Knowledge graph-based learning path analysis methods, devices, equipment, and media

Abstract

This application discloses a learning path analysis method, apparatus, device, and medium based on knowledge graphs, relating to the field of online learning platform analysis. The method includes: determining knowledge behavior events and learning behavior events based on user operation information and the knowledge graph of the online learning platform, thereby determining structured user operation record data; and using a timestamp sequence analysis method to determine the knowledge point learning sequence and learning behavior sequence, thereby determining the basic sequence of the learning path; extracting behavioral pattern features based on learning behavior events; calculating the knowledge correlation degree of the learning path using a hidden Markov model based on the relationships between nodes in the knowledge graph; and determining a learning path representation model based on the behavioral pattern features, the knowledge correlation degree of the learning path, and the basic sequence of the learning path. This application can combine the user's learning behavior pattern with the knowledge point learning sequence and can evaluate the correlation between learning behavior and knowledge points, and between preceding and subsequent knowledge points.

Description

Technical Field

[0001] This application relates to the field of online learning platform analysis, and in particular to a method, apparatus, device, and medium for learning path analysis based on knowledge graphs. Background Technology

[0002] In online learning platforms, user (e.g., student) learning paths are often limited to simple access log recordings, lacking comprehensive consideration and in-depth analysis of knowledge point connections and learning behaviors. When analyzing user learning behavior, these systems focus primarily on superficial data such as the number of actions and page visit time, failing to accurately depict the learner's knowledge acquisition process. Most platforms currently lack suitable technical solutions for effectively combining user learning behavior patterns with the order in which knowledge points are learned. Furthermore, existing learning path analysis methods typically cannot dynamically assess the correlation between learning behaviors and knowledge points, resulting in limited effectiveness of path optimization and personalized teaching suggestions based on this approach. Summary of the Invention

[0003] The purpose of this application is to provide a learning path analysis method, apparatus, device, and medium based on knowledge graphs, which can combine users' learning behavior patterns with the learning sequence of knowledge points, and evaluate the correlation between learning behavior and knowledge points, as well as the correlation between previous and subsequent knowledge points, so as to improve users' learning efficiency and learning effectiveness.

[0004] To achieve the above objectives, this application provides the following solution:

[0005] Firstly, this application provides a knowledge graph-based learning path analysis method, including:

[0006] The system acquires user operation information from an online learning platform; the online learning platform has a knowledge graph; the nodes in the knowledge graph represent knowledge points in the online learning platform; the connections between nodes in the knowledge graph represent the relationships between knowledge points in the online learning platform.

[0007] Based on the user operation information and the knowledge graph, knowledge behavior events and learning behavior events are determined, and structured user operation record data is determined based on the knowledge behavior events and the learning behavior events.

[0008] Based on structured user operation record data, a timestamp-based sequential analysis method is used to determine the knowledge point learning sequence and the learning behavior sequence;

[0009] The basic sequence of the learning path is determined based on the knowledge point learning sequence and the learning behavior sequence.

[0010] Behavioral pattern features are extracted from the learning behavior events; the behavioral pattern features include: behavior frequency, behavior duration, and behavior conversion rate.

[0011] The knowledge relevance of the learning path is calculated using a hidden Markov model based on the relationships between nodes in the knowledge graph.

[0012] The learning path representation model is determined based on the behavioral pattern characteristics, the knowledge relevance of the learning path, and the basic sequence of the learning path. The learning path representation model is used to represent the correspondence between the user's learning behavior pattern and the learning order of knowledge points, the relevance between learning behavior and knowledge points, and the relevance between knowledge points.

[0013] Secondly, this application provides a knowledge graph-based learning path analysis device, comprising:

[0014] An information acquisition module is used to acquire user operation information of an online learning platform; the online learning platform has a knowledge graph; the nodes in the knowledge graph represent knowledge points in the online learning platform; the connections between nodes in the knowledge graph represent the relationships between knowledge points in the online learning platform.

[0015] The structured data determination module is used to determine knowledge behavior events and learning behavior events based on the user operation information and the knowledge graph, and to determine structured user operation record data based on the knowledge behavior events and the learning behavior events.

[0016] The knowledge point and learning behavior sequence extraction module is used to determine the knowledge point learning sequence and learning behavior sequence based on the timestamp sequence analysis method of structured user operation record data.

[0017] The learning path basic sequence determination module is used to determine the basic sequence of the learning path based on the knowledge point learning sequence and the learning behavior sequence.

[0018] The behavior pattern feature extraction module is used to extract behavior pattern features based on the learned behavior events; the behavior pattern features include: behavior frequency, behavior duration, and behavior conversion rate.

[0019] The knowledge relevance calculation module is used to calculate the knowledge relevance of the learning path using a hidden Markov model based on the relationships between nodes in the knowledge graph.

[0020] The learning path representation module is used to determine the learning path representation model based on the behavioral pattern characteristics, the knowledge relevance of the learning path, and the basic sequence of the learning path. The learning path representation model is used to represent the correspondence between the user's learning behavior pattern and the learning order of knowledge points, the relevance between learning behavior and knowledge points, and the relevance between knowledge points.

[0021] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the knowledge graph-based learning path analysis method described in any one of the above.

[0022] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the knowledge graph-based learning path analysis method described above.

[0023] According to the specific embodiments provided in this application, this application has the following technical effects:

[0024] This application provides a learning path analysis method, apparatus, device, and medium based on knowledge graphs. Based on user operation information and incorporating knowledge graphs, it determines the basic sequence of learning paths, enabling learning path mining. By extracting behavioral pattern features from learning behavior events and using a Hidden Markov Model to calculate the knowledge correlation degree of the learning path based on the relationships between nodes in the knowledge graph, a learning path representation model is determined based on the behavioral pattern features, the knowledge correlation degree, and the basic sequence of the learning path, thus representing the learning path. This application not only combines user learning behavior patterns with the learning sequence of knowledge points but also assesses the correlation between learning behaviors and knowledge points, as well as the correlation between knowledge points themselves. By guiding user learning based on the learning path representation model, it helps improve user learning efficiency and effectiveness. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is an application environment diagram of a knowledge graph-based learning path analysis method in one embodiment of this application;

[0027] Figure 2 A flowchart illustrating a knowledge graph-based learning path analysis method provided in one embodiment of this application;

[0028] Figure 3 A diagram illustrating the implementation process of a knowledge graph-based learning path analysis method provided in an embodiment of this application in a practical application;

[0029] Figure 4A schematic diagram of the functional modules of a knowledge graph-based learning path analysis device provided in another embodiment of this application;

[0030] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] In this application, all actions to acquire signals, information, or data are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0034] Addressing the issues of superficial data analysis and a lack of personalized path analysis in current online learning platforms, this application proposes a knowledge graph-based learning path analysis method. This method enables learning path mining and representation using knowledge graphs. With the rapid development of smart education technology, how to utilize knowledge graphs and advanced data mining techniques to deeply analyze the correlation between students' learning behaviors and knowledge points has become an important direction in personalized education research. Under this premise, this application proposes a complete learning path analysis method based on user learning behavior data and the node relationships of the knowledge graph. By introducing Hidden Markov Models (HMMs) and transition probability matrices, it solves the current problem of not being able to accurately assess the correlation between knowledge points in the learning path. Through multi-dimensional quantitative analysis of learning behavior, not only is the accuracy of the learning path improved, but it also provides a basis for subsequent path optimization and personalized teaching strategies.

[0035] The knowledge graph-based learning path analysis method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send user operation information to server 104. After receiving the user operation information, server 104, based on the user operation information and the knowledge graph, determines knowledge behavior events and learning behavior events, and determines structured user operation record data based on these events. Based on the structured user operation record data, it uses a timestamp sequence analysis method to determine the knowledge point learning sequence and learning behavior sequence; it determines the basic sequence of the learning path based on the knowledge point learning sequence and learning behavior sequence; it extracts behavioral pattern features based on the learning behavior events; it calculates the knowledge correlation degree of the learning path using a hidden Markov model based on the relationships between nodes in the knowledge graph; and it determines the learning path representation model based on the behavioral pattern features, the knowledge correlation degree of the learning path, and the basic sequence of the learning path.

[0036] Server 104 can feed back the obtained learning path representation model to terminal 102. Furthermore, in some embodiments, the knowledge graph-based learning path analysis method can also be implemented independently by server 104 or terminal 102. For example, terminal 102 can directly process user operation information, or server 104 can obtain user operation information from the data storage system and process it.

[0037] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0038] In one exemplary embodiment, such as Figure 2 As shown, a knowledge graph-based learning path analysis method is provided. This method is executed by a computer device, specifically a terminal or server, or both. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 207. Wherein:

[0039] Step 201: Obtain user operation information from the online learning platform; the online learning platform has a knowledge graph.

[0040] Specifically, the online learning platform can be a smart education online learning platform with a learning environment that has a course knowledge graph or professional knowledge graph, and can monitor and store user operation information.

[0041] In this knowledge graph, nodes represent knowledge points within the online learning platform; connections between nodes represent relationships between these knowledge points. These relationships include: prerequisite relationships, subsequent relationships, inclusion relationships, and similarity relationships. Prerequisite relationship: Node A is a prerequisite for node B; learning node A helps in understanding node B. Subsequent relationship: Node A is subsequent knowledge of node B; understanding node A is necessary for learning node B. Inclusion relationship: Some knowledge nodes are contained within the content of other nodes. Similarity relationship: Knowledge nodes share similarities but do not completely overlap.

[0042] Step 202: Based on the user operation information and the knowledge graph, determine knowledge behavior events and learning behavior events, and determine structured user operation record data based on the knowledge behavior events and the learning behavior events.

[0043] Step 203: Based on the structured user operation record data, the timestamp sequence analysis method is used to determine the knowledge point learning sequence and the learning behavior sequence.

[0044] Step 204: Determine the basic sequence of the learning path based on the knowledge point learning sequence and the learning behavior sequence.

[0045] Step 205: Extract behavioral pattern features based on the learning behavior events.

[0046] The behavioral pattern features include: behavior frequency, behavior duration, and behavior conversion rate.

[0047] Step 206: Calculate the knowledge association degree of the learning path using a hidden Markov model based on the relationships between nodes in the knowledge graph.

[0048] Step 207: Determine the learning path representation model based on the behavioral pattern features, the knowledge correlation degree of the learning path, and the basic sequence of the learning path.

[0049] The learning path representation model is used to represent the correspondence between the user's learning behavior pattern and the learning order of knowledge points, the correlation between learning behavior and knowledge points, and the correlation between knowledge points.

[0050] Current systems analyzing user learning behavior focus primarily on superficial data such as the frequency of actions and page visit time, lacking deep integration with professional knowledge graphs. This makes it difficult to accurately depict the learner's knowledge acquisition process. However, implementing steps 201 to 207, based on the learning path representation model determined by the knowledge graph, can combine user learning behavior patterns with the order of knowledge point learning, assess the correlation between learning behaviors and knowledge points, and guide user learning according to the learning path representation model, thus improving learning efficiency and effectiveness.

[0051] In another exemplary embodiment of this application, step 202 specifically includes:

[0052] (1) Determine the operation events during the user's learning process based on the user operation information. Among them, the event is defined as: based on the functional characteristics of the online learning platform, define operation events such as node access, function use, login and logout during the user's learning process.

[0053] (2) Determine knowledge behavior events and learning behavior events based on whether the operation event directly affects the nodes in the knowledge graph.

[0054] (3) Collect the basic attributes of the knowledge behavior events to obtain knowledge behavior operation data, and collect the basic attributes of the learning behavior events to obtain learning behavior operation data. The basic attributes include: user ID, accessed page, page type, and access time.

[0055] (4) Perform data structuring on the knowledge behavior operation data and the learning behavior operation data respectively to obtain structured knowledge behavior operation data and structured learning behavior operation data; the structured user operation record data includes: structured knowledge behavior operation data and structured learning behavior operation data.

[0056] The main purpose of structured processing of user operation records is to clean up irrelevant data and calculate the duration of each operation. The data structuring process can be as follows: export user operation data record files (knowledge behavior operation data and learning behavior operation data) — filter irrelevant page data based on page type data — remove blank and duplicate data — sort data by user ID and access time — calculate the duration of the previous action by the time difference between adjacent data — match data with events according to the event definition — obtain structured user operation record data and store it in CSV format.

[0057] In another exemplary embodiment of this application, step 203 specifically includes:

[0058] (1) Extract a set of knowledge points and a set of learning behaviors based on structured user operation record data; the set of knowledge points includes: knowledge point information accessed by the user in the knowledge graph; the set of learning behaviors includes: operation behavior information performed by the user during the learning process.

[0059] Knowledge point information extraction: Based on node access information in the knowledge graph, extract the set P(N) of knowledge points accessed by the user. i This set of knowledge points represents the knowledge content experienced by the user, and its basic identifier is the page information of the node type in the "Page Type" tag.

[0060] Operational behavior information extraction: Based on the event definition formed by the time difference between adjacent data, extract the operational behaviors performed by the user during the learning process (such as practicing exercises, downloading materials, interrupting learning, etc.) to obtain the learning behavior set Q(A). i ).

[0061] (2) The knowledge point set is sorted according to the access time point by the timestamp order analysis method to obtain the knowledge point learning sequence.

[0062] Timestamp-based sequential analysis: First, the set of knowledge points accessed by the user, P(N), is... i Sort the knowledge points according to the access time t to form a learning sequence. For example, user U i The nodes visited at time points t1, t2, and t3 are N1, N2, and N3, respectively. The order of their knowledge points is: N1→N2→N3, denoted as a vector: K=[N1 N2 N3]. The knowledge point learning sequence is represented as K(N i ).

[0063] (3) The learning behavior set is sorted according to the access time point using the timestamp order analysis method to obtain the learning behavior sequence.

[0064] Timestamp-based sequential analysis: First, the set of learning behaviors Q(A) is formed by the user's actions during the learning process. i Sort the data according to the access time point t to form a learning behavior sequence. For example, user U... i The actions performed at time points t1, t2, and t3 are A1, A2, and A3, respectively. The learning sequence of these actions is: A1→A2→A3, denoted as a vector: T=[A1 A2 A3]. The learning sequence is represented as T(A1 → A2 → A3). i ).

[0065] In another exemplary embodiment of this application, step 204 specifically includes:

[0066] (1) The knowledge point learning sequence and the learning behavior sequence are integrated in the form of a matrix to determine the integration matrix; the rows of the integration matrix represent the temporal relationship of each event, and the columns of the integration matrix represent the correspondence between learning behaviors and knowledge points.

[0067] Specifically, a 2×n matrix is ​​used to integrate the knowledge point learning sequence and the learning behavior sequence. Rows represent the temporal relationship between events in the learning path, and columns represent the correspondence between behaviors and knowledge points. The expression for the integration matrix is:

[0068] (2) The knowledge points in the integration matrix that do not correspond to the learning behaviors are filled in to obtain the basic sequence of learning paths; the knowledge points in the basic sequence of learning paths correspond one-to-one with the learning behaviors.

[0069] Specifically, from a vertical perspective, knowledge behaviors can all correspond to specific knowledge node information, but non-knowledge behaviors (i.e., learning behaviors) cannot find corresponding knowledge nodes. In this embodiment, zeros can be used to pad the vector. Furthermore, when the same behavior interval corresponds to multiple knowledge points, the behavior is synchronously copied based on the number of knowledge points to extend the correspondence between the behavior sequence and the knowledge point sequence, thus correcting the learning path represented by the above-mentioned integrated matrix. The basic sequence representation of the corrected learning path is as follows:

[0070] In another exemplary embodiment of this application, in step 205, feature extraction is performed on learning behavior events to define and quantify behavior patterns. Behavior frequency f represents the number of times a specific learning behavior occurs throughout the learning path, quantified by statistically analyzing the frequency of various behaviors in the learning behavior sequence. Behavior duration Δt represents the time a user spends on a particular learning behavior, equal to the time difference Δt between adjacent operation events. By mapping the time difference to the behavior sequence, the duration of each behavior is obtained. Behavior conversion rate C represents the frequency of user switching between different behavior types, defined as the operation conversion frequency between discontinuous similar behaviors, calculated using the following formula: n x This indicates the number of times a certain action has been transformed, and num represents the total number of actions.

[0071] In another exemplary embodiment of this application, step 206 specifically includes:

[0072] (1) Construct a transition probability matrix between knowledge points based on the relationships between nodes in the knowledge graph.

[0073] Specifically, suppose there are a total of m nodes in the knowledge graph, and define the weight parameter P for the transformation between different nodes based on the closeness of the relationships in the knowledge graph. ijThe transition probability matrix is ​​then normalized to form an (m+1)×(m+1) matrix, ensuring that the sum of the probabilities in each row and column is 1. The expression for the transition probability matrix is ​​as follows:

[0074]

[0075] (2) Based on the transition probability matrix, the strongest correlation transition path between knowledge points is calculated using a hidden Markov model.

[0076] Specifically, based on the transition probability matrix, a hidden Markov model is used to estimate the strongest association transition path of the knowledge point sequence actually learned by the user, and to identify the knowledge path with the highest relevance in the knowledge graph. max (U i The overall transition probability NUM of the entire path is calculated using the transition probability matrix. max :

[0077] NUM max =P 12 +P 23 +……+P ij .

[0078] (3) Calculate the knowledge relevance of the learning path based on the strongest relevance transfer path.

[0079] Specifically, to calculate the actual knowledge point path relevance: First, use the same method described above to calculate the user's actual knowledge point path Path(U). i The overall transition probability NUM is calculated, and then the knowledge path with the highest relevance is calculated. max (U i Overall transition probability and user's actual learning path (Path(U)) i The difference Δd between the overall transfer probabilities NUM can be used to calculate the sum of transfer probabilities. In practice, knowledge points may be repeated. Therefore, when calculating the sum of transfer probabilities, for each repeated knowledge point, the maximum transfer probability related to it before it should be calculated, rather than only considering the transfer relationship with the previous knowledge point. The final knowledge relevance of the learning path, S, is expressed as: S = Δd = NUM max -NUM.

[0080] In another exemplary embodiment of this application, step 207 specifically includes:

[0081] (1) Integrate the behavioral pattern features and the knowledge correlation of the learning path to obtain a feature vector. Specifically, normalize the behavioral pattern features and the knowledge correlation of the learning path to obtain normalized behavioral pattern features and normalized knowledge correlation of the learning path; integrate the normalized behavioral pattern features and normalized knowledge correlation of the learning path to obtain a feature vector.

[0082] The purpose of this normalization step is to ensure the comparability of learning paths and behavioral characteristics among different users during analysis. Normalization is performed on the knowledge relevance of learning paths and behavioral pattern characteristics (behavior frequency, behavior duration, and behavior conversion rate). The normalization formula is:

[0083]

[0084] After normalization, the values ​​of all behavioral pattern features and knowledge correlations of learning paths are limited to between 0 and 1, facilitating the comparison and analysis of learning paths among different users. X represents the parameters before normalization, specifically f, Δt, C, and S. norm Let X represent the normalized parameter. min X represents the minimum value of the parameter. max This indicates the maximum value of the parameter.

[0085] The feature vector λ(t) is formed by integrating the normalized behavioral pattern features and the normalized learning path knowledge correlation, and is corresponding to the timestamp data to form data that changes over time.

[0086] (2) Integrate the feature vector with the basic sequence of the learning path to obtain the learning path representation model.

[0087] Specifically, after integrating the feature vectors with the basic sequence of the learning path, the following learning path representation model is formed:

[0088] The following is combined Figure 3 This paper describes an implementation process of the knowledge graph-based learning path analysis method described above in a practical application.

[0089] This method mines and represents students' learning paths based on professional knowledge graphs, and comprehensively constructs a learning path representation model by focusing on the characteristics of computational behavior patterns and the knowledge correlation of learning paths in a smart education platform based on professional knowledge graphs.

[0090] Step 1: Structure User Online Operation Data. 1) Define user operation events, categorizing them into knowledge behavior events and non-knowledge behavior events (i.e., learning behavior events) based on whether they directly affect knowledge graph nodes, thus achieving event classification. 2) Collect user operation records: Record the basic attributes of user online operation events. 3) Structure user operation record data.

[0091] Step 2: Extracting user knowledge point learning sequence and user learning behavior sequence information. 1) Extracting knowledge point and behavior data: Based on the user's operation records on the smart education platform, the user's learning path is extracted according to predefined events to obtain knowledge point information and operation behavior information, thereby determining the knowledge point set and learning behavior set. 2) Generation of knowledge point learning sequence and learning behavior sequence.

[0092] Step 3: Construct the basic learning path sequence. 1) Integrate the knowledge point learning sequence and the learning behavior sequence to obtain the integration matrix. 2) Fill in the non-knowledge behaviors to obtain the basic learning path sequence.

[0093] Step 4: Calculate the learning path behavior pattern features and knowledge relevance. 1) Define and quantify behavior pattern features. 2) Define the relationships between knowledge graph nodes (i.e., the relationships between knowledge points), including: prerequisite relationships, subsequent relationships, inclusion relationships, and similarity relationships. 3) Define the learning path knowledge relevance. Knowledge relevance measures the strength of the logical relationship between the knowledge points learned by the user. A transition probability matrix between knowledge points is constructed based on the node relationships in the knowledge graph. A Hidden Markov Model is used to calculate the strongest relevance transition path between knowledge points, and the relevance of the existing path (i.e., the learning path knowledge relevance) is calculated based on the strongest relevance transition matrix. 4) Data standardization processing.

[0094] Step 5: Construct a learning path representation model, which serves as the result of learning path mining and representation.

[0095] The knowledge graph-based learning path analysis method provided in this application mainly includes five steps: ① structuring user online operation data; ② extracting information on the user's knowledge point learning order and user learning behavior order; ③ constructing a basic learning path sequence; ④ calculating the learning path behavior pattern characteristics and knowledge relevance; and ⑤ constructing a learning path representation model. This method comprehensively analyzes the subjective learning behavior of users around a professional knowledge graph and the objective logical relationships between knowledge nodes, using a 3×n matrix for representation. It encompasses three types of information: Actions, Knowledge, and path characteristics, as well as the time series of each type of information. This method promotes research on student learning path analysis and learning process monitoring, solving two major problems: 1) how to comprehensively represent the student's subjective behavior and the knowledge object organization sequence; and 2) how to measure the characteristics of the student's learning path from multiple dimensions.

[0096] The above methods are mainly reflected in the path mining stage and the path representation stage: 1) In the learning path mining stage, user data is obtained through a specific operation record interface, and time series analysis is used to extract user knowledge point learning and behavior sequences based on timestamp data, and integrate them to form a basic learning path sequence; 2) In the learning path representation stage, firstly, a transition matrix between nodes is constructed based on the directed edge weights of the professional knowledge graph, and then the strongest correlation path is generated using the hidden Markov model analysis method as a standard for evaluating knowledge sequences, so as to generate the knowledge correlation degree of the learning path; In addition, behavioral pattern analysis can be performed based on the Apriori algorithm and the PrefixSpan method to extract learning behavior sequence features.

[0097] The above-mentioned knowledge graph-based learning path analysis method has the following advantages:

[0098] (1) Learning path representation based on knowledge graph: This application utilizes professional knowledge graphs to accurately extract the knowledge nodes experienced by users in the learning process and their corresponding behavioral patterns, forming a clear learning path representation model, making the connection between learning behavior and knowledge points clearer.

[0099] (2) Multi-dimensional behavioral feature quantitative analysis: By quantitatively analyzing the frequency, duration and conversion rate of user learning behavior, we can comprehensively evaluate the user's learning path behavior, gain a deeper understanding of the user's learning habits and behavior patterns, and provide support for personalized teaching strategies.

[0100] (3) Knowledge Relevance Calculation: By constructing a transition probability matrix based on knowledge graphs and using a hidden Markov model to calculate the strongest correlation path between knowledge points, the difference between the user's actual learning path and the optimal path can be effectively evaluated, providing a theoretical basis for optimizing the learning path.

[0101] (4) Precise extraction and quantification of behavioral patterns: Through precise extraction and quantification of learning behavioral patterns, this invention can effectively identify the key features of different operational behaviors of learners during the learning process, providing reliable data support for behavioral pattern analysis.

[0102] (5) Combining knowledge graph with learning behavior: This application innovatively links user learning behavior with knowledge nodes in the knowledge graph, and effectively improves the interpretability and analysis accuracy of the learning path by quantitatively evaluating the relationship between knowledge points and learning behavior in multiple dimensions.

[0103] (6) Calculation of the strongest association path based on the hidden Markov model: The strongest association path of knowledge nodes is calculated by using the hidden Markov model, which ensures the scientificity and rationality of the learning path and enhances the rigor and accuracy of the knowledge association degree calculation.

[0104] (7) Flexible path optimization support: By calculating the difference between the user's actual learning path and the strongest associated path, this application can provide learning path optimization suggestions for the education platform, thereby effectively improving learning efficiency and the depth of knowledge acquisition.

[0105] Based on the same inventive concept, this application also provides a knowledge graph-based learning path analysis device for implementing the knowledge graph-based learning path analysis method described above. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more knowledge graph-based learning path analysis device embodiments provided below can be found in the limitations of the knowledge graph-based learning path analysis method described above, and will not be repeated here.

[0106] In one exemplary embodiment, such as Figure 4 As shown, a knowledge graph-based learning path analysis device is provided, comprising:

[0107] The information acquisition module 401 is used to acquire user operation information of the online learning platform; the online learning platform has a knowledge graph; the nodes in the knowledge graph represent knowledge points in the online learning platform; the lines between the nodes in the knowledge graph represent the relationships between the knowledge points in the online learning platform.

[0108] The structured data determination module 402 is used to determine knowledge behavior events and learning behavior events based on the user operation information and the knowledge graph, and to determine structured user operation record data based on the knowledge behavior events and the learning behavior events.

[0109] The knowledge point and learning behavior sequence extraction module 403 is used to determine the knowledge point learning sequence and learning behavior sequence based on the structured user operation record data using the timestamp order analysis method.

[0110] The learning path basic sequence determination module 404 is used to determine the learning path basic sequence based on the knowledge point learning sequence and the learning behavior sequence.

[0111] The behavior pattern feature extraction module 405 is used to extract behavior pattern features based on the learning behavior events; the behavior pattern features include: behavior frequency, behavior duration and behavior conversion rate.

[0112] The knowledge relevance calculation module 406 is used to calculate the knowledge relevance of the learning path using a hidden Markov model based on the relationships between nodes in the knowledge graph.

[0113] The learning path representation module 407 is used to determine the learning path representation model based on the behavioral pattern characteristics, the knowledge relevance of the learning path, and the basic sequence of the learning path; the learning path representation model is used to represent the correspondence between the user's learning behavior pattern and the learning order of knowledge points, the relevance between learning behavior and knowledge points, and the relevance between knowledge points.

[0114] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 5 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores user operation information. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a knowledge graph-based learning path analysis method.

[0115] Those skilled in the art will understand that Figure 5The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0116] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0117] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0118] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0119] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, etc., and are not limited to these.

[0120] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A learning path analysis method based on knowledge graphs, characterized in that, The knowledge graph-based learning path analysis method includes: The system acquires user operation information from an online learning platform; the online learning platform has a knowledge graph; the nodes in the knowledge graph represent knowledge points in the online learning platform; the connections between nodes in the knowledge graph represent the relationships between knowledge points in the online learning platform. Based on the user operation information and the knowledge graph, knowledge behavior events and learning behavior events are determined, and structured user operation record data is determined based on the knowledge behavior events and the learning behavior events, specifically including: Determine the user's operational events during the learning process based on the user's operational information; Based on whether the operation event applies to a node in the knowledge graph, knowledge behavior events and learning behavior events are determined; The basic attributes of the knowledge behavior events are collected to obtain knowledge behavior operation data, and the basic attributes of the learning behavior events are collected to obtain learning behavior operation data. The knowledge behavior operation data and the learning behavior operation data are respectively subjected to data structuring processing to obtain structured knowledge behavior operation data and structured learning behavior operation data; the structured user operation record data includes: structured knowledge behavior operation data and structured learning behavior operation data; Based on structured user operation record data, a timestamp-based sequential analysis method is used to determine the knowledge point learning sequence and the learning behavior sequence; The basic sequence of the learning path is determined based on the knowledge point learning sequence and the learning behavior sequence. Behavioral pattern features are extracted based on the learning behavior events; the behavioral pattern features include: behavior frequency, behavior duration, and behavior conversion rate; the behavior conversion rate represents the frequency with which a user switches between different behavior types. Based on the relationships between nodes in the knowledge graph, a Hidden Markov Model is used to calculate the knowledge relevance of the learning path, specifically including: Construct a transition probability matrix between knowledge points based on the relationships between nodes in the knowledge graph; Based on the aforementioned transition probability matrix, a hidden Markov model is used to calculate the strongest correlation transition path between knowledge points. Calculate the knowledge relevance of the learning path based on the strongest relevance transfer path; The learning path representation model is determined based on the behavioral pattern characteristics, the knowledge relevance of the learning path, and the basic sequence of the learning path. The learning path representation model is used to represent the correspondence between the user's learning behavior pattern and the learning order of knowledge points, the relevance between learning behavior and knowledge points, and the relevance between knowledge points.

2. The knowledge graph-based learning path analysis method according to claim 1, characterized in that, Based on structured user operation record data, a timestamp-based sequential analysis method is used to determine the knowledge point learning sequence and the learning behavior sequence, specifically including: A set of knowledge points and a set of learning behaviors are extracted from structured user operation record data; the set of knowledge points includes: knowledge point information accessed by the user in the knowledge graph; the set of learning behaviors includes: operation behavior information performed by the user during the learning process; The knowledge point set is sorted according to the access time using the timestamp order analysis method to obtain the knowledge point learning sequence; The learning behavior set is sorted according to the access time point using the timestamp order analysis method to obtain the learning behavior sequence.

3. The knowledge graph-based learning path analysis method according to claim 1, characterized in that, The basic sequence of the learning path is determined based on the knowledge point learning sequence and the learning behavior sequence, specifically including: The knowledge point learning sequence and the learning behavior sequence are integrated in the form of a matrix to determine an integration matrix; the rows of the integration matrix represent the temporal relationship of each event, and the columns of the integration matrix represent the correspondence between learning behaviors and knowledge points; The knowledge points in the integration matrix that do not correspond to learning behaviors are filled in to obtain a basic sequence of learning paths; the knowledge points in the basic sequence of learning paths correspond one-to-one with the learning behaviors.

4. The knowledge graph-based learning path analysis method according to claim 1, characterized in that, The learning path representation model is determined based on the behavioral pattern characteristics, the knowledge relevance of the learning path, and the basic sequence of the learning path, specifically including: The behavioral pattern features and the knowledge correlation of the learning path are integrated to obtain a feature vector; The feature vectors are integrated with the basic sequence of the learning path to obtain the learning path representation model.

5. The knowledge graph-based learning path analysis method according to claim 4, characterized in that, The behavioral pattern features and the knowledge correlation of the learning path are integrated to obtain a feature vector, which specifically includes: The behavioral pattern features and the knowledge correlation degree of the learning path are normalized respectively to obtain normalized behavioral pattern features and normalized knowledge correlation degree of the learning path. The normalized behavioral pattern features and the normalized learning path knowledge correlation are integrated to obtain the feature vector.

6. A learning path analysis device based on knowledge graphs, characterized in that, The knowledge graph-based learning path analysis device includes: An information acquisition module is used to acquire user operation information of an online learning platform; the online learning platform has a knowledge graph; the nodes in the knowledge graph represent knowledge points in the online learning platform; the connections between nodes in the knowledge graph represent the relationships between knowledge points in the online learning platform. The structured data determination module is used to determine knowledge behavior events and learning behavior events based on the user operation information and the knowledge graph, and to determine structured user operation record data based on the knowledge behavior events and the learning behavior events, specifically including: Determine the user's operational events during the learning process based on the user's operational information; Based on whether the operation event applies to a node in the knowledge graph, knowledge behavior events and learning behavior events are determined; The basic attributes of the knowledge behavior events are collected to obtain knowledge behavior operation data, and the basic attributes of the learning behavior events are collected to obtain learning behavior operation data. The knowledge behavior operation data and the learning behavior operation data are respectively subjected to data structuring processing to obtain structured knowledge behavior operation data and structured learning behavior operation data; the structured user operation record data includes: structured knowledge behavior operation data and structured learning behavior operation data; The knowledge point and learning behavior sequence extraction module is used to determine the knowledge point learning sequence and learning behavior sequence based on the timestamp sequence analysis method of structured user operation record data. The learning path basic sequence determination module is used to determine the basic sequence of the learning path based on the knowledge point learning sequence and the learning behavior sequence. The behavior pattern feature extraction module is used to extract behavior pattern features based on the learned behavior events; the behavior pattern features include: behavior frequency, behavior duration, and behavior conversion rate; the behavior conversion rate represents the frequency with which a user switches between different behavior types. The knowledge relevance calculation module is used to calculate the knowledge relevance of the learning path using a hidden Markov model based on the relationships between nodes in the knowledge graph. Specifically, it includes: Construct a transition probability matrix between knowledge points based on the relationships between nodes in the knowledge graph; Based on the aforementioned transition probability matrix, a hidden Markov model is used to calculate the strongest correlation transition path between knowledge points. Calculate the knowledge relevance of the learning path based on the strongest relevance transfer path; The learning path representation module is used to determine the learning path representation model based on the behavioral pattern characteristics, the knowledge relevance of the learning path, and the basic sequence of the learning path. The learning path representation model is used to represent the correspondence between the user's learning behavior pattern and the learning order of knowledge points, the relevance between learning behavior and knowledge points, and the relevance between knowledge points.

7. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the knowledge graph-based learning path analysis method according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the knowledge graph-based learning path analysis method as described in any one of claims 1-5.

Images