,4.2], then by calculating the cosine similarity separately, the similarity corresponding to each clustering result can be obtained: 0.9996, 0.9908 and 0.9713. Then, select the clustering result with the highest cosine similarity as the target clustering result.

[0088] In some embodiments, the learning time indicated by the learning time identifier is updated according to the learning status of the knowledge point by the first user in the learning process of the path segment.

[0089] For example, if the first user learns the knowledge points faster during the learning process of the path segment, the learning time is shortened; and if the first user learns the knowledge points slower during the learning process of the path segment, the learning generation is increased.

[0090] In addition, the learning time may be updated based on the first user's learning results of the learning resource in the learning situation.

[0091] Specifically, the updating of the above-mentioned learning time may include: constructing a time prediction model based on the above-mentioned target clustering results; using the above-mentioned time prediction model, predicting the learning time based on the above-mentioned learning situation of the above-mentioned first user to obtain the learning time of the above-mentioned first user.

[0092] Specifically, based on the target clustering results, a Bayesian optimization algorithm can be used to update the data to obtain updated cluster data. This updated cluster data is then fed into a linear regression model, which uses the linear regression algorithm to determine the weight of each feature's influence on learning time. This model is then used to predict the learning time of the first user's planned future learning points based on their learning progress. This ensures that the entire prediction process not only considers individual differences among students but also integrates the overall trends of historical data, providing more personalized and accurate learning time predictions.

[0093] In some embodiments, the display of the first learning path recommended for the first user on the graphical user interface includes: displaying a scene image including at least one scene element on the graphical user interface, and displaying the first learning path in the scene image, wherein the knowledge nodes and the path segments are at least part of the scene elements.

[0094] In this embodiment, since there are multiple recommendation scenarios when making learning recommendations, such as the learning recommendation scenario of map mode, the learning recommendation scenario of starry sky mode, the learning recommendation scenario of fog map mode, and the learning recommendation scenario of shopping mode, it is necessary to set corresponding scene images for different recommendation scenarios, as well as scene elements in the scene images, so as to recommend the first learning path based on the scene elements in the scene image, thereby enabling the first learning path to be recommended in a manner that is more in line with user preferences.

[0095] In some embodiments, for the learning recommendation scenario in map mode, the above-mentioned scene image including at least one scene element is displayed on the above-mentioned graphical user interface, and the above-mentioned first learning path is displayed in the above-mentioned scene image, and the above-mentioned knowledge nodes and the above-mentioned path segments are at least part of the above-mentioned scene elements, which may include: the terminal can display a learning map including at least one map element on the above-mentioned graphical user interface, and display the above-mentioned first learning path in the above-mentioned learning map, and the above-mentioned knowledge nodes and the above-mentioned path segments are at least part of the above-mentioned map elements.

[0096] The map elements serving as knowledge nodes may be location elements in a learning map, so that different location elements correspond to different knowledge nodes.

[0097] For example, Figure 2 As shown, Figure 2 The lower area of the figure shows a learning map, which can be used to display the first learning path, i.e. Figure 2 The learning path consists of points A and B.

[0098] In some embodiments, the above-mentioned learning map may also include a third user identifier of the above-mentioned first user, and the above-mentioned third user identifier includes a virtual vehicle, which is used to indicate that the first user moves on the learning map with the virtual vehicle, and the vehicle style of the above-mentioned virtual vehicle is used to indicate the learning speed of the above-mentioned first user.

[0099] The vehicle style of the virtual vehicle includes, but is not limited to, a bicycle style, an electric vehicle style, a car style, an airplane style, or a walking style, and can be set as needed and is not limited here. If the vehicle style of the virtual vehicle is a walking style, it means that the first user is moving on the learning map by walking.

[0100] It can be understood that since different first users have different learning speeds, different vehicle styles of the virtual vehicle can be corresponding to the first users according to the learning speed of the first users. For example, if the first user's learning speed is very fast, the vehicle style of the virtual vehicle in the third user identifier can be set to an airplane style; if the first user's learning speed is very slow, the vehicle style of the virtual vehicle in the third user identifier can be set to a walking style.

[0101] In some embodiments, the map elements constituting the path segment include: traffic sign elements and / or geographical environment elements, and the traffic sign elements and / or geographical environment elements change according to the learning progress of the first user in the path segment.

[0102] For example, if the above-mentioned traffic sign element is set to a traffic light, it can be determined whether a red light or a green light will be displayed when the first user encounters a traffic light based on the first user's learning progress in the path segment. If the first user's learning progress on the path segment is faster, then a green light can be displayed. If the first user's learning progress on the path segment is slower, then a red light can be displayed.

[0103] In some embodiments, for the learning recommendation scenario of the starry sky mode, the above-mentioned graphical user interface displays a scene image including at least one scene element, and the above-mentioned first learning path is displayed in the above-mentioned scene image, and the above-mentioned knowledge nodes and the above-mentioned path segments are at least part of the above-mentioned scene elements, which may include: the terminal can display a starry sky map on the above-mentioned graphical user interface, and display the above-mentioned first learning path on the above-mentioned starry sky map, the above-mentioned knowledge nodes are at least part of the planets in the above-mentioned starry sky map, and the above-mentioned path segments are connecting elements between the planets in the above-mentioned starry sky map.

[0104] For example, Figure 3 As shown, Figure 3 The lower area of the image shows a star map, which can be used to display the first learning path, i.e. Figure 3 The learning path consists of points C and D.

[0105] In some embodiments, for the learning recommendation scenario of the shopping mode, the above-mentioned scene image including at least one scene element is displayed on the above-mentioned graphical user interface, and the above-mentioned first learning path is displayed in the above-mentioned scene image, and the above-mentioned knowledge nodes and the above-mentioned path segments are at least part of the above-mentioned scene elements, which may include: the terminal can display a shopping scene map on the above-mentioned graphical user interface, and display the above-mentioned first learning path on the above-mentioned shopping scene map, the above-mentioned knowledge nodes are at least part of the virtual goods in the above-mentioned shopping scene map, and the above-mentioned path segments are navigation paths between the virtual goods in the above-mentioned shopping scene map.

[0106] For example, Figure 4 As shown, Figure 4 A shopping scene diagram is displayed in the figure, through which the first learning path can be displayed, i.e. Figure 4 The learning path consists of points E and F.

[0107] In some embodiments, the method may further include: in response to the completion of the learning event of the second path segment in the first learning path, the terminal may add the virtual commodity indicated by the knowledge point corresponding to the second path segment to the virtual storage space.

[0108] The above-mentioned virtual storage space includes but is not limited to a backpack, a shopping cart, and a virtual pet, etc., which can be set according to specific needs and are not limited here.

[0109] Exemplarily, the target user can push the shopping cart along the first learning path in the shopping scene diagram to complete the shopping list corresponding to the first learning path, that is, the commodity corresponding to each knowledge point on the first learning path is a virtual commodity in the shopping list, and the type of virtual commodity corresponds to the type or difficulty of the knowledge point. When the target user completes the learning event of the second path segment, the commodity indicated by the knowledge point corresponding to the second path segment can be added to the shopping cart, that is, a shopping cart icon can be displayed in the graphical user interface, and the corresponding commodity can be added to the shopping cart icon, so that every time the first user completes learning a knowledge point, there will be one more virtual commodity in the shopping cart.

[0110] In some embodiments, the learning plan for the knowledge points configured at the above-mentioned knowledge nodes is generated based on the historical learning content and / or recommended content of the above-mentioned reference user, wherein the historical learning content of the above-mentioned reference user is the learning plan corresponding to the knowledge points configured at each knowledge node on the second learning path, that is, the learning records experienced by the reference user in the historical period; the above-mentioned recommended content can be the content recommended by the reference user, such as the exercises recommended by the reference user for a certain knowledge point.

[0111] For example, Figure 5 As shown, Figure 5In the exercise recommendation page provided in, the area where "Exercises for a certain subject" is located displays the content of exercises to be recommended, and the "Information display area" can display information about the prerequisite knowledge points and subsequent knowledge points of the exercise. The prerequisite knowledge points are the knowledge points required to master the exercise, and the subsequent knowledge points are the knowledge points that can be learned after mastering the exercise. The "recommendation control" is used to be triggered by the reference user to recommend the exercise. Among them, the recommendation object can be other users with high learning similarity to the reference user at the same learning level, that is, other users with similar learning data before the reference user mastered the exercise.

[0112] In some embodiments, the above-mentioned response to the learning recommendation trigger event corresponding to the first user, displaying the first learning path recommended for the above-mentioned first user on the graphical user interface may include: the terminal may respond to the learning goal determination event corresponding to the first user, obtain the first learning path corresponding to the above-mentioned first user's learning goal, and display the above-mentioned first learning path on the above-mentioned graphical user interface.

[0113] In some embodiments, the above-mentioned learning goal determination event includes the above-mentioned first user's learning goal selection event or learning goal recommendation event.

[0114] The above-mentioned learning goal selection event of the first user may be an event in which the first user selects a learning goal provided on a graphical user interface, such as Figure 2 and Figure 3 As shown, Figure 2 and Figure 3 The first layer of the "User determines his own learning goal" area is used for the first user to operate, so that the first user can select the corresponding learning goal. It can also be the first user's selection operation on the scene map provided on the graphical user interface, such as the first user's selection operation on the location element in the learning map to select a certain knowledge point as a learning goal. For example, the first user selects a planet in the star map to select a knowledge point corresponding to a certain starry sky as a learning goal.

[0115] In some embodiments, obtaining the first learning path corresponding to the first user's learning goal may include: the terminal may obtain first historical learning data of the first user, and determine, based on the first historical learning data, a reference user that matches the first user in terms of the learning goal. The terminal may then obtain a second learning path corresponding to the learning goal of the reference user, and generate the first learning path corresponding to the learning goal of the first user based on the second learning path of the reference user.

[0116] Among them, the above-mentioned first historical learning data is the learning data in which the first user has participated in learning. The first historical learning data can be stored in a database. By collecting the first historical learning data in the database, the first historical learning data of the first user for comparison can be obtained.

[0117] Among them, the above-mentioned historical learning data includes but is not limited to student metadata, question-answering records, knowledge point learning status and behavioral data, etc. The student metadata includes but is not limited to the student's grade, region, school, historical academic performance, etc.; the question-answering records include but are not limited to the student's question-answering status on each knowledge point, answer accuracy, problem-solving time, etc.; the knowledge point learning status includes but is not limited to each student's mastery of different knowledge points, learning progress, etc.; the behavioral data includes but is not limited to other data related to learning performance such as study time and study habits.

[0118] In some embodiments, the above-mentioned determination of a reference user that matches the above-mentioned first user in the above-mentioned learning goal based on the above-mentioned first historical learning data may include: the terminal may obtain the second historical learning data corresponding to the above-mentioned learning goal of at least one historical user, and determine, based on the above-mentioned first historical learning data and at least one above-mentioned second historical learning data, a candidate learning user whose learning similarity with the above-mentioned first user in the above-mentioned learning goal meets a preset similarity condition, and then, based on the learning achievements of the above-mentioned candidate learning users in the above-mentioned learning goal, determine a reference user that matches the above-mentioned first user from the above-mentioned candidate learning users.

[0119] In this embodiment, the terminal can locate similar students with similar learning situations to the above-mentioned first user, that is, the above-mentioned candidate learning users, by analyzing the first historical learning data and at least one of the above-mentioned second historical learning data. Then, based on the learning achievements of the above-mentioned candidate learning users in the above-mentioned learning goals, a reference user with outstanding performance, that is, a "top student" is selected from them.

[0120] Specifically, the terminal can use a dynamic similarity matching algorithm to find students at the same learning level as the first user, such as those with similar learning trajectories or situations on the same knowledge point. The terminal can then model the first user's learning performance on the corresponding knowledge point based on time series data, for example, to determine whether the first user is currently in at least one of the following learning stages: initial learning, intensive learning, or review and consolidation.

[0121] Then, the terminal can perform similarity matching based on the divided learning stages, wherein the terminal can adopt a similarity measurement method to determine the candidate learning users whose learning similarity with the above-mentioned first user in the above-mentioned learning goal meets the preset similarity conditions based on the above-mentioned first historical learning data and at least one of the above-mentioned second historical learning data.

[0122] For example, the terminal may use dynamic time warping (DTW) or other time-related similarity measurement methods to compare the first historical learning data with at least one of the second historical learning data. The terminal may focus on matching users who had similar initial performance in each learning phase and subsequently successfully mastered the corresponding knowledge points. That is, by identifying the evolutionary path of each historical user, such as through time series analysis, the terminal can identify users who had similar initial performance in each learning phase and subsequently successfully mastered the corresponding knowledge points.

[0123] Specifically, the above-mentioned similarity matching algorithms include but are not limited to collaborative filtering methods, clustering methods, representation learning methods based on deep learning, methods based on graph neural networks (GNNs), distance metric learning methods, or similarity matching methods based on behavior sequences.

[0124] Among them, the above-mentioned collaborative filtering method can use the user's test record to find users with similar test records; the above-mentioned clustering method can use K-means and other methods to cluster users; the above-mentioned representation learning method based on deep learning can learn the user's feature representation through neural networks, calculate the similarity between users, and capture nonlinear features; the above-mentioned method based on graph neural network (GNN) can use the association between users and knowledge points to construct a graph structure and calculate the similarity of users through graph neural networks; the above-mentioned distance metric learning method can train the model through methods such as contrastive learning, learn customized similarity metrics, and apply them to similarity calculations between users; the above-mentioned similarity matching method based on behavior sequences can analyze the user's learning behavior sequence through algorithms such as dynamic time warping to find users with similar learning paths.

[0125] In some embodiments, after determining the candidate learning users, the terminal can determine a reference user that matches the above-mentioned first user from the above-mentioned candidate learning users based on the learning achievements of the above-mentioned candidate learning users on the above-mentioned learning objectives, that is, the terminal can use the learning achievements of the candidate learning users on the above-mentioned learning objectives to clarify the learning performance of the candidate learning users on the above-mentioned learning objectives, thereby identifying the user with the best performance as the reference user, for example, giving priority to the user with the highest correct answer rate, the fastest knowledge point mastery, and the most effective learning path as the reference user; or, the terminal can determine a reference user that matches the above-mentioned first user from the above-mentioned candidate learning users based on the learning achievements of the candidate learning users on the above-mentioned learning objectives, and the stability and / or effectiveness shown in the historical learning data of the candidate learning users.

[0126] Among them, the method for determining the above-mentioned user with the best performance includes but is not limited to a ranking algorithm based on performance scoring, a scoring model based on multi-indicator weighting, or an algorithm based on learning result prediction.

[0127] Among them, the above-mentioned ranking algorithm based on performance score can be based on the user's performance on a certain knowledge point, such as the accuracy of answering questions, completion time, learning progress, etc., to sort users by performance score and select the user with the best performance as the reference user.

[0128] Among them, the above-mentioned scoring model based on multi-indicator weighting can be to establish a weighted scoring model for each user's performance on the knowledge point by integrating multiple performance dimensions (such as answer accuracy, learning efficiency, review frequency, etc.), so as to determine the user with the best performance.

[0129] Among them, the above-mentioned learning result prediction algorithm can use decision trees, logistic regression and other algorithms to build a classification or regression model based on the user's learning characteristics on multiple knowledge points, predict the user's performance on a certain knowledge point, and the reference user is the user with the best prediction result.

[0130] In some embodiments, the learning objective is configured with at least two learning stages. The learning objective may be a learning path corresponding to a certain knowledge point. There is a learning sequence between the at least two learning stages. The at least two learning stages include a target learning stage and a historical learning stage before the target learning stage.

[0131] Accordingly, the determining of a reference user that matches the first user in the learning goal based on the first historical learning data includes: determining a reference user that matches the first user in the goal learning stage based on the first historical learning data;

[0132] Accordingly, the generating of the first learning path corresponding to the learning goal of the first user based on the second learning path of the reference user includes: generating the first learning path corresponding to the first user in the target learning stage based on the second learning path of the reference user.

[0133] In this embodiment, different learning stages are divided so that a learning path similar to the first user's learning stage is dynamically matched according to the first user's learning performance in different learning stages.

[0134] Specifically, the above-mentioned dynamic matching method by learning stage can be to decompose the user's learning goals by stage, and based on the user's current learning progress (such as knowledge mastery, answering accuracy, etc.), match the corresponding reference user's learning path in stages to ensure that the terminal can recommend suitable learning content and sequence according to the specific needs of the students, so that when the terminal recommends the learning path, it adjusts the learning difficulty and learning content in the learning plan of the corresponding knowledge points on the path in real time to adapt to the individual differences of the users, ensure that the learning path truly meets the learning ability and progress of each user, and make the recommendation method of the learning path more flexible and dynamic.

[0135] It is understandable that the terminal can model the time series of the first user's learning data to track the first user's performance at different learning stages, thereby adjusting the learning path according to the first user's real-time feedback to flexibly respond to changes in the user's needs during the learning process, and provide instant personalized learning path recommendations.

[0136] Among them, the above-mentioned learning stages can be divided according to different dimensions such as scores, time, etc. For example, if divided by scores, then 30 to 50 points can be set as a learning stage, and reference users with similar learning behaviors when the scores are 30 to 50 points are found, and the learning path of the reference users when their scores are improved from 30 to 50 points to 50 to 70 points is recommended to the first user.

[0137] In some embodiments, the above-mentioned process of dividing the reference user's learning path into learning stages can be to divide the entire learning process into several learning stages, each learning stage representing the reference user's learning method at the corresponding stage. For example, the learning stage can be decomposed into an initial learning stage, an intensive learning stage, and a consolidation review stage, wherein the initial learning stage is the learning stage when the reference user first encounters a certain knowledge point, and the learning plan corresponding to this learning stage includes but is not limited to the selection of learning resources, the accuracy of the initial practice questions, etc.; the intensive learning stage is the process of the reference user further consolidating and in-depth learning of the knowledge point, and the learning plan corresponding to this learning stage includes but is not limited to the review plan, improving the completion of the exercises, etc.; the consolidation review stage is the review and intensive practice performed by the reference user after mastering the knowledge point to ensure long-term memory and flexible application.

[0138] In this embodiment, the learning path of each learning stage will record the reference user's specific learning content, resource usage, learning behavior (such as learning time, number of answers), and other learning plans in that stage.

[0139] Furthermore, for each learning phase, the terminal can extract the core learning features of that phase. These features are then used to match other students, ensuring they receive similar learning guidance as the reference user. The extracted core features include learning resources, study time, accuracy rate, and review frequency. These features can be formed into a multidimensional feature vector representing the reference user's learning status over a specific time period.

[0140] Learning resources refer to the types of learning resources (e.g., videos, courseware, exercises) used by the reference user during that time period. Learning duration refers to the amount of time the reference user spent during that time period, including time spent using resources and completing exercises. Correctness refers to the reference user's performance on the exercises during that period, specifically the accuracy rate and error types. Review frequency refers to whether the reference user reviewed during that period, as well as the frequency and method of review (e.g., through rereading or repeated practice).

[0141] Furthermore, for each learning stage, the terminal can extract the aforementioned core learning features and perform similarity matching with the historical learning data of other students (such as the first user). Specifically, based on time series data, the terminal can match students whose learning features are most similar to those of the reference user in that time period one by one. Then, the terminal can use similarity measurement methods such as dynamic time warping (DTW) or Euclidean distance to ensure that students with similar learning status as the reference user at the same learning level are found. For example, if a student's knowledge mastery speed and answer accuracy in the early stages of learning are similar to those of the reference user, then the terminal can identify the student as a student similar to the reference user at that learning stage.

[0142] For example, during the initial learning phase, the terminal can match a first user who has experienced similar difficulties or progress in learning a particular knowledge point, and recommend learning solutions such as learning resources and strategies used by the reference user in the initial phase. For example, the video courses and basic exercises used by the reference user in that phase will be recommended to the first user.

[0143] For example, during the mid-term learning phase, the terminal can match a first user who has mastered the basics but has encountered a learning bottleneck, and recommend a learning path for the reference user to help overcome the difficulties encountered at that stage. For example, if the reference user breaks through the bottleneck through targeted review, the terminal can recommend these review resources and strategies to the first user.

[0144] For example, in the review and consolidation stage, the terminal may match a first user who has basically mastered the knowledge points but needs further consolidation, and recommend a learning plan such as the learning method and frequency of the reference user in the review and consolidation stage.

[0145] In some embodiments, generating the first learning path corresponding to the learning goal of the first user based on the second learning path of the reference user includes: using the second learning path of the reference user as the first learning path of the first user.

[0146] In some embodiments, the above-mentioned second learning path based on the above-mentioned reference user is used to generate the first learning path corresponding to the above-mentioned learning goal of the above-mentioned first user, including: at least one path processing algorithm such as an algorithm based on the shortest path, a graph reasoning algorithm based on path ranking, or a path selection algorithm based on frequency, to process the second learning path of the above-mentioned reference user to generate the first learning path corresponding to the above-mentioned learning goal of the above-mentioned first user.

[0147] Among them, the above-mentioned shortest path-based algorithm can determine the learning difficulty between the knowledge points on the second learning path based on the learning situation of the reference user (such as determining the learning difficulty based on the correct answer rate, time or resource allocation), and set corresponding weights for the edges between the knowledge points based on the learning difficulty between the knowledge points, and then use the shortest path algorithm to find the optimal learning path. The shortest path algorithm includes but is not limited to the Dijkstra algorithm, the A* algorithm, etc.

[0148] Among them, the above-mentioned graph reasoning algorithm based on path ranking can find all reachable paths from the starting knowledge point to the target knowledge point on the second learning path according to the knowledge point graph, and then rank the paths through heuristic rules to be suitable for scenarios with complex rules and less data.

[0149] Among them, the above-mentioned frequency-based path selection algorithm can identify the learning behavior pattern of at least one reference user at a certain knowledge point on the second academic path according to the frequency statistical method, and select the path with the highest frequency as the recommended path.

[0150] 102. In response to a triggering operation on a knowledge point of the first learning path, display at least part of the learning content in the learning solution corresponding to the triggered knowledge node.

[0151] In this embodiment, the terminal can respond to the triggering operation of the knowledge point of the first learning path and display at least part of the learning content in the learning plan corresponding to the triggered knowledge node, so as to realize the real-time recommendation of the best learning path based on the individual learning situation of the first user, ensuring that the learning recommendation is more personalized and flexible, and by making recommendations based on the learning path of the reference user, the effectiveness and credibility of the recommendation are greatly improved, overcoming the limitations of the lack of verification caused by the traditional fixed learning path recommendation, and by sharing the learning experience of the reference user, learning from the successful experience of outstanding students, effectively improving the learning effect of the first user on weak knowledge points.

[0152] In some embodiments, after displaying at least part of the learning content in the learning plan corresponding to the triggered knowledge node, it can also include: the terminal can obtain the learning status of the knowledge point by the above-mentioned first user in the learning process of the above-mentioned path segment, so as to update the display style of the above-mentioned path segment based on the above-mentioned learning status.

[0153] In some embodiments, after displaying at least part of the learning content in the learning plan corresponding to the triggered knowledge node, it can also include: the terminal can obtain the learning status of the above-mentioned first user on the above-mentioned first learning path, and send the learning status of the above-mentioned first user to a third user associated with the above-mentioned first user, so that the third user can view the learning status of the above-mentioned first user on the above-mentioned first learning path.

[0154] Among them, the third user associated with the first user can be a user with a family relationship, a user with a teacher-student relationship, etc., which can be set according to needs and is not limited here.

[0155] For example, if the above-mentioned associated third user is a user with a family relationship, such as the first user is a student and the third user is a parent, then the parent side can be used for parents to view the student's learning situation. Parents can click on the corresponding point to view what the knowledge point is, how difficult it is, what results can be achieved after learning, etc.

[0156] In some embodiments, the triggered knowledge node is a first knowledge node, and the above-mentioned at least two knowledge nodes also include a second knowledge node adjacent to the above-mentioned first knowledge node and located after the above-mentioned first knowledge node. After displaying at least part of the learning content in the learning plan corresponding to the triggered knowledge node, it can also include: the terminal can obtain the learning status of the above-mentioned first user for the above-mentioned first knowledge node. If the learning status of the above-mentioned first knowledge node meets the learning completion conditions corresponding to the above-mentioned first knowledge node, the above-mentioned second knowledge node will be displayed in the above-mentioned graphical user interface in a preset display style.

[0157] For example, for the learning recommendation scenario in the fog map mode, the second knowledge node can only be displayed after the first user has mastered the knowledge point corresponding to the first knowledge node.

[0158] In some embodiments, after displaying at least part of the learning content in the learning plan corresponding to the triggered knowledge node, it may also include: the terminal can obtain the user learning data and learning results of the above-mentioned first user on the above-mentioned first learning path. If the above-mentioned learning results do not meet the learning completion conditions indicated by the second learning path of the above-mentioned reference user, then the above-mentioned first user is prompted with information based on the above-mentioned user learning data.

[0159] In this embodiment, after recommending a learning path, the system continuously collects student performance and feedback data, dynamically verifying and adjusting the path to ensure that the recommended path aligns with the student's actual mastery. This approach ensures that path selection is based on actual learning performance, contributing to the accuracy and reliability of the recommendations.

[0160] Specifically, after recommending a path, the terminal monitors the current student's learning feedback and performance to evaluate and optimize the recommendation effect. For example, learning effect evaluation means that the terminal can dynamically evaluate the current student's mastery of the recommended path based on their subsequent learning performance. Evaluation dimensions include the accuracy of answering questions and the improvement in knowledge points. Another example is path optimization and iteration. If the recommended path fails to significantly improve the student's learning effect, the system will optimize the recommendation algorithm based on new data feedback and adjust subsequent learning path recommendations based on the learning experience of other similar students.

[0161] Specifically, the data feedback and learning effect optimization module can be used to dynamically optimize recommended learning paths and strategies based on students' learning performance. Data feedback can come from feedback signals automatically generated by the system or generated through interaction between students and the system. There are several main methods:

[0162] The first method, based on the human-in-the-loop approach, is a hybrid optimization method that incorporates human participation into the automated process. It mainly uses the following types of feedback in knowledge point recommendation:

[0163] Among them, teacher feedback: teachers provide expert advice to the system based on students' learning performance and path feedback, adjust the recommended learning path, or re-match new reference users for students.

[0164] Among them, student feedback: During the learning process, students can actively mark their understanding of the recommended paths or knowledge points, and provide feedback on which paths are effective and which paths need adjustment.

[0165] Among them, expert correction: experts can regularly review the learning paths recommended by the system and intervene at key points to correct incorrect paths or strategies.

[0166] The second approach is based on reinforcement learning. This method automatically optimizes learning paths through a feedback loop. The system rewards or penalizes students based on their learning outcomes (such as knowledge mastery and accuracy), dynamically adjusting subsequent recommended paths. Common reinforcement learning algorithms include Q learning and value iteration.

[0167] The third approach is based on the multi-armed bandit model. The multi-armed bandit model is a classic online learning algorithm that gradually finds the optimal learning path through a trade-off between exploration and exploitation during the student's learning process. Each time a student completes a learning step, the system adjusts its strategy based on feedback, gradually determining the optimal path. This feedback includes, but is not limited to, satisfaction, knowledge mastery, and accuracy.

[0168] The fourth method, active learning, uses data feedback optimization to select the most informative student feedback samples to train the model and optimize the learning path. The system prioritizes feedback from representative students, accelerating the model optimization process.

[0169] Among them, real-time feedback optimization: the system continuously collects students' learning feedback (such as learning time, answer accuracy, etc.), and dynamically adjusts the recommendation strategy based on optimization algorithms such as reinforcement learning, so that the recommended path adapts to students' immediate learning needs.

[0170] It can be seen from the above content that by responding to the learning recommendation trigger event corresponding to the first user, the first learning path recommended for the above-mentioned first user is displayed on the graphical user interface, wherein the above-mentioned first learning path is generated based on the second learning path of the reference user matched with the above-mentioned first user, and the above-mentioned first learning path includes at least two knowledge nodes and path segments connecting adjacent knowledge nodes, and the above-mentioned knowledge nodes are configured with corresponding knowledge points and learning plans for knowledge points; in response to the knowledge point triggering operation on the first learning path, at least part of the learning content in the learning plan corresponding to the triggered knowledge node is displayed, so as to match the reference user for the corresponding user and make personalized learning recommendations for the corresponding user based on the learning path of the reference user, thereby improving the recommendation effect of learning recommendations for users.

[0171] In order to better implement the above method, an embodiment of the present application also provides an interactive device for knowledge points, which can be specifically integrated into an electronic device, such as a computer device, which can be a terminal, server, or other device.

[0172] Among them, the terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, a personal computer and other devices; the server can be a single server or a server cluster composed of multiple servers.

[0173] For example, in this embodiment, the method of the embodiment of the present application is described in detail by taking the interactive device of the knowledge point specifically integrated into the terminal as an example. This embodiment provides an interactive device of the knowledge point, such as Figure 6 As shown, the interactive device of the knowledge point may include:

[0174] A path display module 601 is configured to display a first learning path recommended for the first user on a graphical user interface in response to a learning recommendation trigger event corresponding to the first user, wherein the first learning path is generated based on a second learning path of a reference user matching the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, wherein the knowledge nodes are configured with corresponding knowledge points and learning solutions for the knowledge points;

[0175] The solution display module 602 is configured to, in response to a triggering operation on a knowledge point of the first learning path, display at least part of the learning content in the learning solution corresponding to the triggered knowledge node.

[0176] In some embodiments, the display styles of the path segments in the first learning path include at least one, wherein the display style is used to indicate the solution features of the learning solution for the knowledge point corresponding to the path segment.

[0177] In some embodiments, the display style of the path segment includes at least one of the composition structure of the path segment, the length of the path segment, and the curvature of the path segment.

[0178] In some embodiments, the number of path segments between a pair of adjacent knowledge nodes is at least one, and different path segments between the same pair of knowledge nodes correspond to different solution features.

[0179] In some embodiments, the above-mentioned scheme features include at least one of: learning difficulty, learning time, and learning content.

[0180] In some embodiments, the knowledge point interaction device further includes a style updating module, and the style updating module is specifically configured to:

[0181] Obtaining the learning status of the first user on the knowledge point during the learning process of the path segment;

[0182] The display style of the path segment is updated based on the learning situation.

[0183] In some embodiments, the graphical user interface further includes a first user identifier of the first user, and the first user identifier corresponds to a position on the first learning path, and is used to indicate the learning progress of the first user in the first learning path.

[0184] In some embodiments, the above-mentioned graphical user interface also includes a second user identifier, and the above-mentioned second user identifier corresponds to a position on the first path segment of the above-mentioned first learning path, which is used to indicate the learning progress of the second user in the above-mentioned first path segment. The learning path of the above-mentioned second user is at least partially the same as the above-mentioned first learning path, and the same part includes the above-mentioned first path segment.

[0185] In some embodiments, the information indicated by the second user identification includes speed indication information of the second user, and the speed indication information is used to indicate the learning speed of the second user.

[0186] In some embodiments, the graphical user interface further includes learning time identifiers corresponding to adjacent knowledge nodes in the first learning path, and the learning time identifiers are used to indicate the learning time required to complete the path segment between adjacent knowledge nodes.

[0187] In some embodiments, the interactive device for the above method and the above knowledge point further includes a duration determination module, and the above duration determination module is specifically used to:

[0188] Obtaining the knowledge point learning data of multiple historical users between the adjacent knowledge points;

[0189] Clustering the learning time between the adjacent knowledge points based on the knowledge point learning data to obtain at least one clustering result;

[0190] Based on the at least one clustering result, a learning time required for the first user to complete the path segment between the adjacent knowledge points is determined.

[0191] In some embodiments, the duration determination module is specifically configured to:

[0192] Determining at least one learning indicator of the historical user based on the knowledge point learning data, wherein the learning indicator is used to indicate the learning participation of the historical user between the adjacent knowledge points;

[0193] The learning durations of the adjacent knowledge points are clustered based on the learning indicators of the historical users to obtain at least one clustering result.

[0194] In some embodiments, the duration determination module is specifically configured to:

[0195] Obtaining the historical learning behavior of the first user;

[0196] Based on the historical learning behavior, determining at least one clustering result that matches the first user from the clustering results to obtain a target clustering result;

[0197] Based on the target clustering result, the learning time required for the first user to complete the path segment between the adjacent knowledge points is determined.

[0198] In some embodiments, the learning time indicated by the learning time identifier is updated according to the learning status of the knowledge point by the first user in the learning process of the path segment.

[0199] In some embodiments, the interactive device for the above method and the above knowledge point further includes a duration prediction module, and the above duration prediction module is specifically used to:

[0200] Based on the above target clustering results, a time prediction model is constructed;

[0201] The time prediction model is used to predict the learning duration based on the learning situation of the first user to obtain the learning duration of the first user.

[0202] In some embodiments, the path display module 601 is specifically used to:

[0203] A scene image including at least one scene element is displayed on the graphical user interface, and the first learning path is displayed in the scene image, wherein the knowledge node and the path segment are at least part of the scene element.

[0204] In some embodiments, the path display module 601 is specifically used to:

[0205] A learning map including at least one map element is displayed on the graphical user interface, and the first learning path is displayed in the learning map, wherein the knowledge nodes and the path segments are at least part of the map elements.

[0206] In some embodiments, the learning map further includes a third user identifier of the first user, the third user identifier includes a virtual vehicle, and the vehicle style of the virtual vehicle is used to indicate the learning speed of the first user.

[0207] In some embodiments, the map elements constituting the path segment include: traffic sign elements and / or geographical environment elements, and the traffic sign elements and / or geographical environment elements change according to the learning progress of the first user in the path segment.

[0208] In some embodiments, the path display module 601 is specifically used to:

[0209] A star map is displayed on the graphical user interface, and the first learning path is displayed on the star map. The knowledge nodes are at least some of the planets in the star map, and the path segments are connecting elements between the planets in the star map.

[0210] In some embodiments, the path display module 601 is specifically used to:

[0211] A shopping scene diagram is displayed on the graphical user interface, and the first learning path is displayed on the shopping scene diagram. The knowledge nodes are at least some of the virtual commodities in the shopping scene diagram, and the path segments are navigation paths between the virtual commodities in the shopping scene diagram.

[0212] In some embodiments, the interactive device for the above method and the above knowledge point further includes a product adding module, and the above product adding module is specifically used to:

[0213] In response to the completion of the learning event of the second path segment in the first learning path, the virtual commodity indicated by the knowledge point corresponding to the second path segment is added to the virtual storage space.

[0214] In some embodiments, the knowledge point interaction device further includes a viewing module, which is specifically configured to:

[0215] Obtaining the learning status of the first user on the first learning path;

[0216] The learning status of the first user is sent to a third user associated with the first user, so that the third user can view the learning status of the first user on the first learning path.

[0217] In some embodiments, the triggered knowledge node is a first knowledge node, the at least two knowledge nodes further include a second knowledge node adjacent to the first knowledge node and located after the first knowledge node, and the knowledge point interaction device further includes a node display module, which is specifically configured to:

[0218] Obtaining the learning status of the first user for the first knowledge node;

[0219] If the learning status of the above-mentioned first knowledge node meets the learning completion condition corresponding to the above-mentioned first knowledge node, the above-mentioned second knowledge node is displayed in the above-mentioned graphical user interface in a preset display style.

[0220] In some embodiments, the learning plan for the knowledge points configured in the above-mentioned knowledge nodes is generated based on the historical learning content and / or recommended content of the above-mentioned reference user.

[0221] In some embodiments, the knowledge point interaction device further includes an information prompt module, which is specifically configured to:

[0222] Obtaining user learning data and learning outcomes of the first user on the first learning path;

[0223] If the learning outcome does not meet the learning completion condition indicated by the second learning path of the reference user, an information prompt is given to the first user based on the user learning data.

[0224] In some embodiments, the path display module 601 is specifically used to:

[0225] In response to a learning goal determination event corresponding to the first user, obtaining a first learning path corresponding to the learning goal of the first user;

[0226] The first learning path is displayed on the graphical user interface.

[0227] In some embodiments, the above-mentioned learning goal determination event includes the above-mentioned first user's learning goal selection event or learning goal recommendation event.

[0228] In some embodiments, the path display module 601 is specifically used to:

[0229] Obtaining first historical learning data of the first user;

[0230] Determining, based on the first historical learning data, a reference user that matches the first user in terms of the learning goal;

[0231] Obtain a second learning path corresponding to the learning goal of the reference user;

[0232] Based on the second learning path of the reference user, a first learning path corresponding to the learning goal of the first user is generated.

[0233] In some embodiments, the path display module 601 is specifically used to:

[0234] Acquire second historical learning data corresponding to the learning goal of at least one historical user;

[0235] Determining, based on the first historical learning data and the at least one second historical learning data, a candidate learning user whose learning similarity with the first user in terms of the learning goal meets a preset similarity condition;

[0236] Based on the learning achievements of the candidate learning users on the learning objectives, a reference user matching the first user is determined from the candidate learning users.

[0237] In some embodiments, the learning target is configured with at least two learning stages, and there is a learning sequence between the at least two learning stages. The at least two learning stages include a target learning stage and a historical learning stage before the target learning stage. The path display module 601 is specifically configured to:

[0238] Determining, based on the first historical learning data, a reference user that matches the first user in the target learning phase;

[0239] Based on the second learning path of the reference user, a first learning path corresponding to the first user in the target learning stage is generated.

[0240] In some embodiments, the path display module 601 is specifically used to:

[0241] The second learning path of the reference user is used as the first learning path of the first user.

[0242] As can be seen from the above, the knowledge point interaction device of this embodiment displays the first learning path recommended for the first user on the graphical user interface in response to the learning recommendation trigger event corresponding to the first user, wherein the first learning path is generated based on the second learning path of the reference user matched with the first user, and the first learning path includes at least two knowledge nodes and path segments connecting adjacent knowledge nodes, and the knowledge nodes are configured with corresponding knowledge points and learning plans for knowledge points; in response to the knowledge point triggering operation on the first learning path, at least part of the learning content in the learning plan corresponding to the triggered knowledge node is displayed, so as to match the reference user to the corresponding user and make personalized learning recommendations to the corresponding user based on the learning path of the reference user, thereby improving the recommendation effect of learning recommendations to users.

[0243] Accordingly, the embodiment of the present application also provides an electronic device, which may be a terminal, such as a smart phone, a tablet computer, a laptop computer, a touch screen, a game console, a personal computer (PC), a personal digital assistant (PDA), or the like. Figure 7 As shown, Figure 7 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 700 includes a processor 701 having one or more processing cores, a memory 702 having one or more computer-readable storage media, and a computer program stored in the memory 702 and executable on the processor. The processor 701 is electrically connected to the memory 702. It will be understood by those skilled in the art that the electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0244] The processor 701 is the control center of the electronic device 700. It uses various interfaces and lines to connect various parts of the entire electronic device 700. By running or loading software programs and / or modules stored in the memory 702 and calling data stored in the memory 702, it executes various functions of the electronic device 700 and processes data, thereby monitoring the electronic device 700 as a whole.

[0245] In the embodiment of the present application, the processor 701 in the electronic device 700 loads the computer programs corresponding to one or more application processes into the memory 702 according to the following steps, and the processor 701 runs the application stored in the memory 702 to implement various functions:

[0246] In response to a learning recommendation trigger event corresponding to a first user, displaying a first learning path recommended for the first user on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matching the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, wherein the knowledge nodes are configured with corresponding knowledge points and learning solutions for the knowledge points;

[0247] In response to a triggering operation on a knowledge point of the first learning path, at least a portion of the learning content in the learning solution corresponding to the triggered knowledge node is displayed.

[0248] Therefore, the electronic device 700 provided by this embodiment can bring the following technical effects: improving the effect of learning recommendations for users.

[0249] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0250] Optional, such as Figure 7 As shown, the electronic device 700 further includes: a touch screen 703, a radio frequency circuit 704, an audio circuit 705, an input unit 706, and a power supply 707. Among them, the processor 701 is electrically connected to the touch screen 703, the radio frequency circuit 704, the audio circuit 705, the input unit 706, and the power supply 707 respectively. It can be understood by those skilled in the art that Figure 7 The electronic device structure shown in the figure does not constitute a limitation to the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0251] The touch screen display 703 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch screen display 703 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the electronic device. These graphical user interfaces can be composed of graphics, text, icons, videos, or any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. The touch panel can be used to collect user touch operations on or near it (such as operations performed by the user using a finger, stylus, or any other suitable object or accessory on or near the touch panel), generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 701, and can receive the command sent by the processor 701 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 701 to determine the type of touch event, and then the processor 701 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 703 to realize input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize input and output functions. That is, the touch display screen 703 can also be used as part of the input unit 706 to realize the input function.

[0252] The radio frequency circuit 704 may be used to transmit and receive radio frequency signals, so as to establish wireless communication with a network device or other electronic devices through wireless communication, and to transmit and receive signals with the network device or other electronic devices.

[0253] The audio circuit 705 can be used to provide an audio interface between the user and the electronic device through a speaker and microphone. The audio circuit 705 can convert the received audio data into an electrical signal and transmit it to the speaker, which then converts it into a sound signal for output. On the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 705 and converted into audio data. The audio data is then output to the processor 701 for processing, and then sent to another electronic device through the radio frequency circuit 704, or the audio data is output to the memory 702 for further processing. The audio circuit 705 may also include an earphone jack to provide communication between external headphones and the electronic device.

[0254] The input unit 706 may be configured to receive input digital or character information or user feature information (such as fingerprint, iris, or facial information), and to generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control.

[0255] Power supply 707 is used to supply power to various components of electronic device 700. Optionally, power supply 707 can be logically connected to processor 701 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. Power supply 707 can also include one or more DC or AC power supplies, a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0256] although Figure 7 Not shown in the figure, the electronic device 700 may further include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0257] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0258] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0259] To this end, an embodiment of the present application provides a computer-readable storage medium storing a plurality of computer programs, which can be loaded by a processor to execute any of the knowledge point interaction methods provided in the embodiments of the present application. For example, the computer program can execute the following steps:

[0260] In response to a learning recommendation trigger event corresponding to a first user, displaying a first learning path recommended for the first user on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matching the first user, and the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, wherein the knowledge nodes are configured with corresponding knowledge points and learning solutions for the knowledge points;

[0261] In response to a triggering operation on a knowledge point of the first learning path, at least a portion of the learning content in the learning solution corresponding to the triggered knowledge node is displayed.

[0262] It can be seen that the computer program can be loaded by the processor to execute any knowledge point interaction method provided in the embodiments of the present application, thereby bringing the following technical effects: improving the recommendation effect of learning recommendations for users.

[0263] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0264] The computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0265] Since the computer program stored in the computer-readable storage medium can execute any knowledge point interaction method provided in the embodiments of the present application, the beneficial effects that can be achieved by any knowledge point interaction method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0266] The above is a detailed introduction to the interactive method, device, electronic device and computer-readable storage medium of a knowledge point provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A knowledge point interaction method, characterized in that: The method comprises: In response to a learning recommendation trigger event corresponding to a first user, a first learning path recommended for the first user is displayed on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matched with the first user, the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, the knowledge nodes are configured with corresponding knowledge points and learning solutions for the knowledge points, the reference user is matched based on first historical learning data of the first user, and the display style of the path segment in the first learning path includes at least one, the display style is used to indicate solution features of the learning solution for the knowledge point corresponding to the path segment, the solution features including: at least one of learning difficulty, learning duration, and learning content; In response to a triggering operation on a knowledge point of the first learning path, displaying at least part of the learning content in the learning solution corresponding to the triggered knowledge node; The displaying, on a graphical user interface, a first learning path recommended for the first user includes: A scene image including at least one scene element is displayed on the graphical user interface, and the first learning path is displayed in the scene image, the knowledge nodes and the path segments are at least part of the scene elements, the scene image is an image of a learning recommendation scene setting in a corresponding mode, and the scene elements in the scene image are elements in the learning recommendation scene in the corresponding mode, and the modes include map mode, starry sky mode, fog map mode or shopping mode.

2. The knowledge point interaction method according to claim 1, characterized in that: The display style of the path segment includes at least one of the composition structure of the path segment, the length of the path segment, and the curvature of the path segment.

3. The knowledge point interaction method according to claim 1, characterized in that: The number of path segments between a pair of adjacent knowledge nodes is at least one, and different path segments between the same pair of knowledge nodes correspond to different solution features.

4. The knowledge point interaction method according to claim 1, wherein: After displaying at least part of the learning content in the learning solution corresponding to the triggered knowledge node, the method further includes: Obtaining the first user's learning status of the knowledge points in the learning process of the path segment; The display style of the path segment is updated based on the learning situation.

5. The knowledge point interaction method according to claim 1, characterized in that: The graphical user interface also includes a first user identifier of the first user. The first user identifier is located at a corresponding position on the first learning path and is used to indicate the learning progress of the first user in the first learning path.

6. The knowledge point interaction method according to claim 5, characterized in that: The graphical user interface also includes a second user identifier, which is located at a corresponding position on the first path segment of the first learning path and is used to indicate the learning progress of the second user in the first path segment. The learning path of the second user is at least partially identical to the first learning path, and the identical part includes the first path segment.

7. The knowledge point interaction method according to claim 6, characterized in that: The information indicated by the second user identification includes speed indication information of the second user, where the speed indication information is used to indicate a learning speed of the second user.

8. The knowledge point interaction method according to claim 1, wherein: The graphical user interface also includes learning time identifiers corresponding to adjacent knowledge nodes in the first learning path, and the learning time identifiers are used to indicate the learning time required to complete the path segment between adjacent knowledge nodes.

9. The knowledge point interaction method according to claim 8, characterized in that: The method further comprises: Acquire knowledge point learning data of multiple historical users between the adjacent knowledge points; Clustering the learning durations between the adjacent knowledge points based on the knowledge point learning data to obtain at least one clustering result; Based on the at least one clustering result, a learning time required for the first user to complete the path segment between the adjacent knowledge points is determined.

10. The knowledge point interaction method according to claim 9, characterized in that: The clustering of the learning durations between adjacent knowledge points based on the knowledge point learning data to obtain at least one clustering result includes: Determining at least one learning indicator of the historical user based on the knowledge point learning data, wherein the learning indicator is used to indicate the learning participation of the historical user between the adjacent knowledge points; The learning durations between the adjacent knowledge points are clustered based on the learning indicators of the historical users to obtain at least one clustering result.

11. The knowledge point interaction method according to claim 9, characterized in that: The determining, based on the at least one clustering result, a learning time required for the first user to complete the path segment between the adjacent knowledge points includes: Acquiring historical learning behavior of the first user; Based on the historical learning behavior, determining at least one clustering result matching the first user from the clustering results to obtain a target clustering result; Based on the target clustering result, a learning time required for the first user to complete the path segment between the adjacent knowledge points is determined.

12. The knowledge point interaction method according to claim 11, characterized in that: The learning time indicated by the learning time identifier is updated according to the learning status of the knowledge point by the first user during the learning process of the path segment.

13. The knowledge point interaction method according to claim 12, characterized in that: The method further comprises: Based on the target clustering results, construct a time prediction model; The time prediction model is used to predict the learning duration based on the learning situation of the first user to obtain the learning duration of the first user.

14. The knowledge point interaction method according to claim 1, wherein: The step of displaying a scene image including at least one scene element in the graphical user interface, and displaying the first learning path in the scene image, wherein the knowledge nodes and the path segments are at least part of the scene elements, comprises: A learning map including at least one map element is displayed on the graphical user interface, and the first learning path is displayed in the learning map, wherein the knowledge nodes and the path segments are at least part of the map element.

15. The knowledge point interaction method according to claim 14, characterized in that: The learning map also includes a third user identifier of the first user. The third user identifier includes a virtual vehicle. The vehicle style of the virtual vehicle is used to indicate the learning speed of the first user.

16. The knowledge point interaction method according to claim 14, wherein: The map elements constituting the path segment include: traffic sign elements and / or geographical environment elements, and the traffic sign elements and / or the geographical environment elements change according to the learning progress of the first user in the path segment.

17. The knowledge point interaction method according to claim 1, characterized in that: The step of displaying a scene image including at least one scene element in the graphical user interface, and displaying the first learning path in the scene image, wherein the knowledge nodes and the path segments are at least part of the scene elements, comprises: A star map is displayed on the graphical user interface, and the first learning path is displayed on the star map, the knowledge nodes are at least some of the planets in the star map, and the path segments are connecting elements between the planets in the star map.

18. The knowledge point interaction method according to claim 1, wherein: The step of displaying a scene image including at least one scene element in the graphical user interface, and displaying the first learning path in the scene image, wherein the knowledge nodes and the path segments are at least part of the scene elements, comprises: A shopping scene diagram is displayed on the graphical user interface, and the first learning path is displayed on the shopping scene diagram, the knowledge nodes are at least some virtual commodities in the shopping scene diagram, and the path segments are navigation paths between the virtual commodities in the shopping scene diagram.

19. The knowledge point interaction method according to claim 18, characterized in that: The method further comprises: In response to the completion of a learning event of a second path segment in the first learning path, a virtual commodity indicated by a knowledge point corresponding to the second path segment is added to a virtual storage space.

20. The knowledge point interaction method according to claim 1, wherein: After displaying at least part of the learning content in the learning solution corresponding to the triggered knowledge node, the method further includes: Acquiring the learning status of the first user on the first learning path; The learning situation of the first user is sent to a third user associated with the first user, so that the third user can view the learning situation of the first user on the first learning path.

21. The knowledge point interaction method according to claim 1, characterized in that: The triggered knowledge node is a first knowledge node, and the at least two knowledge nodes further include a second knowledge node adjacent to and located after the first knowledge node. After displaying at least part of the learning content in the learning solution corresponding to the triggered knowledge node, the following is further included: Obtaining the first user's learning status for the first knowledge node; If the learning status of the first knowledge node meets the learning completion condition corresponding to the first knowledge node, the second knowledge node is displayed in the graphical user interface in a preset display style.

22. The knowledge point interaction method according to claim 1, characterized in that: The learning scheme of the knowledge point configured by the knowledge node is generated based on the historical learning content and / or recommended content of the reference user.

23. The knowledge point interaction method according to claim 1, characterized in that: After displaying at least part of the learning content in the learning solution corresponding to the triggered knowledge node, the method further includes: Acquiring user learning data and learning achievements of the first user on the first learning path; If the learning outcome does not meet the learning completion condition indicated by the second learning path of the reference user, an information prompt is given to the first user based on the user learning data.

24. The knowledge point interaction method according to any one of claims 1 to 23, characterized in that: The step of displaying a first learning path recommended for the first user on a graphical user interface in response to a learning recommendation triggering event corresponding to the first user includes: In response to a learning goal determination event corresponding to a first user, obtaining a first learning path corresponding to the learning goal of the first user; The first learning path is displayed on the graphical user interface.

25. The knowledge point interaction method according to claim 24, characterized in that: The learning goal determination event includes a learning goal selection event or a learning goal recommendation event of the first user.

26. The knowledge point interaction method according to claim 24, characterized in that: The obtaining of the first learning path corresponding to the learning goal of the first user includes: Acquiring first historical learning data of the first user; Determining, based on the first historical learning data, a reference user that matches the first user in terms of the learning goal; Acquire a second learning path corresponding to the learning goal of the reference user; Based on the second learning path of the reference user, a first learning path corresponding to the learning goal of the first user is generated.

27. The knowledge point interaction method according to claim 26, characterized in that: The determining, based on the first historical learning data, a reference user that matches the first user in terms of the learning goal includes: Acquire second historical learning data corresponding to the learning goal of at least one historical user; Determining, based on the first historical learning data and at least one of the second historical learning data, a candidate learning user whose learning similarity with the first user on the learning goal meets a preset similarity condition; Based on the learning achievements of the candidate learning users on the learning objective, a reference user matching the first user is determined from the candidate learning users.

28. The knowledge point interaction method according to claim 26, characterized in that: The learning target is configured with at least two learning stages, a learning sequence exists between the at least two learning stages, and the at least two learning stages include a target learning stage and a history learning stage before the target learning stage; The determining, based on the first historical learning data, a reference user that matches the first user in terms of the learning goal includes: determining, based on the first historical learning data, a reference user that matches the first user in the target learning phase; Generating a first learning path corresponding to the learning goal of the first user based on the second learning path of the reference user includes: Based on the second learning path of the reference user, a first learning path corresponding to the first user in the target learning stage is generated.

29. The knowledge point interaction method according to claim 26, wherein: Generating a first learning path corresponding to the learning goal of the first user based on the second learning path of the reference user includes: The second learning path of the reference user is used as the first learning path of the first user.

30. A knowledge point interaction device, characterized in that: The device comprises: a path display module, configured to display, in response to a learning recommendation trigger event corresponding to a first user, a first learning path recommended for the first user on a graphical user interface, wherein the first learning path is generated based on a second learning path of a reference user matched with the first user, the first learning path includes at least two knowledge nodes and a path segment connecting adjacent knowledge nodes, the knowledge nodes are configured with corresponding knowledge points and learning solutions for the knowledge points, the reference user is matched based on first historical learning data of the first user, and the display style of the path segment in the first learning path includes at least one, the display style is used to indicate solution characteristics of the learning solution for the knowledge point corresponding to the path segment, the solution characteristics including at least one of learning difficulty, learning duration, and learning content; A solution display module, configured to, in response to a triggering operation on a knowledge point of the first learning path, display at least part of the learning content in the learning solution corresponding to the triggered knowledge node; The path display module is used to: display a scene image including at least one scene element on the graphical user interface, and display the first learning path in the scene image, the knowledge nodes and the path segments are at least part of the scene elements, the scene image is an image of the learning recommendation scene setting in the corresponding mode, and the scene elements in the scene image are elements in the learning recommendation scene in the corresponding mode, and the modes include map mode, starry sky mode, fog map mode or shopping mode.

31. An electronic device, characterized in that: It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the knowledge point interaction method described in any one of claims 1 to 29.

32. A computer-readable storage medium, characterized in that It includes a computer program, which, when running on an electronic device, is used to enable the electronic device to execute the knowledge point interaction method described in any one of claims 1 to 29.

Images