Method, apparatus, storage medium, and electronic device for determining a learning path

Abstract

The present application discloses a method, apparatus, storage medium and electronic device for determining a learning path, relating to the technical field of data processing, including: obtaining operation behavior data generated by a student during learning in a key learning area of a learning map; determining an association relationship network among a plurality of behavior factors included in the operation behavior data; performing clustering processing on the operation behavior data based on the association relationship network, so as to cluster the operation behavior data into a clustering category corresponding to the behavior factor having the greatest influence on it; extracting feature information of the student according to the operation behavior data in a plurality of clustering categories, and determining the number of target students corresponding to each learning grid in the key learning area based on the feature information; updating the learning grids included in the key learning area according to the number of target students, and determining the learning path of the student in the learning map based on the updated key learning area. The present application can improve the learning efficiency and experience of students.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and particularly relates to a method, device, storage medium and electronic device for determining a learning path. Background Art

[0002] In a question-solving software, the way to determine a learning path usually depends on various factors and metrics to comprehensively reflect the user's learning status, mastery level and progress.

[0003] Currently, when students are learning through question-solving software, the learning path of students is usually determined according to the order of the questions that the students have completed.

[0004] However, since the knowledge points that students need to learn can include knowledge points that need to be fully mastered and knowledge points that only need to be understood, the learning path obtained by using this way of determining the learning path includes all the trajectories of the knowledge points that the students have learned. When there are many learned knowledge points, the learning path of the content that the students actually need to master cannot be clearly presented, resulting in students being unable to truly understand their learning situation of the content that they need to master, which affects the students' experience. Summary of the Invention

[0005] In view of this, the present application provides a method, device, storage medium and electronic device for determining a learning path, mainly aiming to improve the technical problem that in the current existing technology, since the knowledge points that students need to learn can include knowledge points that need to be fully mastered and knowledge points that only need to be understood, the learning path obtained by using this way of determining the learning path includes all the trajectories of the knowledge points that the students have learned. When there are many learned knowledge points, the learning path of the content that the students actually need to master cannot be clearly presented, resulting in students being unable to truly understand their learning situation of the content that they need to master, which affects the students' experience.

[0006] In a first aspect, the present application provides a method for determining a learning path, including:

[0007] Obtaining operation behavior data generated by a student during learning in a key learning area in a learning map;

[0008] Determining an association relationship network among multiple behavior factors included in the operation behavior data;

[0009] Performing clustering processing on the operation behavior data based on the association relationship network to cluster the operation behavior data into a clustering category corresponding to the behavior factor that has the greatest influence on it;

[0010] Extract the characteristic information of students based on the operation behavior data in multiple clustering categories, and determine the number of target students corresponding to each learning grid in the key learning area based on the characteristic information. The target students are those who have not mastered the knowledge points in the key knowledge point cluster corresponding to the learning grid.

[0011] Update the learning grids included in the key learning area according to the number of target students, and determine the learning path of the students in the learning map based on the updated key learning area.

[0012] In a second aspect, the present application provides a device for determining a learning path, including:

[0013] An acquisition module, configured to acquire the operation behavior data generated by a student during learning in the key learning area of the learning map;

[0014] A determination module, configured to determine the association relationship network between multiple behavior factors included in the operation behavior data;

[0015] A clustering module, configured to perform clustering processing on the operation behavior data based on the association relationship network, so as to cluster the operation behavior data into the clustering category corresponding to the behavior factor that has the greatest influence on it;

[0016] The determination module is further configured to extract the characteristic information of students based on the operation behavior data in multiple clustering categories, and determine the number of target students corresponding to each learning grid in the key learning area based on the characteristic information. The target students are those who have not mastered the knowledge points in the key knowledge point cluster corresponding to the learning grid.

[0017] An update module, configured to update the learning grids included in the key learning area according to the number of target students, and determine the learning path of the students in the learning map based on the updated key learning area.

[0018] In a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for determining a learning path described in the first aspect is implemented.

[0019] In a fourth aspect, the present application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, the method for determining a learning path described in the first aspect is implemented.

[0020] With the above technical solution, a method, apparatus, storage medium, and electronic device for determining a learning path provided by this application, compared with the current existing technologies, by obtaining the operation behavior data generated by a student during learning in the key learning area in the learning map, determining the association relationship network among multiple behavior factors included in the operation behavior data, and performing clustering processing on the operation behavior data based on the association relationship network to cluster the operation behavior data into the clustering category corresponding to the behavior factor that has the greatest impact on it, can accurately cluster the behavior factor that has the greatest impact on the student's operation behavior data. Then, by extracting the characteristic information of the student from the clustered operation behavior data, the learning situation of the student in the learning grid can be accurately analyzed, and based on the characteristic information, the number of students who have not mastered the knowledge points corresponding to each learning grid in the key learning area can be determined. Through the number of students, the overall mastery situation of the student group for the knowledge point cluster corresponding to the learning grid can be judged. Through the overall mastery situation, a more accurate key learning area can be obtained. Furthermore, through the updated key learning area, a more accurate learning path of the student can be obtained, enabling the student to more clearly understand their own learning situation regarding the key knowledge points according to the updated learning path, improving the student's learning efficiency and experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with this application and, together with the specification, are used to explain the principles of this application.

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 It shows a schematic flowchart of a method for determining a learning path provided by an embodiment of this application;

[0024] Figure 2 It shows a schematic flowchart of a method for determining a learning path provided by an embodiment of this application;

[0025] Figure 3 It shows a schematic flowchart of a method for determining a learning path provided by an embodiment of this application;

[0026] Figure 4 It shows a schematic diagram of an example provided by an embodiment of this application;

[0027] Figure 5 It shows a schematic diagram of an example provided by an embodiment of this application;

[0028] Figure 6 The flowchart shows a method for determining a learning path provided by an embodiment of the present application;

[0029] Figure 7 The schematic diagram shows an example provided by an embodiment of the present application;

[0030] Figure 8 The schematic diagram shows the structure of a device for determining a learning path provided by an embodiment of the present application;

[0031] Figure 9 The schematic diagram shows the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0032] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other.

[0033] In order to improve the technical problem that in the prior art, since the knowledge points that students need to learn can include the knowledge points that need to be fully mastered and the knowledge points that only need to be understood, the learning path obtained by using this method for determining the learning path includes all the trajectories of the knowledge points that students have learned, and in the case of a large number of learned knowledge points, it will not be able to clearly present the learning path of the content that students actually need to master, resulting in students being unable to truly understand their learning situation of the content that needs to be mastered, and affecting the student experience. This embodiment provides a method for determining a learning path, as Figure 1 shown, the method includes:

[0034] Step 101: Obtain the operation behavior data generated by the student during learning in the key learning area of the learning map.

[0035] Among them, the learning map is composed of multiple learning grids arranged according to a predetermined relationship, and the key learning area is obtained by marking and selecting adjacent learning grids corresponding to the key knowledge point clusters in the learning map.

[0036] Optionally, the execution subject of the embodiment of the present application may be a cloud server.

[0037] In the embodiment of the present application, the learning map may be composed of multiple learning grids arranged according to a predetermined relationship. Among them, each grid corresponds to a question in the target question bank, and the target question bank is generated based on the knowledge point clusters extracted from the student textbooks. It should be noted that each learning grid corresponds to all the questions of a knowledge point cluster, and the grid corresponding to the key knowledge point cluster may be a key learning grid, and the adjacent key learning grids can be selected to obtain the key learning area.

[0038] In some examples, mapping the questions in the question bank in the learning map enables students to clearly see their learning progress, learning content, and learning path when viewing the learning map. They can also view the knowledge points in the corresponding textbooks for the current learning content and the importance levels of the knowledge points.

[0039] As an alternative approach, in the embodiments of the present application, through the information interaction between the cloud server and the client, the operation behavior data of students in the key learning areas can be obtained. Specifically, the operation behavior data may include, but is not limited to, the answering progress data, answering duration data, correct rate data, answering content data, number of skipped questions data, wrong question situation data, review frequency data, etc. In some examples, in the present application, by monitoring the key learning areas in the learning map, the operation behavior data of students can be obtained. It should be noted that the key learning areas are the areas where students must conduct learning. In the embodiments of the present application, by monitoring the key learning areas to obtain the operation behavior data of students, compared with obtaining the learning trajectories of students in real time, the amount of information that the cloud server needs to process can be saved to a greater extent, saving computing power.

[0040] Step 102: Determine the association relationship network among multiple behavior factors included in the operation behavior data.

[0041] In the embodiments of the present application, the multiple behavior factors included in the operation behavior data may be the specific operation behaviors corresponding to the operation behavior data. Exemplarily, if the operation behavior data is the answering progress data, the behavior factor is the answering progress. Correspondingly, if the operation behavior data is the answering duration data, the behavior factor is the answering duration, and so on. Details will not be elaborated here one by one.

[0042] In some examples, the association relationship network may be a network composed of all the association relationships among multiple behavior factors. For example, if the multiple behavior factors include answering progress, answering duration, correct rate, and answering content, all the association relationships among the multiple behavior factors may correspond to the association relationship that answering progress affects answering duration, the association relationship that answering duration affects answering progress, the association relationship that answering duration affects correct rate, the association relationship that correct rate affects answering content, the association relationship that answering content affects answering progress, etc. An association relationship network is formed through all the association relationships.

[0043] It should be noted that the association relationship network in the embodiments of the present application may also include the association relationship between the operation behavior data and different types of parameters, the relationship between the operation behavior data information and the learning path, the adjacency relationship of the surrounding user terminal positioning, the preset relationship of the surrounding key monitoring areas, etc.

[0044] Step 103: Perform clustering processing on the operation behavior data based on the association relationship network, so as to cluster the operation behavior data into the clustering categories corresponding to the behavior factors that have the greatest impact on it.

[0045] In the embodiment of the present application, clustering processing of data is an unsupervised learning method for discovering natural groupings of objects in a dataset. The goal of clustering is to group similar objects into the same cluster while ensuring that the objects between different clusters are as dissimilar as possible.

[0046] For this embodiment, the operation behavior data of users corresponds to multiple behavior factors, and each behavior factor will have an impact on the overall operation behavior data. The present application can cluster the operation behavior data through the association relationship network, so as to determine the behavior factor that has the greatest impact on each operation behavior data, and cluster the operation behavior data into different clustering categories according to the differences in the behavior factors that have the greatest impact.

[0047] Exemplarily, if there is operation behavior data 1, operation behavior data 2, operation behavior data 3, and operation behavior data 4, it is necessary to match the operation behavior data 1 based on the association relationship network to determine the behavior factor A that has the greatest impact on the operation behavior data 1, and then match the operation behavior data 2 with the operation behavior data 1. If the match is successful, it is determined that the behavior factor that has the greatest impact on the operation behavior data 2 is also the behavior factor A. Then, match the operation behavior data 3 with the operation behavior data 2, and so on.

[0048] If the operation behavior data 2 fails to match the operation behavior data 1, the operation behavior data 2 is separately determined as a clustering category, and then the operation behavior data 3 is sequentially matched with the operation behavior data 1 and the operation behavior data 2, and so on.

[0049] Step 104: Extract the feature information of the students based on the operation behavior data in multiple clustering categories, and determine the number of target students corresponding to each learning grid in the key learning area based on the feature information.

[0050] Among them, the target students are those who have not mastered the knowledge points in the key knowledge point cluster corresponding to the learning grid.

[0051] As an optional method, the student feature information may include but is not limited to the user ID of the student, learning progress (virtual map location information), notes, learning honors, learning trajectories, learning duration, etc.

[0052] In the embodiment of the present application, by extracting the feature information of the students, it can be judged whether the students have mastered the knowledge point cluster corresponding to the learning grid, and then the overall mastery situation of the students corresponding to the learning grid can be judged, and the number of target students who have not mastered the knowledge points in the key knowledge point cluster corresponding to the learning grid can be determined.

[0053] It should be noted that the number of terminals can reflect the students' mastery of the knowledge points at this location. If the number of students who have mastered is large, the number of student terminals in this area is small, indicating that most students can master it. This is used as the basis for setting key points, so as to construct or increment the information of the new key monitoring area.

[0054] Step 105: Update the learning grids included in the key learning area according to the number of target students, and determine the learning path of the students in the learning map based on the updated key learning area.

[0055] It should be noted that in the learning map of the embodiment of the present application, the learning grids corresponding to the basic knowledge point clusters can be unfilled blank blocks, and the learning grids corresponding to the key knowledge point clusters can be filled with the first color block; the blank blocks that have been learned by the current user can also be filled with the second color block in the learning map, and connecting the second color blocks in sequence can obtain the learning path of the user; by distinguishing the colors of the learning grids in the learning map, the source of the learning grids can be distinguished, and the learning progress of the current student can be visually presented and provided to the parent terminal for supervision.

[0056] In some examples, by updating the learning grids corresponding to the key learning area in the learning map, that is, re-labeling the color blocks of the learning grids, the updated learning path can be obtained.

[0057] Furthermore, the learning map can also be presented on the user terminal, so that the student's parents can clearly and intuitively understand the student's learning progress and learning situation, etc. Therefore, the learning map of the present application can also enable parents to more accurately and comprehensively understand the student's learning process.

[0058] Compared with the current existing technologies, in this embodiment, by obtaining the operation behavior data generated by a student during learning in the key learning area of the learning map, determining the association relationship network among multiple behavior factors included in the operation behavior data, and performing clustering processing on the operation behavior data based on the association relationship network to cluster the operation behavior data into the clustering category corresponding to the behavior factor that has the greatest impact on it, the behavior factor that has the greatest impact on the student's operation behavior data can be accurately clustered. Furthermore, by extracting the student's characteristic information from the clustered operation behavior data, the learning situation of the student in the learning grid can be accurately analyzed, and based on the characteristic information, the number of students who have not mastered the knowledge points corresponding to the learning grid in each learning grid in the key learning area can be determined. Through the number of students, the overall mastery situation of the student group for the knowledge point cluster corresponding to the learning grid can be judged. Through the overall mastery situation, a more accurate key learning area can be obtained. Furthermore, through the updated key learning area, a more accurate learning path of the student can be obtained, enabling the student to more clearly understand their own learning situation of the key knowledge points according to the updated learning path, improving the student's learning efficiency and experience.

[0059] As a refinement and extension of the above embodiment, when performing clustering processing on the operation behavior data based on the association relationship network to cluster the operation behavior data into the clustering category corresponding to the behavior factor that has the greatest impact on it, the following methods can be used but are not limited to, such as Figure 2 As shown, this method includes:

[0060] Step 201, clean the operation behavior data to obtain an operation behavior data sample set.

[0061] In the embodiment of the present application, before performing clustering analysis, data cleaning is a crucial step. It ensures the quality of the data, thereby improving the accuracy and reliability of the clustering results. Specifically, the process of cleaning the data can include but is not limited to handling missing values, handling outliers, performing standardization and normalization processing, etc. Specifically, in the embodiment of the present application, the collected user operation behavior data including the answering progress, correct rate, time spent, etc. can be sorted into files to obtain the operation behavior data sample set.

[0062] It should be noted that the operation behavior data sample set can include the operation behavior data of multiple users. Among them, each user in the operation behavior sample data set can correspond to multiple operation behavior data.

[0063] Step 202, match the first sample data in the operation behavior data sample set with the association relationship network to match the target behavior factor that has the greatest impact on the first sample data.

[0064] Among them, the first sample data is any one of the sample data in the operation behavior data sample set.

[0065] In the embodiment of the present application, any one of the sample data in the operation behavior data sample set can be matched with the association relationship network, and then the behavior factor that has the greatest impact on the sample data can be matched. For example, the sample data 1 in the operation behavior data sample set can be matched with the association relationship network, and then the behavior factor that has the greatest impact on the sample data is determined to be behavior factor 1.

[0066] Step 203: Determine the first sample data as the cluster center sample of the target cluster.

[0067] Among them, the cluster center of the target cluster is the target behavior factor, and the cluster center of each cluster is used to indicate the operation behavior that has the greatest impact on the sample data of that cluster.

[0068] In the embodiment of the present application, in the case of determining the target behavior factor corresponding to the first sample data, the first sample data can be determined as the cluster center sample of the cluster corresponding to the target behavior factor.

[0069] Exemplarily, based on step 202, in the case of determining the behavior factor 1 corresponding to the sample data 1, the sample data 1 can be determined as the cluster center sample of the cluster corresponding to the behavior factor 1.

[0070] Step 204: Sequentially perform similarity matching between the other sample data in the operation behavior data sample set except the first sample data and the cluster center sample of the target cluster, so as to match out multiple clusters except the target cluster, and determine the multiple clusters as multiple clustering categories.

[0071] Among them, the cluster center of each of the multiple clusters corresponds to one of the multiple behavior factors.

[0072] Optionally, in the process of executing step 204, the following steps can be adopted but are not limited to:

[0073] Step 11: Sequentially perform similarity matching between the other sample data in the operation behavior data sample set except the first sample data and the cluster center sample of the target cluster.

[0074] In the embodiment of the present application, based on the example in step 203, any one sample data 2 can be selected from the other sample data in the operation behavior data sample set except the first sample data, and the sample data 2 is matched with the sample data 1 through formula one (distance formula based on cosine angle) to obtain the similarity matching result of the sample data 1 and the sample data 2. Among them, formula one is specifically as follows:

[0075] (Formula One)

[0076] In Formula 1, X i and X j are respectively the vector representations corresponding to sample i and sample j.

[0077] Step 12: In the case where it is determined that the similarity value obtained by matching is greater than or equal to a predetermined similarity threshold, update the second sample data currently matched with the first sample data to the cluster center sample of the target cluster.

[0078] Among them, the second sample data is any one of the other sample data.

[0079] For this embodiment, based on the example in Step 11, the similarity matching result of the obtained sample data 1 and sample data 2 can be compared with the predetermined similarity threshold, and in the case where the similarity matching result is greater than or equal to the predetermined similarity threshold, determine sample data 2 as the cluster center sample of the cluster where sample data 1 is located.

[0080] Step 13: In the case where it is determined that the similarity value obtained by matching is less than the predetermined similarity threshold, perform similarity matching between the second sample data and other clusters respectively, and based on the matching result, use the second sample data as the cluster center sample of the cluster with the highest similarity to it.

[0081] In some examples, based on the example in Step 12, if and in the case where the similarity matching result is less than the predetermined similarity threshold, it is necessary to perform separate matching between sample data 2 and the cluster center samples of the already determined clusters. If there is a cluster center sample whose similarity to sample data 2 is greater than or equal to the predetermined similarity threshold, update the cluster center sample to sample data 2.

[0082] Step 14: If it is determined based on the matching result that there is currently no cluster whose similarity to the second sample data is greater than or equal to the predetermined similarity threshold, use the second sample data as the cluster center sample to construct a cluster.

[0083] As an alternative, based on the example in Step 13, if among all the already determined clusters, there is no cluster center sample whose similarity to sample data 2 is greater than or equal to the predetermined similarity threshold, it is necessary to use sample data 2 as the cluster center sample to reconstruct a cluster.

[0084] Repeat Step 11 to Step 14 until all the sample data in the operation behavior data sample set are matched to obtain several clusters, and select the samples corresponding to the cluster centers of each cluster as the cluster center samples; through sample purification, samples with relatively large similarity within the category are reduced, improving the accuracy of subsequent clustering features.

[0085] Further, when extracting the feature information of students based on the operation behavior data in multiple clustering categories and determining the number of target students corresponding to each learning grid in the key learning area based on the feature information, the following steps can be adopted but are not limited to, as Figure 3 shown, including:

[0086] Step 301: Based on multiple clustering categories and the cluster centers corresponding to the multiple clustering categories, construct a label portrait feature database for the operation behavior data sample set, and extract the label information of the students corresponding to the operation behavior data from the label portrait database.

[0087] In the embodiment of the present application, the label portrait feature database can be as shown in Table 1 below:

[0088] Table 1

[0089]

[0090] In Table 1, the first label (X) may include: recording the effective duration of Q&A interactions, and finally obtaining X1: the learning online duration in Table 1; obtaining the operation behavior records of students, and counting X2, that is, the number of help requests in Table 1; according to the result that the dialogue feedback of the student is solved, counting X3 of the helped object, that is, the number of effective help in Table 1; counting the response time and total duration of the dialogue of the helped object, and obtaining X4, that is, the response efficiency in Table 1.

[0091] Correspondingly, in Table 1, the second label (Y) may include: Y1: accuracy rate: counting the first answering situation for the same question; Y2: learning progress; Y3: answering duration: counting the first answering situation for the same question; Y4: proficiency in a single knowledge point: there may be multiple questions about the same knowledge point for users. Some users may have only done some of the questions but have already mastered the knowledge point, and some users may have done this question wrong, then read the answer and exited the software and re-answered the question to brush the data. Therefore, it is necessary to accurately judge whether the user has mastered the knowledge point.

[0092] Further, the third label (Z) may include: Z1: balanced development type; Z2: basic cultivation type; Z3: advanced challenge type; The third label mainly analyzes the learning style of the user according to the learning path of the user. For top students, they may be more inclined to challenge high difficulties. For the balanced development type, they may be more inclined to combine basic knowledge points and key knowledge points. For those with weak foundations, they are more inclined to consolidate basic knowledge; based on the answering performance of the user on basic knowledge points (K_B) and important knowledge points (K_I), they are divided into three categories: (1) basic type: need to strengthen basic knowledge point training; (2) solid type: both basic and important knowledge points meet the standards; (3) challenge type: have the ability to expand high-difficulty content.

[0093] In the embodiments of the present application, based on the label portrait feature database, the label information corresponding to each student can be extracted. Exemplarily, if the operation behavior dataset includes the operation behavior data of student 1, after determining the maximum influencing factor of the operation behavior data of student 1, the label information of student 1 can be extracted based on the label portrait feature database. For example, it can include X1 learning duration, Y2 learning progress, Z2 foundation type, etc.

[0094] Step 302: Determine the student to be analyzed who generates operation learning data within the target learning grid, and analyze the mastery of the knowledge points in the key knowledge point cluster corresponding to the target learning grid by the student to be analyzed based on the label information.

[0095] Among them, the target learning grid is any one of the learning grids included in the key learning area.

[0096] In some examples, the operation behavior data within the key monitoring area will be obtained, and the operation behavior data will be cleaned, classified, clustered, and a multi-class operation behavior database will be established; based on the in-depth integration and machine learning of the operation behavior data in the multi-class operation behavior database, a user label portrait feature database will be established. The user label portrait feature is the user feature information of the user terminal when the user enters the key monitoring area. The machine learning algorithm can be based on a knowledge graph or a k-means clustering algorithm. By deeply mining and analyzing the user label portrait feature database, the portrait features of the users within the key monitoring area are obtained, and the portrait features of the users are perceived and recognized.

[0097] In the embodiments of the present application, the learning situation of students in the learning grids of the key learning area can be analyzed based on the label information of the students, and then the mastery of the key knowledge point clusters corresponding to the learning grids by the students can be accurately judged.

[0098] It should be noted that in the learning map of the present application, there are grids corresponding to the basic knowledge point clusters and grids corresponding to the key knowledge point clusters. Among them, the process of extracting the basic knowledge point clusters based on the student textbooks can include: uploading the textbook content to the first knowledge point analysis module to obtain the basic knowledge point clusters; through text analysis of the textbook content, using technologies such as text mining, natural language, and semantic analysis, extracting the knowledge points in the text and performing hierarchical identification, and through encoding processing of the identification, obtaining the identification coding value. According to the identification coding value, constructing the identification vector set Uori (basic knowledge point cluster) corresponding to the knowledge point identification, and generating the knowledge point network; the hierarchical identification is divided into n levels. For example, n = 3, then U = [An, Bm, Ck], and the general expression: U = (k, β), where k is the knowledge point set and β is the edge set, such as Figure 4As shown: The first-level classification An serves as the main node and can be classified by chapter, resulting in An = [A1, A2... An]; the second-level classification Bm serves as the subordinate node of An and can be classified by section, resulting in Bm = [A1b1, A1b2, A2b1.. Anbm]; the third-level classification Ck serves as the subordinate node of Bm and can be classified by unit results, resulting in Ck = [A1b1c1, A1b2c2, A1b2c3.. Anbmck].

[0099] Because knowledge points will appear in the form of a single unit or a combination of multiple units according to their difficulty levels and learning depths. Therefore, when constructing the knowledge point network, it is determined that the existence form of the first-level classification An is the identification vector of a single unit, and the existence forms of the second and third levels are in the form of a combination of multiple units, and the identification vectors are superimposed in turn; multiple knowledge point networks form a knowledge point cluster; in this way, the constructed knowledge point network coverage can cover all the combination forms in which knowledge points appear. In actual question pushing, if the difficulty is simple, the first level can be pushed; if the difficulty is medium, the second level can be pushed; if the difficulty is difficult, the third level can be pushed.

[0100] The process of extracting key knowledge point clusters based on students' textbooks can include: obtaining important knowledge point clusters through the knowledge point extraction module according to the distribution of the knowledge point cluster U; as Figure 5 shown, count the number Z of the first-level branch identification vectors, the number X of the second-level branch identification vectors, and the number V of the third-level branch identification vectors, and input them into the pre-trained scoring model G to calculate the knowledge point cluster score, as shown in the following formula two:

[0101] , 、 、

[0102] (Formula Two)

[0103] In formula two, respectively represent the weight scores of the importance of the corresponding indicators of Z, X, and V, and β1 < β2 < β3, because as the degree of knowledge point refinement deepens, the proportion of importance increases; set the screening threshold T1, when G > T1, the screened knowledge point identification vectors are used as the first important knowledge point cluster Unew; the threshold T can be set with an initial threshold using methods such as self-definition, average method, median, etc.

[0104] Further, through screening by a pre-trained key knowledge point evaluation model, a new important knowledge point cluster is generated, including: obtaining a historical question bank, constructing a set of identification vectors G corresponding to knowledge point identifications in the same steps as the process of extracting a basic knowledge point cluster based on students' textbooks, and generating a knowledge point network; adopting the same method of hierarchical identification in step S1 to obtain vector sets Wn, Rm, and Hk, and Zori = [Wn, Rm, Hk]; screening through a pre-trained key knowledge point evaluation model to obtain a key knowledge point evaluation model, specifically as shown in formula three below:

[0105] (Formula Three)

[0106] In formula three, G j represents the number of occurrences of test point knowledge points; G q : the number of error frequency occurrences of test point knowledge points; G r : the number of branches of test point knowledge points; α is the weight score of the corresponding index; set a scoring threshold T2, when y G > T2, screen out the key knowledge point combinations to form the second important knowledge point cluster Znew.

[0107] Step 303: Based on the analysis results, determine students who have not mastered the knowledge points in the key knowledge point cluster corresponding to the target learning grid among the students to be analyzed as target students.

[0108] In the embodiment of the present application, based on the mastery of the key knowledge point cluster by students in the key learning area, determine students who have not mastered the key knowledge points as target students, and count the number of target students.

[0109] Optionally, when updating the learning grid included in the key learning area according to the number of target students, the following methods can be used but are not limited to, such as Figure 6 shown, this method includes:

[0110] Step 401: Evaluate the overall mastery of the knowledge points in the key knowledge point cluster corresponding to the target learning grid according to the number of target students.

[0111] In the embodiment of the present application, if it is indicated in the obtained operation behavior data that 10 students are learning in learning grid 1 in key learning area 1, it is necessary to determine the number of students among the 10 students who have not mastered the knowledge points in the key knowledge point cluster corresponding to learning grid 1, and judge the overall mastery of the knowledge points in the key knowledge point cluster corresponding to learning grid 1 by students based on the number of students who have not mastered and the total number of students.

[0112] Step 402: If the number of target students is greater than or equal to the predetermined quantity threshold, it is determined that the overall mastery situation does not meet the standard, and then the second identifier marked on the target learning grid is retained in the learning map.

[0113] Among them, the second identifier is used to represent the learning grid corresponding to the key knowledge point cluster in the learning map.

[0114] Exemplarily, based on the example in Step 401, if the number of students who have not mastered is 5 and the predetermined quantity threshold for the number of students who have not mastered is 3, it can be determined that the current overall mastery situation does not meet the standard, indicating that the students in general have not mastered the knowledge points in the key knowledge point cluster corresponding to learning grid 1. Then, the second identifier marked on the target learning grid can be retained in the learning map.

[0115] In the embodiments of the present application, the first identifier and the second identifier can be distinguished by colors, and can also be set differently by other factors. The specific distinguishing method for the first identifier and the second identifier is not limited herein.

[0116] Step 403: If the number of target students is less than the predetermined quantity threshold, it is determined that the overall mastery situation meets the standard, and then the second identifier marked on the target learning grid is replaced with the first identifier in the learning map.

[0117] Among them, the first identifier is used to represent the learning grid corresponding to the basic knowledge point cluster in the learning map.

[0118] In some examples, based on the example in Step 402, if the number of students who have not mastered is 1 and the predetermined quantity threshold for the number of students who have not mastered is 3, it can be determined that the current overall mastery situation meets the standard, indicating that the students in general have mastered the knowledge points in the key knowledge point cluster corresponding to learning grid 1. Then, the second identifier marked on the target learning grid can be replaced with the first identifier in the learning map, that is, the target learning grid is no longer classified into the key learning area.

[0119] Step 404: Re-mark and circle the learning grids marked with the second identifier in the learning map to obtain an updated key learning area.

[0120] Optionally, before executing Step 404, the method of this embodiment further includes: collecting the number of requests for learning collaboration requests triggered by the learning grids marked with the first identifier by students, and comparing the number of requests with a predetermined request threshold; marking the learning grids with the number of requests greater than the predetermined request threshold among the learning grids marked with the first identifier with the second identifier.

[0121] In the embodiments of the present application, during the learning process, a student can trigger a learning assistance request, enabling other students to respond to the learning assistance request. Specifically, the embodiments of the present application can count the number of learning assistance requests triggered by the student in the learning grid outside the key learning area. When the number of learning assistance requests reaches a certain threshold, it is determined that the student's overall mastery of the learning grid is poor, and then the learning grid can be marked with a second identifier.

[0122] Further, when determining the learning path of the student in the learning map based on the updated key learning area, the following steps can also be adopted but are not limited to:

[0123] Step 21: Determine the first quantity corresponding to the learning grids marked with the first identifier in the content already learned by the student, the second quantity corresponding to the learning grids marked with the second identifier, and the third quantity corresponding to the learning grids marked with the second identifier in the content already learned based on the updated key learning area.

[0124] Step 22: Use Formula Four for weighted scoring based on the first quantity, the second quantity, and the third quantity to update the learning path of the student for the key knowledge point clusters in the current learning path, and obtain the updated learning path.

[0125] (Formula Four)

[0126] Among them, C represents the first quantity, V represents the second quantity, V new represents the third quantity, αβ represents the corresponding weight scores, and Z base represents the total progress score of the learning path.

[0127] It should be noted that, as Figure 7 shown, in the learning map of the embodiments of the present application, the learning grids corresponding to the basic knowledge point clusters can be unfilled blank white blocks, and the learning grids corresponding to the key knowledge point clusters can be filled with the first color block; the unfilled blank white blocks already learned by the current user in the learning map can also be filled with the second color block, and connecting the second color blocks in sequence can obtain the learning path of the user; differentiating the colors of the learning grids in the learning map can be used to distinguish the sources of the learning grids, and can also visually present the progress of the content already learned by the current student, which is provided for supervision by the parent side.

[0128] Further, the learning map can also be presented on the user terminal, enabling the student's parents to clearly and intuitively understand the student's learning progress and learning situation, etc. Therefore, the learning map of the present application can also enable parents to more accurately and comprehensively understand the student's learning process.

[0129] Compared with the current existing technologies, in this embodiment, by obtaining the operation behavior data generated by a student during learning in the key learning area of the learning map, determining the association relationship network among multiple behavior factors included in the operation behavior data, and performing clustering processing on the operation behavior data based on the association relationship network to cluster the operation behavior data into the clustering category corresponding to the behavior factor that has the greatest impact on it, it is possible to accurately cluster the behavior factors that have the greatest impact on the student's operation behavior data. Furthermore, by extracting the student's characteristic information from the clustered operation behavior data, the learning situation of the student in the learning grid can be accurately analyzed, and based on the characteristic information, the number of students who have not mastered the knowledge points corresponding to the learning grid in each learning grid in the key learning area can be determined. Through the number of students, the overall mastery situation of the student group for the knowledge point cluster corresponding to the learning grid can be judged. Through the overall mastery situation, a more accurate key learning area can be obtained. Furthermore, through the updated key learning area, a more accurate learning path of the student can be obtained, enabling the student to more clearly understand their own learning situation regarding the key knowledge points according to the updated learning path, improving the student's learning efficiency and experience.

[0130] Further, as Figures 1 to 6 a specific implementation of the method shown, this embodiment provides a device for determining a learning path, as Figure 8 shown. The device includes: an acquisition module 51, a determination module 52, a clustering and matching module 53, and an update module 54.

[0131] The acquisition module 51 is configured to acquire the operation behavior data generated by a student during learning in the key learning area of the learning map;

[0132] The determination module 52 is configured to determine the association relationship network among multiple behavior factors included in the operation behavior data;

[0133] The clustering module 53 is configured to perform clustering processing on the operation behavior data based on the association relationship network to cluster the operation behavior data into the clustering category corresponding to the behavior factor that has the greatest impact on it;

[0134] The determination module 52 is further configured to extract the student's characteristic information based on the operation behavior data in multiple clustering categories, and determine the number of target students corresponding to each learning grid in the key learning area based on the characteristic information. The target student is a student who has not mastered the knowledge points in the key knowledge point cluster corresponding to the learning grid;

[0135] The update module 54 is configured to update the learning grids included in the key learning area based on the number of target students, and determine the learning path of the student in the learning map based on the updated key learning area.

[0136] In some examples of this embodiment, the clustering module 53 is specifically configured to clean the operation behavior data to obtain an operation behavior data sample set; match the first sample data in the operation behavior data sample set with the association relationship network to match the target behavior factor that has the greatest impact on the first sample data, where the first sample data is any sample data in the operation behavior data sample set; determine the first sample data as the cluster center sample of the target cluster, and the cluster center of the target cluster is the target behavior factor, where the cluster center of each cluster is used to indicate the operation behavior that has the greatest impact on the sample data of that cluster; sequentially match the other sample data in the operation behavior data sample set except the first sample data with the cluster center sample of the target cluster to match multiple clusters other than the target cluster, and determine the multiple clusters as the multiple clustering categories, where the cluster center of each cluster in the multiple clusters corresponds to one behavior factor among the multiple behavior factors.

[0137] In some examples of this embodiment, the clustering module 53 is further specifically configured to sequentially match the other sample data in the operation behavior data sample set except the first sample data with the cluster center sample of the target cluster; in the case where it is determined that the similarity value obtained by the match is greater than or equal to a predetermined similarity threshold, update the second sample data currently matched with the first sample data as the cluster center sample of the target cluster, where the second sample data is any sample data in the other sample data; in the case where it is determined that the similarity value obtained by the match is less than the predetermined similarity threshold, match the second sample data with other clusters respectively, and based on the match result, use the second sample data as the cluster center sample of the cluster with the highest similarity to it; if it is determined based on the match result that there is currently no cluster whose similarity to the second sample data is greater than or equal to the predetermined similarity threshold, use the second sample data as the cluster center sample to construct a cluster.

[0138] In some examples of this embodiment, the determination module 52 is specifically configured to construct a label portrait feature database corresponding to the operation behavior data sample set based on the multiple clustering categories and the cluster centers corresponding to the multiple clustering categories, and extract the label information of the student corresponding to the operation behavior from the label portrait database; determine the student to be analyzed who generates operation learning data in the target learning grid, and analyze the mastery situation of the student to be analyzed for the knowledge points in the key knowledge point cluster corresponding to the target learning grid based on the label information, where the target learning grid is any one of the learning grids included in the key learning area; based on the analysis result, determine the student who has not mastered the knowledge points in the key knowledge point cluster corresponding to the target learning grid among the students to be analyzed as the target student.

[0139] In some examples of this embodiment, the update module 54 is specifically configured to evaluate the overall mastery of the knowledge points in the key knowledge point cluster corresponding to the target learning grid according to the number of target students;

[0140] When the number of target students is greater than or equal to a predetermined number threshold, if it is determined that the overall mastery is not up to standard, the second identifier marked for the target learning grid is retained in the learning map, and the second identifier is used to represent the learning grid corresponding to the key knowledge point cluster in the learning map; when the number of target students is greater than or equal to the predetermined number threshold, if it is determined that the overall mastery is up to standard, the second identifier marked for the target learning grid in the learning map is replaced with the first identifier, and the first identifier is used to represent the learning grid corresponding to the basic knowledge point cluster in the learning map; the learning grid marked with the second identifier in the learning map is re-marked and circled to obtain an updated key learning area.

[0141] In some examples of this embodiment, the update module 54 is specifically further configured to collect the number of requests for learning collaboration triggered by the learning grid marked with the first identifier by students in the learning map, and compare the number of requests with a predetermined request threshold; mark the learning grid with a number of requests greater than the predetermined request threshold among the learning grids marked with the first identifier with the second identifier.

[0142] In some examples of this embodiment, the update module 54 is specifically further configured to determine a first quantity corresponding to the learning grid marked with the first identifier, a second quantity corresponding to the learning grid marked with the second identifier, and a third quantity corresponding to the learning grid marked with the second identifier in the learned content based on the updated key learning area in the learned content of the student; perform weighted scoring using Formula 1 based on the first quantity, the second quantity, and the third quantity to update the learning path for the key knowledge point cluster in the current learning path of the student, and obtain an updated learning path.

[0143] Formula 1

[0144] where C represents the first quantity, V represents the second quantity, V new represents the third quantity, αβ represents the corresponding weight score, and Z base represents the total progress score of the learning path.

[0145] It should be noted that for other corresponding descriptions of each functional unit involved in the learning path determination device provided in this embodiment, reference can be made to Figures 1 to 6 the corresponding description in, which will not be elaborated here.

[0146] Based on the above-mentioned method as Figures 1 to 6 shown, correspondingly, this embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method as Figures 1 to 6 shown is implemented.

[0147] Based on such an understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various implementation scenarios of this application.

[0148] As Figure 9 shown, the following is a schematic hardware structure diagram of an electronic device according to the present invention, including:

[0149] At least one processor 501; and,

[0150] A memory 502 communicatively connected to at least one of the processors 501; wherein,

[0151] The memory 502 stores instructions executable by at least one of the processors. The instructions are executed by at least one of the processors so that at least one of the processors can execute the method for determining the learning path as described above.

[0152] Figure 9 One processor 501 is taken as an example in

[0153] The electronic device may further include: an input device 503 and a display device 504.

[0154] The processor 501, the memory 502, the input device 503, and the display device 504 may be connected through a bus or other means, Figure 9 Taking the connection through a bus as an example in

[0155] The memory 502, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for determining the learning path in the embodiments of this application. For example, Figures 1 to 6 the method flow shown. The processor 501 executes various functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in the memory 502, that is, implements the method for determining the learning path in the above-mentioned embodiments.

[0156] The memory 502 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. The data storage area may store data created according to the use of the learning path determination method, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 502 may optionally include a memory remotely provided with respect to the processor 501, and these remote memories may be connected to the device executing the learning path determination method through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0157] The input device 503 may receive input user clicks and generate signal inputs related to user settings and function controls of the learning path determination method. The display device 504 may include a display device such as a display screen.

[0158] When the one or more modules are stored in the memory 502 and run by the one or more processors 501, the learning path determination method in any of the above method embodiments is executed.

[0159] Optionally, the above physical device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, sensors, an audio circuit, a WI-FI module, etc. The user interface may include a display screen (Display) and an input unit such as a keyboard (Keyboard), etc. Optionally, the user interface may further include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0160] Those skilled in the art can understand that the above physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0161] The storage medium may further include an operating system and a network communication module. The operating system is a program for managing the hardware and software resources of the above physical device, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to implement communication between components inside the storage medium, and communication between other hardware and software in the information processing physical device.

[0162] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or can also be implemented by hardware. By applying the solution of this embodiment, compared with the current existing technologies, in this embodiment, by obtaining the operation behavior data generated by a student during learning in the key learning area of the learning map, determining the association relationship network among multiple behavior factors included in the operation behavior data, and performing clustering processing on the operation behavior data based on the association relationship network to cluster the operation behavior data into the clustering category corresponding to the behavior factor that has the greatest impact on it, the behavior factor that has the greatest impact on the student's operation behavior data can be accurately clustered. Then, by extracting the student's characteristic information from the clustered operation behavior data, the learning situation of the student in the learning grid can be accurately analyzed. And based on the characteristic information, the number of students who have not mastered the knowledge points corresponding to the learning grid in each learning grid in the key learning area can be determined. Through the number of students, the overall mastery situation of the student group for the knowledge point cluster corresponding to the learning grid can be judged. Through the overall mastery situation, a more accurate key learning area can be obtained. Furthermore, through the updated key learning area, a more accurate learning path of the student can be obtained, so that the student can more clearly understand his own learning situation for the key knowledge points according to the updated learning path, improving the student's learning efficiency and experience.

[0163] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0164] The above are only specific embodiments of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments described herein, but will be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for determining a learning path, characterized in that: include: Obtain the operational behavior data generated by students in the key learning area of ​​the learning map; Determine a correlation network between multiple behavior factors included in the operation behavior data, wherein the multiple behavior factors included in the operation behavior data are specific operation behaviors corresponding to the operation behavior data; the operation behavior data includes the student's answering progress data, answering time data, accuracy data, answering content data, number of skipped questions data, wrong question situation data, and review frequency data; The operation behavior data is clustered based on the association relationship network to cluster the operation behavior data into cluster categories corresponding to the behavior factors that have the greatest impact on the operation behavior data, including: cleaning the operation behavior data to obtain an operation behavior data sample set; matching first sample data in the operation behavior data sample set with the association relationship network to match the target behavior factor that has the greatest impact on the first sample data, the first sample data being any sample data in the operation behavior data sample set; Determining the first sample data as the cluster center sample of the target cluster, the cluster center of the target cluster being the target behavior factor, includes: performing similarity matching on the other sample data except the first sample data in the operation behavior data sample set with the cluster center sample of the target cluster in sequence; when it is determined that the similarity value obtained by matching is greater than or equal to a predetermined similarity threshold, updating the second sample data currently matched with the first sample data as the cluster center sample of the target cluster, the second sample data being any one of the other sample data; when it is determined that the similarity value obtained by matching is less than the predetermined similarity threshold, performing similarity matching on the second sample data with other clusters respectively, and taking the second sample data as the cluster center sample of the cluster with the highest similarity based on the matching result; if it is determined based on the matching result that there is currently no cluster with a similarity greater than or equal to the predetermined similarity threshold with the second sample data, then taking the second sample data as the cluster center sample to construct a cluster, wherein the cluster center of each cluster is used to indicate the operation behavior that has the greatest impact on the cluster sample data; Performing similarity matching on other sample data in the operation behavior data sample set except the first sample data and the cluster center samples of the target cluster in sequence, so as to match a plurality of clusters except the target cluster, and determining the plurality of clusters as the plurality of cluster categories, wherein the cluster center of each cluster in the plurality of clusters corresponds to one of the plurality of behavior factors; Extracting characteristic information of students according to the operation behavior data in a plurality of clustering categories, and determining the number of target students corresponding to each learning grid in the key learning area based on the characteristic information, wherein the target students are students who have not mastered the knowledge points in the key knowledge point cluster corresponding to the learning grid; The learning grid contained in the key learning area is updated according to the number of the target students, and the learning path of the students in the learning map is determined based on the updated key learning area.

2. The method according to claim 1, characterized in that Extracting characteristic information of students according to the operation behavior data in a plurality of cluster categories, and determining the number of target students corresponding to each learning grid in the key learning area based on the characteristic information, including: Based on the multiple clustering categories and the cluster centers corresponding to the multiple clustering categories, a label portrait feature database corresponding to the operation behavior data sample set is constructed, and label information of students corresponding to the operation behavior data is extracted from the label portrait database; Determine a student to be analyzed who has learned and generated operational learning data in a target learning grid, and analyze the mastery of the knowledge points in the key knowledge point cluster corresponding to the target learning grid by the student to be analyzed based on the label information, wherein the target learning grid is any one of the learning grids included in the key learning area; Based on the analysis results, students among the students to be analyzed who have not mastered the knowledge points in the key knowledge point cluster corresponding to the target learning grid are determined as the target students.

3. The method according to claim 2, characterized in that The updating of the learning grid contained in the key learning area according to the target number of students includes: Evaluate the overall mastery of the knowledge points in the key knowledge point cluster corresponding to the target learning grid according to the number of the target students; When the number of target students is greater than or equal to a predetermined number threshold, it is determined that the overall mastery is not up to standard, and a second identifier for marking the target learning grid is retained in the learning map, the second identifier being used to indicate a learning grid corresponding to a cluster of key knowledge points in the learning map; When the number of target students is greater than or equal to the predetermined number threshold, it is determined that the overall mastery is up to standard, and the second identifier marking the target learning grid in the learning map is replaced with the first identifier, where the first identifier is used to indicate the learning grid corresponding to the basic knowledge point cluster in the learning map; In the learning map, the learning grid marked with the second identifier is re-marked and circled to obtain an updated key learning area.

4. The method according to claim 3, characterized in that Before re-marking and circling the learning grid marked with the second identifier in the learning map to obtain an updated key learning area, the method further includes: Collecting the number of requests for learning collaboration triggered by the student marking the learning grid with the first identifier in the learning map, and comparing the number of requests with a predetermined request threshold; The learning grids with the first identification and the number of requests of which is greater than the predetermined request threshold are marked with the second identification.

5. The method according to claim 4, characterized in that Determine the learning path of students in the learning map based on the updated key learning areas, including: Determine a first number of learning grids marked with the first identifier in the student's learned content, a second number of learning grids marked with the second identifier, and determine a third number of learning grids marked with the second identifier in the learned content based on the updated key learning area; Performing weighted scoring based on the first number, the second number, and the third number using Formula 1 to update the learning path for the key knowledge point cluster in the student's current learning path to obtain an updated learning path; Formula 1 Wherein, C represents the first quantity, V represents the second quantity, and V new represents the third quantity, αβ represents the corresponding weight score, and Z base Indicates the total progress score of the learning path.

6. A device for determining a learning path, characterized in that: include: The acquisition module is configured to acquire the operation behavior data generated by the student in the key learning area in the learning map, wherein the multiple behavior factors included in the operation behavior data are specific operation behaviors corresponding to the operation behavior data; the operation behavior data includes the student's answering progress data, answering time data, correctness data, answering content data, number of skipped questions data, wrong question situation data, and review frequency data; A determination module, configured to determine a correlation relationship network between a plurality of behavior factors included in the operation behavior data; The clustering module is configured to perform clustering processing on the operation behavior data based on the association relationship network to cluster the operation behavior data into cluster categories corresponding to the behavior factors that have the greatest impact on the operation behavior data, including: cleaning the operation behavior data to obtain an operation behavior data sample set; matching the first sample data in the operation behavior data sample set with the association relationship network to match the target behavior factor that has the greatest impact on the first sample data, the first sample data being any sample data in the operation behavior data sample set; Determining the first sample data as the cluster center sample of the target cluster, the cluster center of the target cluster being the target behavior factor, includes: performing similarity matching on the other sample data except the first sample data in the operation behavior data sample set with the cluster center sample of the target cluster in sequence; when it is determined that the similarity value obtained by matching is greater than or equal to a predetermined similarity threshold, updating the second sample data currently matched with the first sample data as the cluster center sample of the target cluster, the second sample data being any one of the other sample data; when it is determined that the similarity value obtained by matching is less than the predetermined similarity threshold, performing similarity matching on the second sample data with other clusters respectively, and taking the second sample data as the cluster center sample of the cluster with the highest similarity based on the matching result; if it is determined based on the matching result that there is currently no cluster with a similarity greater than or equal to the predetermined similarity threshold with the second sample data, then taking the second sample data as the cluster center sample to construct a cluster, wherein the cluster center of each cluster is used to indicate the operation behavior that has the greatest impact on the cluster sample data; Performing similarity matching on other sample data in the operation behavior data sample set except the first sample data and the cluster center samples of the target cluster in sequence, so as to match a plurality of clusters except the target cluster, and determining the plurality of clusters as the plurality of cluster categories, wherein the cluster center of each cluster in the plurality of clusters corresponds to one of the plurality of behavior factors; The determination module is further configured to extract characteristic information of students according to the operation behavior data in the plurality of clustering categories, and determine the number of target students corresponding to each learning grid in the key learning area based on the characteristic information, wherein the target students are students who have not mastered the knowledge points in the key knowledge point cluster corresponding to the learning grid; The updating module is configured to update the learning grid contained in the key learning area according to the number of the target students, and determine the learning path of the students in the learning map based on the updated key learning area.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

8. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

Images