Teaching intelligent service method, electronic equipment and storage medium

Abstract

The invention discloses a teaching intelligent service method, electronic equipment and a storage medium. The method comprises the following steps: acquiring a jump vector set of P target teaching objects; wherein the jump vector set comprises J jump vectors; performing neighbor clustering on J jump vectors in the jump vector set to generate K jump vector clusters; calculating Gini coefficients of J jump vectors in the K jump vector clusters; comparing the Gini coefficients of the K jump vector clusters with a coefficient threshold, and performing structural jump screening on the K jump vector clusters until S structural jump clusters are obtained; positioning jump knowledge points according to the S structural jump clusters; according to the method, the jump vectors of the target teaching object on the adjacent knowledge points are constructed, and all the jump vectors are classified by adopting a neighbor clustering mode, so that clear positioning of the jump knowledge points in the teaching path is realized, and support is provided for content feedback acquisition and knowledge point micro-reconstruction.

Description

Technical Field

[0001] The present invention relates to the field of teaching services, and in particular to an intelligent teaching service method. Background Art

[0002] With the development of intelligent teaching platforms, personalized teaching driven by behavioral data has become a key trend in teaching systems. Existing technologies typically analyze students' learning behaviors, answer records, and knowledge mastery to recommend learning paths and adapt content. However, in actual teaching, the cognitive spans between different knowledge points are uneven. Some knowledge points may experience sudden changes in learning behavior due to problems such as broken cognitive structures and insufficient knowledge transfer. This can manifest as a surge in error rates, abnormally prolonged learning times, or increased reliance on prompts, which in turn affects the overall teaching rhythm and learning outcomes.

[0003] Existing solutions primarily focus on content recommendation and learning assessment, lacking mechanisms for identifying "jumping knowledge points." This makes it difficult to identify key knowledge pairs within the global path that lead to drastic changes in students' learning status, hindering the optimization of teaching content structure and the dynamic adjustment of paths. Furthermore, existing methods often rely on single-point indicators to judge individual differences and lack aggregated behavioral modeling, making it difficult to characterize structural learning barriers that are representative of a group. To this end, the present invention provides an intelligent teaching service method. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a teaching intelligent service method, which solves the technical problems raised in the background technology by accurately identifying skipped knowledge points.

[0005] In a first aspect, the present invention provides a teaching intelligent service method, comprising the following steps: S1. Obtain a jump vector set of P target teaching objects; wherein the jump vector set includes J jump vectors; S2. performing nearest neighbor clustering on the J jump vectors in the jump vector set to generate K jump vector clusters; S3, calculating the Gini coefficients of the J jump vectors in the K jump vector clusters; S4, comparing the Gini coefficients of the K jump vector clusters with the coefficient threshold; If the Gini coefficient is less than the coefficient threshold, it is determined that there is no significant structural jump in the learning path of the target teaching object; otherwise, the K jump vector clusters are screened for structural jumps until S structural jump clusters are obtained; S5. Locate the jump knowledge points based on the S structural jump clusters.

[0006] In some specific embodiments, obtaining a jump vector set of P target teaching objects includes: S1-1, obtaining the learning mastery of M original teaching subjects in N knowledge points in the teaching subject; S1-2, select P target teaching subjects from M original teaching subjects whose learning and mastery of N knowledge points all exceed the mastery threshold; S1-3. For each target teaching object, obtain a behavior performance vector sequence of the target teaching object at N knowledge points; wherein the behavior performance vector sequence represents an ordered sequence of the behavior performance vectors of the target teaching object at the N knowledge points; S1-4, calculating the state distance between adjacent behavior performance vectors in the behavior performance vector sequence; S1-5. If the state distance exceeds the distance threshold, the corresponding adjacent behavior performance vectors are concatenated into a jump vector; S1-6, traverse P target teaching objects and repeatedly obtain jump vectors until a jump vector set containing J jump vectors is generated.

[0007] In some specific embodiments, obtaining the learning mastery of M original teaching objects in N knowledge points in a teaching subject includes: S1-1-1. Obtain several behavioral performance parameters of the original teaching object at each knowledge point; S1-1-2. Normalize several behavioral performance parameters to obtain several behavioral performance characteristics of the original teaching object at each knowledge point; S1-1-3. Perform weighted summation of several behavioral performance characteristics to generate the learning mastery of the original teaching subject at each knowledge point; S1-1-4. Repeatedly obtain the learning mastery of the original teaching subjects in N knowledge points until the learning mastery of M original teaching subjects in N knowledge points is obtained.

[0008] In some specific embodiments, obtaining a behavior performance vector sequence of the target teaching object on N knowledge points includes: S1-3-1. Determine the behavioral performance characteristics of the target teaching object at each knowledge point based on the behavioral performance characteristics of the original teaching object at each knowledge point; S1-3-2. Constructing a behavior performance vector of the target teaching object at each knowledge point based on a number of behavior performance characteristics of the target teaching object at each knowledge point; S1-3-3. Obtain the behavior performance vectors of the target teaching object at N knowledge points, and sort the behavior performance vectors of the N knowledge points based on the teaching order of the N knowledge points to obtain the behavior performance vector sequence.

[0009] In some specific embodiments, performing nearest neighbor clustering on the J jump vectors in the jump vector set to generate K jump vector clusters includes: S2-1, randomly selecting K jump vectors from the jump vector set as initial cluster centers; S2-2. For each jump vector, calculate its Euclidean distance with the K initial cluster centers to obtain K Euclidean distances for each jump vector; S2-3. Select the minimum Euclidean distance from the K Euclidean distances of each jump vector; S2-4, assign J jump vectors to the initial cluster center with the minimum Euclidean distance, and obtain K initial clusters; S2-5, calculating the centroid of the jump vector in each initial cluster and determining K centroids; S2-6, take the K centroids as the next round of cluster centers; S2-7, calculating the change distance between the next round of cluster centers and the initial cluster centers; S2-8. If the change distance is greater than the threshold, repeatedly traverse the jump vector set and assign J jump vectors to the next round of cluster centers with the minimum Euclidean distance from them until the change distance of the cluster center is less than the threshold; S2-9. Define the cluster center and its assigned skip vector when the change distance of the cluster center is less than a threshold as the skip vector clustering cluster, so as to generate K skip vector clusters.

[0010] In some specific embodiments, calculating the Gini coefficients of J jump vectors in K jump vector clusters includes: S3-1. Obtain the number of jump vectors contained in each jump vector cluster and the total number of jump vectors in the K jump vector clusters; S3-2. Calculate the Gini coefficients of the J jump vectors based on the number of jump vectors contained in each jump vector cluster and the total number of jump vectors in the K jump vector clusters. The calculation formula of the Gini coefficient is: ; Among them, G is the Gini coefficient of J jump vectors, K is the number of jump vector clusters, and J is the total number of jump vectors in the jump vector set. Indicates the number of jump vectors contained in the i-th jump vector cluster.

[0011] In some specific embodiments, structural jump screening is performed on K jump vector clusters until S structural jump clusters are obtained, including: S4-1. Obtain the average Euclidean distance from the jump vector to the cluster center in each jump vector cluster; S4-2. Calculate the structural jump index of each jump vector cluster based on the Gini coefficients of the J jump vectors, the number of jump vectors contained in each jump vector cluster, and the average Euclidean distance of each jump vector cluster; The calculation formula of the structural jump index is: ; Among them, the represents the structural jump index of the i-th jump vector cluster, Indicates the logarithmic transformation of the Gini coefficient, which is used to adjust the impact of the Gini coefficient and avoid the skewness of the indicator caused by an excessively high G value; represents the frequency ratio adjustment item of the i-th jump vector cluster, represents the average Euclidean distance of the i-th jump vector cluster, which is used to measure the stability within the jump vector cluster; To prevent division by zero for small constants, Indicates the intra-cluster compactness of the i-th jump vector cluster. The larger the value, the higher the consistency of the jump vector. and Respectively represent the weight factors of the frequency ratio adjustment item and the cluster compactness adjustment item; S4-3, obtaining structural jump indices of K jump vector clusters; S4-4, sorting the structural jump indices of the K jump vector clusters to generate a structural jump sequence; S4-5. Select the top S structural jump clusters from the structural jump sequence.

[0012] In some specific embodiments, locating jump knowledge points based on S structural jump clusters includes: S5-1, extracting structural jump vectors from S structural jump clusters; S5-2, obtaining adjacent knowledge points of the structural jump vector; S5-3, defining the next knowledge point in the adjacent knowledge point pair as the skipping knowledge point; S5-4. Obtain some content feedback from the target teaching object regarding the skipped knowledge points, and perform micro-reconstruction of the knowledge points based on the some content feedback.

[0013] Compared with the prior art, the present invention provides an intelligent teaching service method. The present invention solves the problem that jump performance is difficult to uniformly model due to excessive differences in individual behavior by constructing jump vectors of the target teaching object on adjacent knowledge points and classifying all jump vectors using the nearest neighbor clustering method. Jump vectors with similar behavioral characteristics are clustered in the same cluster, providing a structural division basis for subsequent identification. Based on the clustering results, the Gini coefficient is introduced to measure the distribution concentration of jump vectors in each cluster, and a structural jump index is constructed by combining multi-dimensional factors such as jump frequency ratio and average distance within the cluster, thereby achieving quantitative screening of jump clusters and effectively improving the recognition accuracy of jump behaviors with group commonality. By extracting the knowledge point pairs corresponding to the jump vectors in the structural jump clusters and defining the latter knowledge point as a jump knowledge point, the clear positioning of the jump knowledge points in the teaching path is achieved, providing support for content feedback acquisition and knowledge point micro-reconstruction.

[0014] In a second aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores at least one computer-executable instruction, and the processor is configured to run the computer-executable instruction. When the computer-executable instruction is run by the processor, the teaching intelligent service method described in the first aspect is implemented.

[0015] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the teaching intelligent service method described in the first aspect is implemented.

[0016] Compared with the prior art, the beneficial effects of the electronic device and storage medium thereof of the present invention are the same as the beneficial effects of the above-mentioned teaching intelligent service method, so they will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of an intelligent teaching service method according to the present invention; Figure 2 Schematic diagram of the process of generating the jump vector cluster according to the present invention; Figure 3 Schematic diagram of the selection process of the structural jump clustering cluster described in the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] See also Figures 1 to 3 The present invention provides a teaching intelligent service method, comprising the following steps: S1. Obtain a jump vector set of P target teaching objects; wherein the jump vector set includes J jump vectors; It should be noted that the jump vector represents a joint behavior vector constructed when there is a significant difference in the behavior performance of the target teaching subject in the learning task of two adjacent knowledge points. Specifically, the jump vector is formed by splicing the behavior performance vectors of the teaching subject at the previous knowledge point and the next knowledge point, and is used to represent the turning point behavior of the learning style change. S2. performing nearest neighbor clustering on the J jump vectors in the jump vector set to generate K jump vector clusters; S3, calculating the Gini coefficients of the J jump vectors in the K jump vector clusters; S4, comparing the Gini coefficients of the K jump vector clusters with the coefficient threshold; If the Gini coefficient is less than the coefficient threshold, it is determined that there is no significant structural jump in the learning path of the target teaching object; otherwise, the K jump vector clusters are screened for structural jumps until S structural jump clusters are obtained; S5. Locate the jump knowledge points based on the S structural jump clusters.

[0020] In this embodiment, by constructing jump vectors and using nearest neighbor clustering and the Gini coefficient to identify the locations of structural jumps in the target teaching subject's learning path, the ability to model sudden changes in behavioral style during the teaching process is improved. By concatenating the behavioral performance vectors of two adjacent knowledge points, the jump vector can accurately capture the behavioral differences of the teaching subject in continuous learning tasks. By clustering all jump vectors and introducing the Gini coefficient to measure their distribution concentration, it is easier to distinguish between occasional jumps and structural jumps with common characteristics, avoiding the limitations of traditional behavioral analysis where individual fluctuations interfere with recognition results. Finally, by comparing the Gini coefficient with a threshold and screening representative jump clusters, the jump knowledge points are located.

[0021] Exemplarily, in this embodiment, step S1 further includes: S1-1, obtaining the learning mastery of M original teaching subjects in N knowledge points in the teaching subject; S1-2, select P target teaching subjects from M original teaching subjects whose learning and mastery of N knowledge points all exceed the mastery threshold; Specifically, in this embodiment, the "original teaching object" refers to the individual unit participating in the teaching task, which can be a student, trainee, or other form of learning participant. The "target teaching object" refers to the subset of the original teaching objects that meet certain learning performance conditions (such as the learning mastery of each knowledge point exceeds a preset threshold); S1-3. For each target teaching object, obtain a behavior performance vector sequence of the target teaching object at N knowledge points; wherein the behavior performance vector sequence represents an ordered sequence of the behavior performance vectors of the target teaching object at the N knowledge points; S1-4, calculating the state distance between adjacent behavior performance vectors in the behavior performance vector sequence; For example, in this embodiment, the adjacent behavior performance vector can be a test behavior feature vector of the target teaching subject on two consecutive knowledge points, including a combination of features such as test score, completion time, number of error corrections, and number of prompts used. Therefore, the state distance can preferably be selected as weighted Euclidean distance; weighted Euclidean distance can set corresponding weights based on the degree of influence of different behavioral characteristics on teaching jump changes, and has higher interpretability when identifying changes in learning style. S1-5. If the state distance exceeds the distance threshold, the corresponding adjacent behavior performance vectors are concatenated into a jump vector; It should be noted that the jump vector represents the characteristics of significant differences in the learning performance of the original teaching subject in the learning task of two adjacent knowledge points. It is used to characterize the learning style switching or learning strategy changes in the sequential teaching process. S1-6, traverse P target teaching objects and repeatedly obtain jump vectors until a jump vector set containing J jump vectors is generated; It should be noted that the number of jump vectors for each target teaching object may be different, which is determined by the number of jump vectors exceeding the distance threshold in its behavior performance vector sequence. Therefore, the obtained J jump vectors are a non-balanced distribution set.

[0022] In this example, high-quality jump behavior extraction is achieved by screening learning subjects with excellent mastery and constructing a jump vector set based on their behavioral performance vector sequences. A mastery threshold is used to effectively eliminate interference from low-quality learning trajectories on jump behavior recognition, and a state distance is used to select jump vectors that significantly exceed the threshold. Ultimately, a jump vector set containing J jump vectors is generated.

[0023] Exemplarily, the step S1-1 further includes: S1-1-1. Obtain several behavioral performance parameters of the original teaching object at each knowledge point; Among them, several behavioral performance parameters include but are not limited to test scores, test completion time, number of errors corrected, and number of prompts used; S1-1-2. Normalize several behavioral performance parameters to obtain several behavioral performance characteristics of the original teaching object at each knowledge point; S1-1-3. Perform weighted summation of several behavioral performance characteristics to generate the learning mastery of the original teaching subject at each knowledge point; S1-1-4. Repeatedly obtain the learning mastery of the original teaching subjects in N knowledge points until the learning mastery of M original teaching subjects in N knowledge points is obtained.

[0024] In this embodiment, a learning mastery metric is constructed to assess the subject's mastery level by acquiring multiple behavioral performance parameters and performing normalization and weighting. This embodiment converts raw behavioral data such as test scores, completion time, and number of revisions into a comprehensive mastery metric under a unified measurement system, ultimately yielding the learning mastery metric for N knowledge points.

[0025] Exemplarily, the step S1-3 further includes: S1-3-1. Determine the behavioral performance characteristics of the target teaching object at each knowledge point based on the behavioral performance characteristics of the original teaching object at each knowledge point; S1-3-2. Constructing a behavior performance vector of the target teaching object at each knowledge point based on a number of behavior performance characteristics of the target teaching object at each knowledge point; S1-3-3. Obtain the behavior performance vectors of the target teaching object at N knowledge points, and sort the behavior performance vectors of the N knowledge points based on the teaching order of the N knowledge points to obtain the behavior performance vector sequence.

[0026] In this embodiment, the target teaching subject's behavior performance vectors at each knowledge point are sorted based on the teaching sequence, forming a structured behavior performance vector sequence. This embodiment preserves the sequential logic of teaching tasks while ensuring complete feature representation, providing an orderly input for distance calculation of jump behaviors and identification of sequence mutations.

[0027] Exemplarily, in this embodiment, step S2 further includes: S2-1, randomly selecting K jump vectors from the jump vector set as initial cluster centers; S2-2. For each jump vector, calculate its Euclidean distance with the K initial cluster centers to obtain K Euclidean distances for each jump vector; S2-3. Select the minimum Euclidean distance from the K Euclidean distances of each jump vector; S2-4, assign J jump vectors to the initial cluster center with the minimum Euclidean distance, and obtain K initial clusters; S2-5, calculating the centroid of the jump vector in each initial cluster and determining K centroids; S2-6, take the K centroids as the next round of cluster centers; S2-7, calculating the change distance between the next round of cluster centers and the initial cluster centers; S2-8. If the change distance is greater than the threshold, repeatedly traverse the jump vector set and assign J jump vectors to the next round of cluster centers with the minimum Euclidean distance from them until the change distance of the cluster center is less than the threshold; S2-9. Define the cluster center and its assigned skip vector when the change distance of the cluster center is less than a threshold as the skip vector clustering cluster, so as to generate K skip vector clusters.

[0028] In this embodiment, an iterative clustering operation based on minimum Euclidean distance is performed on a set of jump vectors, completing the complete clustering process from initial cluster center selection, vector assignment, centroid update, to convergence determination, ultimately generating K jump vector clusters. While ensuring computational control, this embodiment utilizes multiple rounds of centroid updates to enhance the similarity of jump vectors within the same cluster and ensure that the clustering results can distinguish different jump behaviors, providing a clear-cut clustering foundation for structural jump screening.

[0029] Exemplarily, in this embodiment, step S3 further includes: S3-1. Obtain the number of jump vectors contained in each jump vector cluster and the total number of jump vectors in the K jump vector clusters; S3-2. Calculate the Gini coefficients of the J jump vectors based on the number of jump vectors contained in each jump vector cluster and the total number of jump vectors in the K jump vector clusters. The calculation formula of the Gini coefficient is: ; Among them, G is the Gini coefficient of J jump vectors, K is the number of jump vector clusters, and J is the total number of jump vectors in the jump vector set. Indicates the number of jump vectors contained in the i-th jump vector cluster.

[0030] Specifically, the Gini coefficient measures the distribution and concentration of jump vectors within each jump vector cluster by calculating the normalized cumulative difference in the number of jump vectors within each jump vector cluster. A Gini coefficient close to 0 indicates a relatively uniform distribution of jump vectors across each jump vector cluster, indicating that jump behavior is relatively dispersed and lacks structural characteristics. A Gini coefficient close to 1 indicates that jump vectors are concentrated in a few jump vector clusters, indicating the presence of high-frequency, typical jump patterns, which can be used to identify structural jump clusters. In other words, the Gini coefficient is used to determine whether jump behavior is concentrated within clusters. If certain jump behaviors are repeatedly identified in a group of target subjects and clustered in a few jump patterns, this indicates the presence of common structural jumps within the learning path. Otherwise, the jump behaviors are likely due to individual differences or incidental factors and lack universal value for optimizing teaching structures.

[0031] In this embodiment, the structural nature of jump behavior is quantified by calculating the distribution of jump vectors within each cluster and introducing the Gini coefficient for concentration analysis. As an indicator of the uneven distribution of jump vectors, the Gini coefficient can identify whether jump behavior is concentrated in a small number of clusters, thereby determining whether it exhibits group commonality.

[0032] Exemplarily, in this embodiment, step S4 further includes: S4-1. Obtain the average Euclidean distance from the jump vector to the cluster center in each jump vector cluster; S4-2. Calculate the structural jump index of each jump vector cluster based on the Gini coefficients of the J jump vectors, the number of jump vectors contained in each jump vector cluster, and the average Euclidean distance of each jump vector cluster; The calculation formula of the structural jump index is: ; Among them, the represents the structural jump index of the i-th jump vector cluster, Indicates the logarithmic transformation of the Gini coefficient, which is used to adjust the impact of the Gini coefficient and avoid the skewness of the indicator caused by an excessively high G value; represents the frequency ratio adjustment item of the i-th jump vector cluster, reflecting the possibility of the jump vector cluster as a “main contributor”; represents the average Euclidean distance of the i-th jump vector cluster, which is used to measure the stability within the jump vector cluster; To prevent division by zero for small constants, Indicates the intra-cluster compactness of the i-th jump vector cluster. The larger the value, the higher the consistency of the jump vector. and Respectively represent the weight factors of the frequency ratio adjustment item and the cluster compactness adjustment item; S4-3, obtaining structural jump indices of K jump vector clusters; S4-4, sorting the structural jump indices of the K jump vector clusters to generate a structural jump sequence; S4-5. Select the top S structural jump clusters from the structural jump sequence.

[0033] In this embodiment, by constructing a structural jump index that integrates the Gini coefficient, the average Euclidean distance within the cluster, and the number of jump vectors, the quantification and ranking of K jump vector clusters are achieved. This index logically combines three key factors: the Gini coefficient is used to measure the concentration of jump behavior, reflecting whether the cluster represents a common jump pattern of the group; the average Euclidean distance is used to measure the consistency of jump vectors within the cluster to ensure that the selected cluster has internally stable behavioral characteristics; the proportion of the number of jump vectors is used as a dominant reference to reflect the relative influence of the cluster in the overall jump behavior. By fusing and calculating the above factors, the structural strength of the cluster can be determined on a multidimensional scale, and then the top S structural jump clusters can be screened out to provide a reliable basis for the positioning of jump knowledge points. This method avoids the deviation caused by single-factor screening and realizes multi-dimensional discrimination of structural jump identification.

[0034] Exemplarily, in this embodiment, step S5 further includes: S5-1, extracting structural jump vectors from S structural jump clusters; S5-2, obtaining adjacent knowledge points of the structural jump vector; S5-3, defining the next knowledge point in the adjacent knowledge point pair as the skipping knowledge point; S5-4. Obtain some content feedback from the target teaching object regarding the skipped knowledge points, and perform micro-reconstruction of the knowledge points based on the some content feedback.

[0035] Furthermore, micro-reconstruction of knowledge points based on feedback from a number of content points refers to structural adjustments to the teaching content of the skipped knowledge points based on the learning behavior characteristics of the target teaching subjects at the skipped knowledge points, combined with feedback parameters such as error rate, prompt dependency, and correction path. Specifically, it includes: Rearrange the structure or difficulty order of question options, insert transitional exercises or video materials related to the knowledge points before jumping, add a layered prompt mechanism or answer guidance logic, or recommend personalized explanation modules based on the error cause clustering results, so that the teaching design of skipping knowledge points is more in line with learning behavior, thereby improving its coherence in the teaching sequence.

[0036] A teaching intelligent service method in this embodiment, through the present invention, constructs jump vectors of the target teaching object on adjacent knowledge points, and classifies all jump vectors by using the nearest neighbor clustering method, thereby solving the problem that the jump performance is difficult to uniformly model due to the large differences in individual behavior, so that jump vectors with similar behavioral characteristics are clustered in the same cluster, providing a structural division basis for subsequent identification. Based on the clustering results, the Gini coefficient is introduced to measure the distribution concentration of jump vectors in each cluster, and a structural jump index is constructed by combining multi-dimensional factors such as the jump frequency ratio and the average distance within the cluster, thereby achieving quantitative screening of jump clusters and effectively improving the recognition accuracy of jump behaviors with group commonality. By extracting the knowledge point pairs corresponding to the jump vectors in the structural jump clusters and defining the latter knowledge point as a jump knowledge point, a clear positioning of the jump knowledge points in the teaching path is achieved.

[0037] An embodiment of the present invention also provides an electronic device, which includes a memory and a processor, wherein the memory stores at least one computer-executable instruction, and the processor is configured to run the computer-executable instruction. When the computer-executable instruction is run by the processor, the above-mentioned teaching intelligent service method is implemented.

[0038] The electronic device may include a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The processor may call logic instructions in the memory to execute a teaching intelligent service method disclosed in this embodiment.

[0039] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0040] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (e.g., infrared, wireless, microwave, etc.).

[0041] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative, and for example, multiple units or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0042] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A teaching intelligent service method, characterized in that: include: S1. Obtain a jump vector set of P target teaching objects; wherein the jump vector set includes J jump vectors; S2. performing nearest neighbor clustering on the J jump vectors in the jump vector set to generate K jump vector clusters; S3, calculating the Gini coefficients of the J jump vectors in the K jump vector clusters; S4, comparing the Gini coefficients of the K jump vector clusters with the coefficient threshold; If the Gini coefficient is less than the coefficient threshold, it is determined that there is no significant structural jump in the learning path of the target teaching object; otherwise, the K jump vector clusters are screened for structural jumps until S structural jump clusters are obtained; S5. Locate the jump knowledge points based on the S structural jump clusters.

2. A teaching intelligent service method according to claim 1, characterized in that: Obtain the jump vector set of P target teaching objects, including: S1-1, obtaining the learning mastery of M original teaching subjects in N knowledge points in the teaching subject; S1-2, select P target teaching subjects from M original teaching subjects whose learning and mastery of N knowledge points all exceed the mastery threshold; S1-3. For each target teaching object, obtain a behavior performance vector sequence of the target teaching object at N knowledge points; wherein the behavior performance vector sequence represents an ordered sequence of the behavior performance vectors of the target teaching object at the N knowledge points; S1-4, calculating the state distance between adjacent behavior performance vectors in the behavior performance vector sequence; S1-5. If the state distance exceeds the distance threshold, the corresponding adjacent behavior performance vectors are concatenated into a jump vector; S1-6, traverse P target teaching objects and repeatedly obtain jump vectors until a jump vector set containing J jump vectors is generated.

3. A teaching intelligent service method according to claim 2, characterized in that: Obtain the learning mastery of M original teaching objects in N knowledge points in the teaching subject, including: S1-1-1. Obtain several behavioral performance parameters of the original teaching object at each knowledge point; S1-1-2. Normalize several behavioral performance parameters to obtain several behavioral performance characteristics of the original teaching object at each knowledge point; S1-1-3. Perform weighted summation of several behavioral performance characteristics to generate the learning mastery of the original teaching subject at each knowledge point; S1-1-4. Repeatedly obtain the learning mastery of the original teaching subjects in N knowledge points until the learning mastery of M original teaching subjects in N knowledge points is obtained.

4. A teaching intelligent service method according to claim 2, characterized in that: Obtaining a behavioral performance vector sequence of the target teaching object on N knowledge points, including: S1-3-1. Determine the behavioral performance characteristics of the target teaching object at each knowledge point based on the behavioral performance characteristics of the original teaching object at each knowledge point; S1-3-2. Constructing a behavior performance vector of the target teaching object at each knowledge point based on a number of behavior performance characteristics of the target teaching object at each knowledge point; S1-3-3. Obtain the behavior performance vectors of the target teaching object at N knowledge points, and sort the behavior performance vectors of the N knowledge points based on the teaching order of the N knowledge points to obtain the behavior performance vector sequence.

5. A teaching intelligent service method according to claim 2, characterized in that: Performing nearest neighbor clustering on the J jump vectors in the jump vector set to generate K jump vector clusters, including: S2-1, randomly selecting K jump vectors from the jump vector set as initial cluster centers; S2-2. For each jump vector, calculate its Euclidean distance with the K initial cluster centers to obtain K Euclidean distances for each jump vector; S2-3. Select the minimum Euclidean distance from the K Euclidean distances of each jump vector; S2-4, assign J jump vectors to the initial cluster center with the minimum Euclidean distance, and obtain K initial clusters; S2-5, calculating the centroid of the jump vector in each initial cluster and determining K centroids; S2-6, take the K centroids as the next round of cluster centers; S2-7, calculating the change distance between the next round of cluster centers and the initial cluster centers; S2-8. If the change distance is greater than or equal to the threshold, repeatedly traverse the jump vector set and assign J jump vectors to the next round of cluster centers with the minimum Euclidean distance from them until the change distance of the cluster center is less than the threshold; S2-9. Define the cluster center and its assigned skip vector when the change distance of the cluster center is less than a threshold as the skip vector clustering cluster, so as to generate K skip vector clusters.

6. A teaching intelligent service method according to claim 2, characterized in that: Calculate the Gini coefficient of J jump vectors in K jump vector clusters, including: S3-1. Obtain the number of jump vectors contained in each jump vector cluster and the total number of jump vectors in the K jump vector clusters; S3-2. Calculate the Gini coefficients of the J jump vectors based on the number of jump vectors contained in each jump vector cluster and the total number of jump vectors in the K jump vector clusters. The calculation formula of the Gini coefficient is: ； Among them, G is the Gini coefficient of J jump vectors, K is the number of jump vector clusters, and J is the total number of jump vectors in the jump vector set. Indicates the number of jump vectors contained in the i-th jump vector cluster.

7. A teaching intelligent service method according to claim 2, characterized in that: Perform structural jump screening on the K jump vector clusters until S structural jump clusters are obtained, including: S4-1. Obtain the average Euclidean distance from the jump vector to the cluster center in each jump vector cluster; S4-2. Calculate the structural jump index of each jump vector cluster based on the Gini coefficients of the J jump vectors, the number of jump vectors contained in each jump vector cluster, and the average Euclidean distance of each jump vector cluster; The calculation formula of the structural jump index is: ； in, represents the structural jump index of the i-th jump vector cluster, Indicates that the Gini coefficient is logarithmically transformed to adjust the impact of the Gini coefficient and avoid the index being skewed due to excessively high G values; represents the frequency ratio adjustment item of the i-th jump vector cluster, represents the average Euclidean distance of the i-th jump vector cluster, which is used to measure the stability within the jump vector cluster; To prevent division by zero for small constants, Indicates the intra-cluster compactness of the i-th jump vector cluster. The larger the value, the higher the consistency of the jump vector. and Respectively represent the weight factors of the frequency ratio adjustment item and the cluster compactness adjustment item; S4-3, obtaining structural jump indices of K jump vector clusters; S4-4, sorting the structural jump indices of the K jump vector clusters to generate a structural jump sequence; S4-5. Select the top S structural jump clusters from the structural jump sequence.

8. The teaching intelligent service method according to claim 2, characterized in that: Based on S structural jump clusters, jump knowledge points are located, including: S5-1, extracting structural jump vectors from S structural jump clusters; S5-2, obtaining adjacent knowledge points of the structural jump vector; S5-3, defining the next knowledge point in the adjacent knowledge point pair as the skipping knowledge point; S5-4. Obtain some content feedback from the target teaching object regarding the skipped knowledge points, and perform micro-reconstruction of the knowledge points based on the some content feedback.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores at least one computer-executable instruction, and the processor is configured to execute the computer-executable instruction. When the computer-executable instruction is executed by the processor, the teaching intelligent service method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the teaching intelligent service method according to any one of claims 1 to 8 is implemented.

Images