An AI agent-based knowledge point recommendation method, device and electronic equipment

Abstract

The application discloses a knowledge point recommendation method and device based on an AI agent and electronic equipment, and relates to the technical field of education. The method comprises the following steps: acquiring learning behavior data of a student in learning a knowledge point in a knowledge point learning grid, determining question information and note information of the student in learning the knowledge point, mapping the learning behavior data in a knowledge graph corresponding to the knowledge point learning grid, obtaining learning knowledge point data of the student, generating learning content data of the student, performing multidimensional information matching on the learning content data and the learning knowledge point data, generating knowledge point positioning information of a set of unmastered knowledge points, updating the set of unmastered knowledge points to obtain a set of target unmastered knowledge points, and recommending the set of target unmastered knowledge points to the student. The application can improve the accuracy of knowledge point recommendation and realize accurate matching between knowledge point recommendation and actual learning needs of the student.

Description

Technical Field

[0001] This application relates to the field of educational technology, and in particular to a knowledge point recommendation method, device, and electronic device based on AI intelligent agents. Background Technology

[0002] Significant progress has been made in the development of intelligent learning companion systems, particularly in dynamic learning path planning and personalized content recommendation. However, current intelligent learning companion systems struggle to accurately establish a deep correspondence between student learning behaviors and knowledge graph structures, hindering their ability to accurately understand the semantics of learning content and pinpoint knowledge points.

[0003] Currently, existing intelligent learning companion systems typically associate learning activities with specific knowledge points based on simple label matching or rule mapping. This approach struggles to handle the semantic complexity and contextual ambiguity inherent in learning behavior data. Furthermore, the systems fail to adequately consider the structural position of knowledge points within the knowledge network and their overall correspondence with the learning content. This results in recommended knowledge point sets potentially lacking necessary cognitive context support, hindering the formation of coherent knowledge construction paths, and leading to a lack of comprehensive evaluation of the multi-dimensional relationships between learning content and knowledge points. Consequently, a reliable and interpretable mapping relationship cannot be established between learning behavior data and knowledge graph nodes. This results in significant discrepancies between the generated set of unmastered knowledge points and the students' actual unmastered knowledge points. Summary of the Invention

[0004] In view of this, this application provides a knowledge point recommendation method, device, and electronic device based on AI intelligent agents. The main purpose is to improve the technical problems of existing intelligent learning companion systems, which usually associate learning activities with specific knowledge points based on simple label matching or rule mapping. This approach is difficult to handle the semantic complexity and contextual ambiguity in learning behavior data. The system fails to fully consider the structural position of knowledge points in the knowledge network and their overall correspondence with the learning content. As a result, the recommended knowledge point set may lack the necessary cognitive context support, making it difficult to form a coherent knowledge construction path. This leads to a lack of comprehensive evaluation of the multi-dimensional relationship between learning content and knowledge points, and an inability to establish a reliable and interpretable mapping relationship between learning behavior data and knowledge graph nodes. This results in a large deviation between the generated set of unmastered knowledge points and the actual unmastered knowledge points of the students.

[0005] Firstly, this application provides a knowledge point recommendation method based on AI intelligent agents, including:

[0006] The learning behavior data of students learning knowledge points in the set of knowledge points they have not mastered in the knowledge point learning grid is obtained from the learning companion system. Based on the learning behavior data, the question information and note information of the students learning knowledge points in the set of knowledge points they have not mastered are determined.

[0007] The learning behavior data is mapped into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph.

[0008] Based on the question information and the note information, the student's learning content data is generated, and the learning content data is matched with the learning knowledge point data in multiple dimensions to generate the knowledge point location information of the set of unmastered knowledge points.

[0009] Based on the student's target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, the set of unmastered knowledge points is updated to obtain the target set of unmastered knowledge points, and the target set of unmastered knowledge points is recommended to the student.

[0010] Optionally, the step of generating the student's learning content data based on the question information and the note information, and performing multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information for the set of unmastered knowledge points, includes:

[0011] The student's learning content data is generated based on the question information and the note information;

[0012] Similarity matching is performed based on the first semantic embedding vector corresponding to the learning content data and the second semantic embedding vector corresponding to the learning knowledge point data to match the content similarity between the learning content data and the learning knowledge point data, and a first similarity matching result is obtained.

[0013] Similarity matching is performed based on the context data corresponding to the learning content data and the adjacent knowledge point data corresponding to the learning knowledge point data to match the overall similarity of the learning content data and the learning knowledge point data in the knowledge graph, and a second similarity matching result is obtained.

[0014] A similarity match is performed based on the first position data of the learning content data in the textbook and the second position data of the learning knowledge point data in the textbook to match the position similarity of the learning content data and the learning knowledge point data, and a third similarity match result is obtained.

[0015] Based on the first similarity matching result, the second similarity matching result, and the third similarity matching result, knowledge point location information of the set of unmastered knowledge points is generated.

[0016] Optionally, generating knowledge point location information for the set of unmastered knowledge points based on the first similarity matching result, the second similarity matching result, and the third similarity matching result includes:

[0017] A fusion analysis is performed based on the first similarity matching result, the second similarity matching result, and the third similarity matching result to evaluate the accuracy of locating knowledge points in the set of unmastered knowledge points, and to obtain the location reliability data of the learning content data and the learning knowledge point data.

[0018] Based on the location confidence data, select unacknowledged knowledge points that meet the confidence conditions from the set of unacknowledged knowledge points to form a location knowledge point set;

[0019] Based on the prior and relevance relationships of knowledge points in the set of knowledge points in the knowledge graph, the knowledge point location information of the set of unmastered knowledge points is generated.

[0020] Optionally, generating knowledge point location information for the set of unmastered knowledge points based on the prior and relevance relationships of knowledge points in the set of located knowledge points in the knowledge graph includes:

[0021] Based on the prerequisite relationships of knowledge points in the set of location knowledge points in the knowledge graph, a first set of knowledge points consisting of prerequisite knowledge points corresponding to the set of location knowledge points in the knowledge graph is determined, and a second set of knowledge points using the knowledge points in the set of location knowledge points as prerequisite knowledge points is determined.

[0022] Based on the location knowledge point set, the first knowledge point set, and the second knowledge point set, extract the knowledge point dependency chain corresponding to the unmastered knowledge point set from the knowledge graph;

[0023] Based on the correlation relationship of knowledge points in the set of location knowledge points in the knowledge graph, a third set of knowledge points related to the set of location knowledge points in the knowledge graph is determined, and the knowledge point related relationship chain corresponding to the set of unmastered knowledge points is extracted based on the set of location knowledge points and the third set of knowledge points.

[0024] Based on the knowledge point dependency relationship chain and the knowledge point related relationship chain, knowledge point location information of the set of unmastered knowledge points is generated.

[0025] Optionally, mapping the learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph includes:

[0026] The knowledge point information corresponding to the learning behavior data is determined, the knowledge point information is matched in the knowledge graph, and the knowledge point information is linked to the graph nodes in the knowledge graph according to the matching results.

[0027] Based on the graph knowledge point information corresponding to the graph nodes linked with knowledge point information, the learning knowledge point data of the student in the knowledge graph is generated.

[0028] Optionally, the step of updating the set of unmastered knowledge points to obtain a target set of unmastered knowledge points based on the student's target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, and recommending the target set of unmastered knowledge points to the student, includes:

[0029] Based on the question information and the note information, the student's learning needs for the knowledge points in the set of unmastered knowledge points are evaluated, and the learning intention intensity data corresponding to the knowledge points in the knowledge point learning grid are obtained.

[0030] Based on the learning intention intensity data, the question information, and the note information, the student's target learning intention for the knowledge points in the set of unmastered knowledge points is identified.

[0031] The set of unmastered knowledge points is updated based on the target learning intention and the knowledge point location information to obtain the target unmastered knowledge point set, and the target unmastered knowledge point set and the target learning path corresponding to the target unmastered knowledge point set are generated.

[0032] The system generates a set of knowledge points that the target student has not mastered and recommended information for the target learning path, so that the student can master the knowledge points in the set of knowledge points that the target student has not mastered based on the set of knowledge points that the target student has not mastered and the target learning path.

[0033] Optionally, the step of acquiring learning behavior data from the learning support system, showing students' learning of knowledge points in the set of unmastered knowledge points within the knowledge point learning grid, and determining the students' question information and note information for learning the knowledge points in the set of unmastered knowledge points based on the learning behavior data, includes:

[0034] The learning behavior data of students learning knowledge points in the set of knowledge points they have not mastered in the knowledge point learning grid is obtained from the learning companion system;

[0035] The student's learning behavior data in the knowledge point learning grid is divided into at least one learning behavior data set, and a set of behavioral features corresponding to the at least one learning behavior data set is generated.

[0036] Determine the time information corresponding to each behavioral feature in the behavioral feature set, and evaluate the effectiveness of each behavioral feature in the behavioral feature set based on the time information to obtain the effective value data of each behavioral feature in the behavioral feature set;

[0037] Based on the effective value data, the behavioral features in the behavioral feature set are filtered to obtain the target behavioral features that meet the effective conditions in the behavioral feature set, and the target behavioral features are combined into a target behavioral feature set.

[0038] Based on the target behavior feature set, analyze the student’s mastery of the knowledge points in the knowledge point learning grid, and determine the set of knowledge points that the student has not mastered in the knowledge point learning grid.

[0039] Identify box selection behavior from the target behavior feature set, and classify the learning content selected by the box selection behavior to obtain the question information and note information of the student learning the knowledge points in the set of unmastered knowledge points.

[0040] Secondly, this application provides a knowledge point recommendation device based on an AI intelligent agent, comprising:

[0041] The determination module is configured to obtain learning behavior data of students learning knowledge points in the set of unmastered knowledge points in the knowledge point learning grid from the learning companion system, and determine the question information and note information of the students learning knowledge points in the set of unmastered knowledge points based on the learning behavior data.

[0042] The mapping module is configured to map the learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph.

[0043] The generation module is configured to generate the student's learning content data based on the question information and the note information, and to perform multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information of the set of unmastered knowledge points.

[0044] The update module is configured to update the set of unmastered knowledge points to obtain a target set of unmastered knowledge points based on the student's target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, and recommend the target set of unmastered knowledge points to the student.

[0045] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the knowledge point recommendation method based on AI intelligent agents as described in the first aspect.

[0046] Fourthly, this application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement the knowledge point recommendation method based on AI intelligent agents as described in the first aspect.

[0047] By employing the above technical solutions, this application provides a knowledge point recommendation method, device, and electronic device based on AI intelligent agents. Compared with existing technologies, this application achieves accurate collection of core data related to student learning by obtaining learning behavior data of students' unmastered knowledge points in the knowledge point learning grid from the learning companion system and determining question information and note information, thus providing a reliable data foundation for subsequent knowledge point association and matching. By mapping the learning behavior data in the knowledge graph corresponding to the knowledge point learning grid, a deep correspondence between the learning behavior data and the knowledge graph structure is achieved, providing graph-level support for knowledge point positioning. By generating learning content data based on question information and note information and performing multi-dimensional information matching with learning knowledge point data, accurate positioning of unmastered knowledge points is achieved, improving the accuracy of knowledge point positioning. By updating and recommending the set of unmastered knowledge points based on the student's target learning intention and knowledge point positioning information, accurate matching between the target set of unmastered knowledge points and the student's actual learning needs is achieved. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 The illustration shows a flowchart of a knowledge point recommendation method based on an AI agent provided in an embodiment of this application;

[0051] Figure 2 This illustration shows a schematic diagram of a knowledge point learning grid provided in an embodiment of this application;

[0052] Figure 3 The illustration shows a flowchart of a knowledge point recommendation method based on an AI agent provided in an embodiment of this application;

[0053] Figure 4 This illustration shows a structural schematic diagram of a knowledge point recommendation device based on an AI agent, provided in an embodiment of this application.

[0054] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0055] The embodiments of this application will now be described in more detail with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0056] To improve upon existing intelligent learning companion systems, which typically associate learning activities with specific knowledge points based on simple label matching or rule mapping, this approach struggles to handle the semantic complexity and contextual ambiguity inherent in learning behavior data. Furthermore, the system fails to adequately consider the structural position of knowledge points within the knowledge network and their overall correspondence with the learning content. This results in recommended knowledge point sets potentially lacking necessary cognitive context support, hindering the formation of coherent knowledge construction paths, and leading to a lack of comprehensive evaluation of the multi-dimensional relationships between learning content and knowledge points. Consequently, it cannot establish a reliable and interpretable mapping between learning behavior data and knowledge graph nodes, resulting in significant discrepancies between the generated set of unmastered knowledge points and the student's actual unmastered knowledge points. This embodiment provides a knowledge point recommendation method based on an AI intelligent agent, such as... Figure 1 As shown, the method includes:

[0057] Step 101: Obtain learning behavior data from the learning companion system, which shows the student's learning behavior on the knowledge points in the set of knowledge points that they have not mastered in the knowledge point learning grid. Based on the learning behavior data, determine the question information and note information of the student on the knowledge points in the set of knowledge points that they have not mastered.

[0058] In this embodiment, the learning companion system can be the backend system corresponding to the AI ​​learning assistant installed on the learning tablet. The learning companion system can store students' basic information, learning records, course materials, and other data. The basic information such as class, grade, name, age, and semester filled in when logging into the student's learning companion system can be used to generate a user ID, which can be associated with all of the student's learning data.

[0059] In this embodiment of the application, the knowledge point learning grid can be a two-dimensional grid formed by mapping the learning content of the student's current semester's courses according to logical relationships (such as chapter order, knowledge dependencies), such as... Figure 2 As shown, in Figure 2 Each grid cell represents a knowledge point. The proficiency level of a knowledge point can be marked by filling the cell with different circles, different symbols on different circles, or different shapes. The specific marking method for the proficiency level of a knowledge point is not limited in this embodiment.

[0060] As an optional method, when marking the proficiency of knowledge points by filling different circles, red can be used to indicate not mastered, yellow can be used to indicate mastered but not proficient, and green can be used to indicate proficient; when marking the proficiency of knowledge points by filling different shapes, 1 can be used to indicate not mastered, 2 can be used to indicate mastered but not proficient, and 3 can be used to indicate proficient; when marking the proficiency of knowledge points by filling different shapes, circles can be used to indicate not mastered, triangles can be used to indicate mastered but not proficient, squares can be used to indicate proficient, and so on, without further examples.

[0061] In this embodiment, learning behavior data can be various operational data generated by students when learning in a knowledge point learning grid. Learning behavior data can be used to reflect the student's learning process and learning status. For example, the learning behavior data in this embodiment may specifically include, but is not limited to, online course learning data (such as video completion rate, number of repeated views, dwell time, fast forward / rewind operation records), practice question data (such as answer accuracy rate, answer speed, number of incorrect questions, correct rate of redoing incorrect questions, number of questions completed, question difficulty level), and interaction data (such as question frequency, question content, number of notes, detail of notes, number of comments, and activity level in discussions).

[0062] In this embodiment of the application, the set of unmastered knowledge points can be a set of knowledge points in the knowledge point learning grid in which the student's mastery level has not reached the qualified standard (e.g., the mastery probability is less than 0.4).

[0063] In this embodiment of the application, the question information can be detailed information about questions on knowledge points in the set of knowledge points not yet mastered. Specifically, the question information may include the question ID, question stem text, answer explanation, system-pre-annotated knowledge points, and student's answer result. (1 indicates correct, 0 indicates incorrect), answer timestamp, and other information.

[0064] In this embodiment of the application, the note information can be the notes recorded by a student during the process of learning knowledge points from a set of knowledge points that have not yet been mastered. Specifically, in this embodiment of the application, the note information can be used as... This can be represented as the note information, which may include the note text (Text), note location (Loc), and the contextual knowledge points corresponding to the note (…). ).

[0065] Step 102: Map the learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph.

[0066] In this embodiment of the application, the knowledge graph can be a graph that displays knowledge points and the relationships between knowledge points in a graphical structure. The nodes of the knowledge graph can be knowledge points, the edges of the knowledge graph can be the relationships between knowledge points (including directed prior relationships and undirected correlation relationships), the weights of the edges of the knowledge graph can be the strength of the relationships between knowledge points, and the importance of knowledge points can be evaluated by indicators such as degree centrality, betweenness centrality, and proximity centrality.

[0067] In this embodiment of the application, the learning knowledge point data can be related information about the knowledge points involved by the student in the knowledge graph. The learning knowledge point data can include the attributes, relationships, and positions of the knowledge points in the graph. The learning knowledge point data can be used to reflect the correspondence of the student's learning trajectory in the overall knowledge system.

[0068] In this embodiment, learning behavior data is mapped onto the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph. First, relevant information about the knowledge points encountered by the student can be extracted from the learning behavior data, such as the course chapters studied, the knowledge points involved in answering questions, and the knowledge points recorded in notes, forming corresponding knowledge point information. This knowledge point information can then be matched with nodes in the knowledge graph. Matching methods can be semantic matching based on the knowledge point's name and description text, or contextual information such as the knowledge point's position in the textbook and its chapter can be used to assist in matching. Based on the matching results, the extracted knowledge point information can be linked with the corresponding graph nodes in the knowledge graph, establishing a connection between learning behavior and the knowledge graph. Based on the graph nodes linked with knowledge point information, the corresponding attributes (such as difficulty, importance, and learning time), associated edges (such as prerequisite relationships, relevance relationships, and corresponding weights), centrality indicators, and other graph knowledge point information can be extracted. Integrating this graph knowledge point information generates the student's learning knowledge point data in the knowledge graph.

[0069] Step 103: Generate student learning content data based on question information and note information, and perform multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information for the set of unmastered knowledge points.

[0070] In this embodiment of the application, multi-dimensional information matching can be a matching of learning content data and learning knowledge point data from multiple perspectives such as content, context, and location.

[0071] In this embodiment of the application, the knowledge point location information may be the specific location and relationship of the unmastered knowledge point in the knowledge graph corresponding to the knowledge point learning grid. The knowledge point location information may include the knowledge point's prerequisite knowledge points, subsequent knowledge points, related knowledge points, and centrality indicators in the knowledge network.

[0072] In this embodiment of the application, the learning content data can be the specific content that students encounter when learning knowledge points they have not yet mastered, such as the application scenarios of knowledge points involved in the questions, the key points of knowledge points recorded in notes, and points of doubt.

[0073] Step 104: Based on the student's learning objectives and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, update the set of unmastered knowledge points to obtain the target set of unmastered knowledge points, and recommend the target set of unmastered knowledge points to the student.

[0074] In this application embodiment, the set of knowledge points that the target has not mastered can be a set of knowledge points that is more in line with the student's cognitive goals and knowledge system logic, obtained by filtering, supplementing and sorting the initial set of knowledge points that have not been mastered based on the target's learning intention and knowledge point location information.

[0075] In this embodiment of the application, the target learning intention can be the learning intention of a student when learning knowledge points that they have not yet mastered. The target learning intention can include the intention of in-depth understanding, the intention of consolidating the basics, and the intention of questioning concepts. The intention of in-depth understanding can be the learning intention of a student who wants to deeply understand the core logic, internal connections, and application scenarios of knowledge points. The intention of consolidating the basics can be the learning intention of a student who wants to strengthen the basic concepts and basic usages of knowledge points, consolidate existing preliminary understanding, and improve mastery and proficiency. The intention of questioning concepts can be the learning intention of a student who is confused about the basic concepts, definitions, theorems, etc. of knowledge points and needs to resolve basic questions before further learning.

[0076] Compared with existing technologies, this embodiment achieves precise collection of core learning-related data by acquiring students' learning behavior data on unmastered knowledge points in the knowledge point learning grid from the learning companion system and determining question and note information, providing a reliable data foundation for subsequent knowledge point association matching. By mapping the learning behavior data into the knowledge graph corresponding to the knowledge point learning grid, a deep correspondence between the learning behavior data and the knowledge graph structure is achieved, providing graph-level support for knowledge point location. By generating learning content data based on question and note information and performing multi-dimensional information matching with learning knowledge point data, precise location of unmastered knowledge points is achieved, improving the accuracy of knowledge point location. By updating and recommending the set of unmastered knowledge points based on students' target learning intentions and knowledge point location information, precise matching between the target set of unmastered knowledge points and students' actual learning needs is achieved.

[0077] As an optional approach, when performing the task of "generating student learning content data based on question and note information, and performing multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information for the set of unmastered knowledge points," the following methods can be used, but are not limited to: Figure 3 As shown, the method includes:

[0078] Step 201: Generate student learning content data based on question information and note information.

[0079] In this embodiment of the application, generating student learning content data based on question information and note information can first extract key content from the question information. Key content may include the core questions in the question stem, the known conditions involved, the explanation of knowledge points in the answer analysis, and text information such as tips on common mistakes. Note text, question marks, key points, and supplementary explanations can be extracted from the note information. The extracted content is then deduplicated and integrated to remove redundant information and structure the scattered information to form learning content data that can centrally reflect the student's current learning content, key points of understanding, and existing questions.

[0080] Step 202: Perform similarity matching based on the first semantic embedding vector corresponding to the learning content data and the second semantic embedding vector corresponding to the learning knowledge point data to match the content similarity between the learning content data and the learning knowledge point data, and obtain the first similarity matching result.

[0081] In the embodiments of this application, the first semantic embedding vector can be a vector obtained by semantically encoding the learning content data, and the first semantic embedding vector can be used to quantify the semantic information of the learning content data.

[0082] In the embodiments of this application, the second semantic embedding vector can be a vector obtained by semantically encoding the learned knowledge point data, and the second semantic embedding vector can be used to quantify the semantic information of the learned knowledge point data.

[0083] In the embodiments of this application, semantic encoding can be implemented using a natural language processing model, which includes, but is not limited to, models such as Word2Vec, BERT, and GPT. The natural language processing model can convert textual learning content data and learning knowledge point data into vector representations, making the vector distance between semantically similar texts closer.

[0084] In this embodiment of the application, similarity matching based on the first semantic embedding vector corresponding to the learning content data and the second semantic embedding vector corresponding to the learning knowledge point data can calculate the cosine similarity between the first semantic embedding vector and the second semantic embedding vector. The value range of the cosine similarity can be [-1, 1]. The closer the value of the cosine similarity is to 1, the higher the semantic similarity between the first semantic embedding vector and the second semantic embedding vector, that is, the more matched the learning content data and the learning knowledge point data are in the core meaning.

[0085] In this embodiment of the application, the first similarity matching result can be the cosine similarity value between the first semantic embedding vector and the second semantic embedding vector. The first similarity matching result can be used to reflect the degree of matching between the learning content data and the learning knowledge point data at the content level.

[0086] In this embodiment of the application, the calculation formula for the first similarity matching result can be as shown in Formula 1, wherein It can represent the semantic embedding vector of the selected content. It can represent the semantic embedding vector of knowledge point K.

[0087] (Formula 1)

[0088] Step 203: Perform similarity matching based on the context data corresponding to the learning content data and the adjacent knowledge point data corresponding to the learning knowledge point data, so as to match the overall similarity between the learning content data and the learning knowledge point data in the knowledge graph and obtain the second similarity matching result.

[0089] In the embodiments of this application, the context data corresponding to the learning content data can be peripheral knowledge information related to the learning content, such as the preceding knowledge points, subsequent knowledge points, and application scenario-related knowledge points involved in the learning content.

[0090] In the embodiments of this application, the adjacent knowledge point data corresponding to the learning knowledge point data can be a set of knowledge points in the knowledge graph that are directly related to the learning knowledge point. The adjacent knowledge point data can include prerequisite knowledge points, subsequent knowledge points, related knowledge points, etc., that is, the set of neighboring knowledge points of the knowledge point.

[0091] In the embodiments of this application, the second similarity matching result can be calculated by analyzing the set of neighboring knowledge points in the knowledge graph to determine the matching result between the learning content data and the set of neighboring knowledge points. The second similarity matching result can be used to reflect the overall matching situation of the learning content in the knowledge network. The calculation formula for the second similarity matching result can be as shown in Formula 2, where N(K) can represent the set of neighboring knowledge points of knowledge point K. It can represent contextual similarity. It can be used to reflect the overall matching degree in a knowledge network.

[0092] (Formula 2)

[0093] Step 204: Perform similarity matching based on the first position data of learning content data in the textbook and the second position data of learning knowledge point data in the textbook to match the positional similarity of learning content data and learning knowledge point data, and obtain the third similarity matching result.

[0094] In the embodiments of this application, the first location data may be the specific location information of the knowledge point corresponding to the learning content data in the textbook. The first location data may include the chapter number, page number, paragraph position, etc. of the textbook.

[0095] In the embodiments of this application, the second location data may be the specific location information of the knowledge point corresponding to the learning knowledge point data in the textbook. The second location data may include chapter number, page number, paragraph position, etc.

[0096] In the embodiments of this application, position similarity matching can be calculated based on the distance between the first position data and the second position data. The closer the distance, the higher the position similarity between the two.

[0097] For the embodiments of this application, the calculation formula for the third similarity matching result can be as shown in Formula 3, where It can represent the distance between locations. It can represent the position of the knowledge point corresponding to the learning content data in the textbook (i.e., the first position data in the embodiment of this application). It can represent the position of the knowledge point corresponding to the learning knowledge point data in the textbook (i.e., the second position data in the embodiments of this application).

[0098] (Formula 3)

[0099] Step 205: Based on the first similarity matching result, the second similarity matching result, and the third similarity matching result, generate knowledge point location information for the set of unmastered knowledge points.

[0100] In this embodiment of the application, the system can perform a weighted summation of the first similarity matching result, the second similarity matching result, and the third similarity matching result to obtain a comprehensive matching degree. If the comprehensive matching degree value exceeds the matching threshold, it can be determined that the knowledge point corresponding to the learning knowledge point data is the target knowledge point focused on by the learning content data. The system can combine the association information of the knowledge points in the knowledge graph to generate knowledge point location information of the set of unmastered knowledge points.

[0101] As an optional approach, when performing the step of "generating knowledge point location information for the set of unmastered knowledge points based on the first, second, and third similarity matching results," the following methods can be used, but are not limited to: performing a fusion analysis based on the first, second, and third similarity matching results to evaluate the accuracy of the location of knowledge points in the set of unmastered knowledge points, and obtaining location reliability data for learning content data and learning knowledge point data; selecting unmastered knowledge points that meet the confidence criteria from the set of unmastered knowledge points based on the location reliability data to form a location knowledge point set; and generating knowledge point location information for the set of unmastered knowledge points based on the prerequisite and relevance relationships of knowledge points in the location knowledge point set in the knowledge graph.

[0102] In the embodiments of this application, fusion analysis can be a comprehensive process of three similarity matching results to fully evaluate the accuracy of knowledge point positioning.

[0103] In the embodiments of this application, the location reliability data can be numerical data that quantifies the accuracy of location. The value range of the location reliability data can be [0,1]. The closer the value of the location reliability data is to 1, the more reliable the location result is. The calculation formula for the location reliability data can be as shown in Formula 4, where... Content similarity weights can be represented. Weights can represent contextual similarity. The position matching rate weight can be represented.

[0104] (Formula 4)

[0105] In the embodiments of this application, the fusion analysis can be performed using a weighted summation method, assigning weights (the sum of the weights is 1) to the first similarity matching result, the second similarity matching result, and the third similarity matching result respectively. The weights can be determined based on experimental data or empirical values.

[0106] In the embodiments of this application, the confidence condition can be a location confidence threshold. Unmastered knowledge points whose location confidence data is greater than the location confidence threshold can be selected to form a location knowledge point set. The location knowledge point set is the unmastered knowledge point that is accurately located and highly relevant to the student's current learning content.

[0107] In the embodiments of this application, the prerequisite relationship can be the dependency relationship between other knowledge points that need to be mastered in advance before learning a knowledge point and the knowledge point itself. The prerequisite relationship can correspond to the directed edge in the knowledge graph, and the dependency weight of the prerequisite relationship can be set to a specific range.

[0108] In the embodiments of this application, the relevance relationship can be the association or complementarity between knowledge points and other knowledge points in terms of content. The relevance relationship can correspond to the undirected edge in the knowledge graph, and the dependency weight of the relevance relationship can also be set to another specific range.

[0109] As an optional approach, when performing the task of "generating knowledge point location information for a set of unmastered knowledge points based on the prerequisite and relevance relationships of knowledge points in a knowledge point set located in a knowledge graph," the following methods may be used, but are not limited to: determining a first set of knowledge points in the knowledge graph consisting of prerequisite knowledge points corresponding to the location knowledge point set, and a second set of knowledge points using the knowledge points in the location knowledge point set as prerequisite knowledge points, based on the prerequisite relationships of knowledge points in the location knowledge point set; extracting the knowledge point dependency relationship chain corresponding to the set of unmastered knowledge points from the knowledge graph based on the location knowledge point set, the first knowledge point set, and the second knowledge point set; determining a third set of knowledge points in the knowledge graph related to the location knowledge point set, based on the relevance relationships of knowledge points in the location knowledge point set, and extracting the knowledge point related relationship chain corresponding to the set of unmastered knowledge points based on the location knowledge point set and the third knowledge point set; and generating knowledge point location information for the set of unmastered knowledge points based on the knowledge point dependency relationship chain and the knowledge point related relationship chain.

[0110] In the embodiments of this application, the first knowledge point set may be a set composed of the prerequisite knowledge points of each knowledge point in the location knowledge point set.

[0111] In the embodiments of this application, the second knowledge point set can be a set of subsequent knowledge points composed of the knowledge points in the location knowledge point set as the prerequisite knowledge points, and the learning of subsequent knowledge points can depend on the mastery of the location knowledge points.

[0112] In the embodiments of this application, the first set of knowledge points, which is composed of the prerequisite knowledge points corresponding to the set of knowledge points in the knowledge graph, can be formed by traversing each knowledge point in the set of knowledge points, searching for all the prerequisite knowledge points of the knowledge point in the knowledge graph (i.e., knowledge points that point to the knowledge point through directed edges), and deduplicating the prerequisite knowledge points to form the first set of knowledge points.

[0113] In the embodiments of this application, the second set of knowledge points, which uses the knowledge points in the set of location knowledge points as prerequisite knowledge points, can be used to search for all subsequent knowledge points in the knowledge graph that have the location knowledge points as prerequisite knowledge points (i.e., knowledge points pointed to by the location knowledge points through directed edges). After deduplication of the subsequent knowledge points, the second set of knowledge points can be formed.

[0114] In the embodiments of this application, the knowledge point dependency chain can be a chain structure that reflects the sequential learning dependency order between knowledge points. The knowledge point dependency chain can be used to show the dependency path from the prior knowledge point to the location knowledge point and then to the subsequent knowledge point.

[0115] In this embodiment, extracting the knowledge point dependency chain can be centered on locating knowledge points. Prerequisite knowledge points in the first knowledge point set can be arranged in dependency order at the front, and subsequent knowledge points in the second knowledge point set can be arranged in dependency order at the back, forming a complete knowledge point dependency chain. The extraction of the knowledge point dependency chain can be as shown in Formula 5, where... It can represent the m-th prerequisite knowledge point of knowledge point K. It can represent the nth subsequent knowledge point of knowledge point K.

[0116] (Formula 5)

[0117] In this embodiment of the application, the third set of knowledge points may be a set of knowledge points that are related to the knowledge points in the location knowledge point set.

[0118] In this embodiment of the application, based on the correlation relationship of knowledge points in the knowledge point set in the knowledge graph, the third knowledge point set related to the knowledge point set in the knowledge graph can be determined by traversing each knowledge point in the knowledge point set, searching for all related knowledge points of the knowledge point in the knowledge graph (i.e. knowledge points connected by undirected edges), and after deduplicating the related knowledge points, the third knowledge point set can be formed.

[0119] In this embodiment of the application, the knowledge point related relationship chain can be a chain structure that reflects the relationship between the positioning knowledge point and related knowledge points. The knowledge point related relationship chain can be used to display the surrounding related knowledge of the positioning knowledge point.

[0120] In this embodiment, the extraction of knowledge point-related relationship chains corresponding to the set of unmastered knowledge points based on the set of located knowledge points and the set of third knowledge points can be achieved by taking the located knowledge point as the center and sequentially connecting the relevant knowledge points in the set of third knowledge points around the located knowledge point in descending order of association strength. This forms a knowledge point-related relationship chain. The knowledge point-related relationship chain can be used to mine the complementary knowledge points associated with the unmastered knowledge points. The extraction of the relevant relationship chain can be as shown in Formula 6, where... It can represent knowledge points related to knowledge point K. It can represent the similarity between knowledge points.

[0121] (Formula 6)

[0122] As an optional approach, when performing the task of "mapping learning behavior data in the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph", the following methods can be used, but are not limited to: determining the knowledge point information corresponding to the learning behavior data, matching the knowledge point information in the knowledge graph, and linking the knowledge point information to the graph nodes in the knowledge graph according to the matching results; generating the student's learning knowledge point data in the knowledge graph based on the graph knowledge point information corresponding to the graph nodes linked with knowledge point information.

[0123] In this embodiment of the application, the system can map students' learning behavior data into the knowledge graph corresponding to the knowledge point learning grid. The system can determine the students' learning knowledge point data in the knowledge graph based on the knowledge points, learning order, and interactive content involved in the learning behavior data.

[0124] In the embodiments of this application, matching knowledge point information in a knowledge graph can be based on information such as the name, keywords, and description text of the knowledge point, and semantic matching can be performed with nodes in the knowledge graph. Semantic matching can be implemented using algorithms such as TF-IDF and cosine similarity, or it can be combined with the attributes of the knowledge point (such as difficulty, subject, and learning time) to assist in matching and improve matching accuracy.

[0125] In this embodiment of the application, knowledge point information is linked to graph nodes in the knowledge graph based on the matching results. If the knowledge point information is successfully matched with a node in the knowledge graph (the similarity exceeds the matching threshold), the knowledge point information can be associated with the graph node, and the graph node can be marked as the knowledge point node involved in the student's learning process.

[0126] In the embodiments of this application, the graph knowledge point information can be all the relevant information corresponding to the nodes in the knowledge graph that are linked with knowledge point information. The graph knowledge point information can include the node's attributes (difficulty, importance, learning time, prerequisite knowledge, etc.), the associated edges (prerequisite relation edges, relevance relation edges and their corresponding weights), and the centrality indicators (degree centrality, betweenness centrality, proximity centrality), etc.

[0127] In this embodiment, the graph knowledge point information corresponding to the graph nodes linked with knowledge point information is used to generate student learning knowledge point data in the knowledge graph. This can integrate the graph knowledge point information of each linked node and remove duplicate information to form structured learning knowledge point data, which can comprehensively reflect the knowledge nodes and associations corresponding to student learning behavior in the knowledge graph.

[0128] As an optional approach, when executing the process of "updating the set of unmastered knowledge points based on the student's target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid to obtain a target set of unmastered knowledge points, and recommending the target set of unmastered knowledge points to the student," the following methods can be used, but are not limited to: evaluating the student's learning needs for the knowledge points in the set of unmastered knowledge points based on question information and note information to obtain the learning intention intensity data corresponding to the knowledge points in the knowledge point learning grid; identifying the student's target learning intention for the knowledge points in the set of unmastered knowledge points based on the learning intention intensity data, question information, and note information; updating the set of unmastered knowledge points based on the target learning intention and knowledge point location information to obtain a target set of unmastered knowledge points, generating the target set of unmastered knowledge points and the target learning path corresponding to the target set of unmastered knowledge points; and generating recommendation information for the target set of unmastered knowledge points and the target learning path so that students can master the knowledge points in the target set of unmastered knowledge points based on the target set of unmastered knowledge points and the target learning path.

[0129] In this embodiment of the application, the learning intention intensity data can be numerical data that quantifies the student's need to learn the knowledge points that they have not mastered. The value range of the learning intention intensity data can be [0,1]. The larger the value of the learning intention intensity data, the stronger and more urgent the student's need to learn the knowledge points. The learning intention intensity data can be used to provide a quantitative basis for subsequent learning intention recognition and knowledge point recommendation.

[0130] In this embodiment of the application, the target learning intention can be the learning intention of a student when learning knowledge points that they have not yet mastered. The target learning intention can include the intention of in-depth understanding, the intention of consolidating the basics, and the intention of questioning concepts. The intention of in-depth understanding can be the learning intention of a student who wants to deeply understand the core logic, internal connections, and application scenarios of knowledge points. The intention of consolidating the basics can be the learning intention of a student who wants to strengthen the basic concepts and basic usages of knowledge points, consolidate existing preliminary understanding, and improve mastery and proficiency. The intention of questioning concepts can be the learning intention of a student who is confused about the basic concepts, definitions, theorems, etc. of knowledge points and needs to resolve basic questions before further learning.

[0131] In this embodiment of the application, the target learning path can be an ordered learning path planned for students based on the set of unmastered knowledge points and the relationships in the knowledge graph. The target learning path can be used to guide students to master the unmastered knowledge points logically and step by step.

[0132] In this embodiment of the application, the system can update the initial set of unmastered knowledge points based on the target learning intention and knowledge point location information. If the target learning intention is to deepen understanding, it can supplement the unmastered knowledge points with related extended knowledge points and associated application knowledge points, and filter out the unmastered knowledge points that are crucial to the deep understanding of the knowledge points. If the target learning intention is to consolidate the basic knowledge points, it can focus on the basic concept-related knowledge points of the unmastered knowledge points and the knowledge points corresponding to similar basic exercises, and supplement the unmastered basic related knowledge points. If the target learning intention is to ask questions about concepts, it can filter out the core concept knowledge points and prerequisite concept knowledge points of the unmastered knowledge points to ensure that students can solve basic questions first. After the initial set of unmastered knowledge points is updated, the target set of unmastered knowledge points is obtained. It can combine the prerequisite relationships and relevance relationships in the knowledge graph and use graph traversal algorithms (such as breadth-first search BFS and depth-first search DFS) to generate the target learning path.

[0133] In this embodiment of the application, the recommendation information may be a comprehensive set of information including the target set of unmastered knowledge points, the target learning path, corresponding learning resources (such as online course videos, practice question sets, knowledge point explanation documents), learning time suggestions, and learning method tips. The recommendation information can be used to guide students in their learning.

[0134] As an optional approach, when performing the task of "obtaining learning behavior data of students learning knowledge points in the set of unmastered knowledge points within the knowledge point learning grid from the learning companion system, and determining the question information and note information of students learning knowledge points in the set of unmastered knowledge points based on the learning behavior data," the following methods can be used, but are not limited to: obtaining learning behavior data of students learning knowledge points in the set of unmastered knowledge points within the knowledge point learning grid from the learning companion system; dividing the students' learning behavior data in the knowledge point learning grid into at least one learning behavior data set, and generating a behavioral feature set corresponding to at least one learning behavior data set; determining the time information corresponding to each behavioral feature in the behavioral feature set. The system collects information and evaluates the effectiveness of each behavioral feature in the behavioral feature set based on time information, obtaining effective value data for each behavioral feature in the behavioral feature set. Based on the effective value data, the behavioral features in the behavioral feature set are filtered to obtain target behavioral features that meet the effective conditions, and these target behavioral features are combined into a target behavioral feature set. Based on the target behavioral feature set, the system analyzes the students' mastery of the knowledge points in the knowledge point learning grid, determining the set of knowledge points that students have not mastered in the knowledge point learning grid. The system identifies boxed behaviors from the target behavioral feature set and classifies the learning content selected by the boxed behaviors to obtain the question information and note information of students learning the knowledge points in the set of knowledge points that they have not mastered.

[0135] In the embodiments of this application, the process of obtaining learning behavior data from the learning companion system can be achieved by real-time monitoring of the student's operations on the learning tablet. The learning behavior data can include data generated by various operations such as online learning, answering questions, taking notes, and asking questions.

[0136] In the embodiments of this application, learning behavior data can be divided into learning behavior data sets according to behavior type. For example, learning behavior data can be divided into online course learning data sets, question-solving data sets, note data sets, question-asking data sets, etc., and each set can contain all learning behavior data of the corresponding type.

[0137] In this embodiment, the generated behavioral feature set can extract key behavioral features for each learning behavior data set. For example, the online course learning data set can extract features such as video completion rate, number of repeated viewings, dwell time, and the proportion of viewing time for key chapters; the question-solving data set can extract features such as answer accuracy, answering speed, number of wrong questions, correct answer rate for redoing wrong questions, and answering performance for questions of different difficulty; the note data set can extract features such as note update frequency, note detail, and number of question marks; and the question data set can extract features such as question frequency, question type, and timeliness of question response.

[0138] In this embodiment, evaluating the effectiveness of each behavioral feature in the behavioral feature set based on time information to obtain the effective value data of each behavioral feature in the behavioral feature set can be based on evaluating the effectiveness of the behavioral features using a time decay model to obtain the effective value data; the time decay model can be calculated using an exponential decay formula, as shown in Formula 7, where... It can represent whether the i-th answer is correct or incorrect (1 or 0). It can represent the time for the i-th answer. It can indicate the current time for answering the question. It can represent the attenuation coefficient.

[0139] (Formula 7)

[0140] In this embodiment of the application, the behavioral features in the behavioral feature set are filtered based on the effective value data to obtain the target behavioral features that meet the effective conditions in the behavioral feature set. The target behavioral features are then combined into a target behavioral feature set. This can be done by first setting the effective condition to be that the effective value data is greater than a threshold, filtering out the behavioral features that meet the condition to form the target behavioral feature set, and removing features with too low effective values ​​(such as features that are too outdated or have no reference value for assessing the current level of mastery).

[0141] In this embodiment, the analysis of students' mastery of knowledge points in the knowledge point learning grid based on the target behavioral feature set determines the set of unmastered knowledge points in the knowledge point learning grid. This can be achieved by inputting the target behavioral feature set into a mastery assessment model (such as logistic regression model, softmax regression model, etc., including but not limited to the above models). The mastery assessment model can be trained based on historical student behavioral feature data and corresponding knowledge point mastery labels (such as exam scores, teacher evaluations). The mastery assessment model can be used to output the probability of students mastering each knowledge point. Knowledge points with a mastery probability lower than a threshold can be identified as unmastered knowledge points, forming a set of unmastered knowledge points.

[0142] In this embodiment of the application, the box selection behavior is identified from the target behavior feature set, and the learning content selected by the box selection behavior is classified to obtain the question information and note information of the student learning the knowledge points in the set of knowledge points that have not been mastered. The student's box selection operation can be identified through the operation record of the learning tablet, and the text of the boxed learning content can be extracted. The boxed content can be classified by a text classification model (such as a binary classification model based on BERT) to distinguish between question-related content (such as question stem, options, and answer analysis) and note-related content (such as key points and questions marked by the student). Question-related content can form question information, and note-related content can form note information.

[0143] Compared with existing technologies, this embodiment achieves multi-dimensional and accurate matching of learning content data and learning knowledge point data by performing similarity matching based on the first and second semantic embedding vectors, context data and adjacent knowledge point data, and first and second position data, providing a comprehensive matching basis for generating knowledge point positioning information. By fusing and analyzing the first, second, and third similarity matching results to obtain positioning confidence data, knowledge points meeting the confidence criteria are selected to form a positioning knowledge point set, and positioning information is generated based on prior and relevance relationships, thus achieving reliable generation of knowledge point positioning information and improving the credibility of the positioning information. By determining the first knowledge... The system extracts dependency and correlation chains for knowledge points from three sets: a first set, a second set, and a third set. This enables the structured generation of location information for sets of unmastered knowledge points. By identifying the knowledge point information corresponding to learning behavior data and matching links in the knowledge graph, learning knowledge point data is generated based on the linked graph knowledge point information. This achieves a reliable mapping between learning behavior data and knowledge graph nodes, improving the accuracy of learning knowledge point data. Furthermore, by obtaining learning intent intensity data based on question and note information and identifying the target learning intent, the system updates the target set of unmastered knowledge points and generates the target learning path and recommendation information. This achieves precise matching of knowledge point recommendations with students' learning intent, improving the targeting and effectiveness of recommendations.

[0144] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0145] Example 1: Based on the knowledge point set corresponding to the course material information, determine the basic learning information of the knowledge points in the knowledge point set, as well as the prerequisite knowledge information and correlation information between the knowledge points; generate attribute information of the knowledge points based on the basic learning information, the prerequisite knowledge information, and the correlation information, and construct a knowledge graph corresponding to the knowledge point set based on the attribute information; map the knowledge graph into the knowledge point learning grid corresponding to the course material information to obtain the knowledge point learning grid; generate the student's learning plan for the target time period based on the knowledge point learning grid in the knowledge point learning grid module, and generate the student's learning path based on the learning plan; the knowledge point learning grid module is used to display the learning path to the student through the knowledge point learning grid; wherein, the knowledge point learning grid is a learning grid that includes the attribute information of the knowledge points and the correlation information between the knowledge points.

[0146] Example 11: Based on attribute information, determine the frequency data of knowledge points appearing in the same historical learning sessions, and generate a first association strength corresponding to the knowledge points in the knowledge point set based on the frequency data; based on attribute information, determine the mastery level data of knowledge points, and generate a second association strength corresponding to the knowledge points in the knowledge point set based on the mastery level data; based on attribute information, determine the proximity of the learning order of knowledge points, and generate a third association strength corresponding to the knowledge points in the knowledge point set based on the proximity of the learning order; based on attribute information, determine the probability data of incorrect answers to knowledge points, and generate a fourth association strength corresponding to the knowledge points in the knowledge point set based on the probability data of incorrect answers; generate a target association strength corresponding to the knowledge points in the knowledge point set based on the first association strength, second association strength, third association strength, and fourth association strength.

[0147] Example 12: Determine the first association type between knowledge points based on basic learning information, the second association type between knowledge points based on prerequisite knowledge information, and the third association type between knowledge points based on relevance information; generate directed edges corresponding to the knowledge point set based on the first association type between knowledge points corresponding to basic learning information and the second association type between knowledge points corresponding to prerequisite knowledge information, and generate undirected edges corresponding to the knowledge point set based on the first association type between knowledge points corresponding to the first association type and the third association type between knowledge points corresponding to relevance information; determine the target association strength corresponding to the knowledge points in the knowledge point set based on attribute information, and generate an association matrix based on the knowledge point set, directed edges, undirected edges, and association strength; construct graph edges based on the association matrix, and construct graph nodes based on the knowledge point set and attribute information, and combine graph nodes and graph edges to generate a knowledge graph.

[0148] Example 13: Quality assessment of the knowledge graph. In the case of isolated nodes in the knowledge graph, the knowledge point set is refined, and the knowledge graph is adjusted based on the refined knowledge point set. In the case of node density in the knowledge graph that is greater than the density threshold, the knowledge point set is merged, and the knowledge graph is adjusted based on the merged knowledge point set.

[0149] Example 14: In response to acquiring learning behavior data of students learning based on the learning plan, the system determines the students' question information and note information during the learning process based on the learning behavior data; identifies implicit knowledge points in the question information and note information, and determines the implicit attribute information of the implicit knowledge points, including implicit prerequisite knowledge information and implicit relevance information; when the implicit attribute information meets the knowledge graph update conditions, the system updates the knowledge graph based on the implicit knowledge points and implicit attribute information to obtain the target knowledge graph, which is used to generate a learning grid that includes implicit knowledge points and their attribute information.

[0150] Example 15: Determine the prerequisite knowledge points corresponding to the implicit knowledge points based on implicit prerequisite knowledge information; determine the students' mastery of the implicit knowledge points and prerequisite knowledge points based on the question information, as well as the answer results data of the questions containing the implicit knowledge points and prerequisite knowledge points; determine the confidence level of the implicit prerequisite knowledge information based on the mastery level and answer results data; in response to the confidence level of the implicit prerequisite knowledge information being greater than the confidence level threshold and the number of times the implicit knowledge points are identified being greater than the number of times threshold, update the graph nodes in the knowledge graph based on the implicit knowledge points, and update the directed edges in the knowledge graph based on the implicit prerequisite knowledge information.

[0151] Example 16: Determine the relevant knowledge points corresponding to the implicit knowledge points based on implicit correlation information; determine the student's mastery of the implicit knowledge points and relevant knowledge points based on note information, as well as the information contribution data of note information to implicit correlation information; determine the confidence level of implicit correlation information based on the mastery level and information contribution data; in response to the confidence level of implicit correlation information being greater than the confidence level threshold and the number of times implicit knowledge points are identified being greater than the number of times threshold, update the graph nodes in the knowledge graph based on the implicit knowledge points, and update the undirected edges in the knowledge graph based on implicit prerequisite knowledge information.

[0152] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0153] Example 2: In response to obtaining first learning behavior data of a student learning questions based on the learning plan, the system determines first question information and first note information of the student's learning target questions based on the first learning behavior data, and sends the first question information and first note information to the knowledge point learning grid module; based on the implicit knowledge point set in the knowledge point set corresponding to the first question information and first note information; according to the prerequisite relationship and relevance information between the implicit knowledge point set and the first knowledge point set, the system determines the target implicit knowledge point set corresponding to the learning plan from the implicit knowledge point set; the system updates the target implicit knowledge point set in the knowledge point learning grid, and sends the updated knowledge point learning grid to the learning path generation module; the system updates the learning plan to include the target implicit knowledge point set.

[0154] Example 21: Extract knowledge points from the first question information and the first note information respectively to obtain the second knowledge point set corresponding to the first question information and the third knowledge point set corresponding to the note information; determine the knowledge points in the second knowledge point set that are not included in the first knowledge point set as the first implicit knowledge point subset corresponding to the target question; determine the knowledge points in the third knowledge point set that are not included in the first knowledge point set as the second implicit knowledge point subset corresponding to the target question; determine the implicit knowledge point set based on the first and second implicit knowledge point subsets.

[0155] Example 22: Establish multiple prerequisite relationships for knowledge points based on a first subset of implicit knowledge points and a first set of knowledge points, so as to determine the knowledge points in the first subset of implicit knowledge points as prerequisite knowledge points for the knowledge points in the first set of knowledge points; establish multiple correlation relationships for knowledge points based on a second subset of implicit knowledge points and a first set of knowledge points, so as to associate the knowledge points in the second subset of implicit knowledge points with the knowledge points in the first set of knowledge points; determine the first confidence level of using the multiple prerequisite relationships for knowledge points as prerequisite relationships for target knowledge points corresponding to the learning plan and the second confidence level of using the multiple correlation relationships for knowledge points as correlation relationships for target knowledge points corresponding to the learning plan; determine the target implicit knowledge point set corresponding to the learning plan from the implicit knowledge point set based on the first confidence level and the second confidence level.

[0156] Example 23: Determine the student's first mastery data on the first subset of implicit knowledge points, and determine the student's answer to the questions based on the student's answer data in the question information; determine the first support data for each knowledge point prerequisite relationship in multiple knowledge point prerequisite relationships based on the first mastery data and the answer results; update the first confidence of each knowledge point prerequisite relationship based on the historical confidence of the first support data to obtain the first confidence of using multiple knowledge point prerequisite relationships as the target knowledge point prerequisite relationship.

[0157] Example 24: Determine the second mastery data of students on the second subset of implicit knowledge points, and the contribution data of note information to the correlation relationship of multiple knowledge points; determine the second support data of each knowledge point correlation relationship in the multiple knowledge point correlation relationships based on the mastery data and contribution data; update the data according to the historical confidence of each knowledge point correlation relationship based on the second support data, and obtain the second confidence of using the current correlation relationship of multiple knowledge points as the correlation relationship of the target knowledge point.

[0158] Example 25: Multiple prerequisite relationships and multiple correlation relationships of knowledge points are stored in a candidate relation library corresponding to the learning plan, so as to monitor the first confidence level and the second confidence level through the candidate relation library; in response to the first confidence level of the prerequisite relationship of the first knowledge point being greater than the prerequisite confidence threshold and the number of times the first implicit knowledge point corresponding to the prerequisite relationship of the first knowledge point being identified being greater than the number of times threshold, the first implicit knowledge point is determined as the first target implicit knowledge point corresponding to the learning plan; in response to the first confidence level of the correlation relationship of the first knowledge point being greater than the correlation confidence threshold and the number of times the first implicit knowledge point corresponding to the correlation relationship of the first knowledge point being identified being greater than the number of times threshold, the first implicit knowledge point is determined as the first target implicit knowledge point corresponding to the learning plan; the target implicit knowledge point set corresponding to the learning plan is determined based on the first target implicit knowledge point and the second target implicit knowledge point.

[0159] Example 26: Determine the monitoring period for the first confidence level and the second confidence level of the candidate relation library; within the monitoring period, in response to the first confidence level of the second knowledge point prerequisite relation among multiple knowledge point prerequisite relations and / or the second confidence level of the second knowledge point prerequisite relation among multiple knowledge point correlation relations being lower than the monitoring threshold, remove the second knowledge point prerequisite relation and / or the second knowledge point prerequisite relation from the candidate relation library; in response to the end of the monitoring period, remove multiple knowledge point prerequisite relations and multiple knowledge point correlation relations from the candidate relation library.

[0160] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0161] Example 3: Based on the student's learning location information in the knowledge point learning grid, determine the target learning course corresponding to the learning location information; divide the student's second learning behavior data in the target learning course into at least one learning behavior data set, and generate at least one behavioral feature set corresponding to the at least one learning behavior data set; analyze the student's mastery of knowledge points in the target learning course based on the at least one behavioral feature set, and determine the student's unmastered knowledge point set in the target learning course; match the unmastered knowledge point set with the target knowledge graph corresponding to the knowledge point learning grid to obtain the target knowledge point network corresponding to the unmastered knowledge point set in the target knowledge graph; generate the student's target learning path in the knowledge point learning grid based on the target knowledge point network, and the target learning path is used to assist the student in mastering the unmastered knowledge point set.

[0162] Example 31: Determine the time information corresponding to each behavioral feature in at least one set of behavioral features, and evaluate the effectiveness of each behavioral feature in at least one set of behavioral features based on the time information to obtain effective value data for each behavioral feature in at least one set of behavioral features; filter the behavioral features in at least one set of behavioral features based on the effective value data to obtain target behavioral features that meet the effective conditions in at least one set of behavioral features, and form at least one set of target behavioral features; analyze the students' mastery of knowledge points in the target learning course based on at least one set of target behavioral features to determine the set of knowledge points that students have not mastered in the target learning course.

[0163] Example 32: Match at least one set of target behavioral features with each knowledge point in the target learning course to determine at least one target behavioral feature corresponding to each knowledge point in the target learning course; identify the importance data of at least one target behavioral feature corresponding to each knowledge point in the target learning course to each knowledge point in the target learning course through a target model, which is trained based on students' historical behavioral features and historical knowledge point mastery levels; determine students' mastery data of each knowledge point in the target learning course based on at least one target behavioral feature and importance data corresponding to each knowledge point; determine the set of unmastered knowledge points in the target learning course based on the mastery data.

[0164] Example 33: Based on importance data, determine the influence coefficient of at least one behavioral feature corresponding to each knowledge point on the degree of mastery of each knowledge point; analyze at least one behavioral feature based on the influence coefficient to generate data on the student's mastery of each knowledge point in the target learning course.

[0165] Example 34: Map the mastery data of each knowledge point to the objective function to obtain the mastery probability data of each knowledge point; select knowledge points that meet the unmastered conditions from the knowledge corresponding to the target learning course based on the mastery probability data, and form a set of unmastered knowledge points from the knowledge points selected from the knowledge corresponding to the target learning course.

[0166] Example 35: Generate a sequence of unmastered knowledge points based on the set of unmastered knowledge points; mark the sequence of unmastered knowledge points with unmastered identifiers in the target learning grid, and extract the paths of unmastered knowledge points corresponding to the sequence of unmastered knowledge points from the target learning grid; match the paths of unmastered knowledge points with the target knowledge graph according to the unmastered identifiers to obtain the target knowledge point network corresponding to the set of unmastered knowledge points in the target knowledge graph.

[0167] Example 36: This method is used to match the paths of unmastered knowledge points with the target knowledge graph based on the unmastered identifier, thereby obtaining the network of knowledge points to be screened corresponding to the set of unmastered knowledge points in the target knowledge graph; and to determine the target knowledge point network from the network of knowledge points to be screened based on the prerequisite relationships and relevance information of the paths of unmastered knowledge points in the network of knowledge points to be screened.

[0168] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0169] Example 4: Obtain third learning behavior data of the student learning knowledge points in the set of unmastered knowledge points within the knowledge point learning grid; determine second question information and second note information based on the third learning behavior data; evaluate the student's learning needs for knowledge points in the set of unmastered knowledge points based on the second question information and the second note information, and obtain learning intention intensity data corresponding to the knowledge points in the knowledge point learning grid; identify the student's target learning intention for knowledge points in the set of unmastered knowledge points based on the learning intention intensity data, the second question information, and the second note information; update the set of unmastered knowledge points based on the target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid to obtain a target set of unmastered knowledge points, and recommend the target set of unmastered knowledge points to the student.

[0170] Example 41: Based on note information, determine the update frequency of students' notes within the target time range, and evaluate students' learning activity data within the target time range based on the update frequency; based on note information and question information, determine the question frequency of students' doubts about knowledge points in the set of unmastered knowledge points, and evaluate students' difficulty in understanding knowledge points in the set of unmastered knowledge points based on the question frequency; evaluate students' learning needs for knowledge points in the set of unmastered knowledge points based on learning activity data and difficulty in understanding data, and obtain the learning intention intensity data corresponding to knowledge points in the knowledge point learning grid.

[0171] Example 42: Based on the third learning behavior data, determine the learning end time for students to learn the knowledge points in the set of unmastered knowledge points; determine the decay factor of learning intention intensity over time based on the learning end time and time decay coefficient; evaluate the urgency data of students learning the knowledge points in the set of unmastered knowledge points based on the decay factor; perform weighted analysis on learning activity data, comprehension difficulty data and urgency data to evaluate students' learning needs for the knowledge points in the set of unmastered knowledge points, and obtain the learning intention intensity data corresponding to the knowledge points in the knowledge point learning grid.

[0172] Example 43: Based on the second question information and the second note information, generate student learning content data and corresponding behavior sequence data for the third learning behavior data; evaluate the student's learning intention for the knowledge points in the set of unmastered knowledge points as a first probability data of deep understanding intention, a second probability data of basic consolidation intention, and a third probability data of conceptual questioning intention based on the learning intention intensity data, learning content data, and behavior sequence data; determine the target learning intention from deep understanding intention, basic consolidation intention, and conceptual questioning intention based on the first probability data, the second probability data, and the third probability data.

[0173] Example 44: Evaluate the student's required level of understanding of the knowledge points in the set of unmastered knowledge points based on the first probability data, the second probability data, and the third probability data; if the required level of understanding data is greater than the first required level of understanding threshold, determine the student's intention to deepen understanding as the target learning intention for the knowledge points in the set of unmastered knowledge points; if the required level of understanding data is less than or equal to the first required level of understanding threshold and greater than the second required level of understanding threshold, determine the student's intention to consolidate basic knowledge as the target learning intention for the knowledge points in the set of unmastered knowledge points, wherein the second required level of understanding threshold is less than the first required level of understanding threshold; if the required level of understanding data is less than the second required level of understanding threshold, determine the student's intention to raise conceptual questions as the target learning intention for the knowledge points in the set of unmastered knowledge points.

[0174] Example 45: Generate student learning content data based on the second question information and the second note information; map the third learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph; perform multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information for the set of unmastered knowledge points; update the set of unmastered knowledge points according to the target learning intention and the knowledge point location information to obtain the target set of unmastered knowledge points, generate the target set of unmastered knowledge points and the target learning path corresponding to the target set of unmastered knowledge points; generate recommendation information for the target set of unmastered knowledge points and the target learning path so that students can master the knowledge points in the target set of unmastered knowledge points based on the target set of unmastered knowledge points and the target learning path.

[0175] Example 46: Obtain third learning behavior data from the learning support system, showing students learning knowledge points in the set of unmastered knowledge points within the knowledge point learning grid; divide the third learning behavior data of students in the knowledge point learning grid into at least one learning behavior data set, and generate a behavioral feature set corresponding to at least one learning behavior data set; determine the time information corresponding to each behavioral feature in the behavioral feature set, and evaluate the effectiveness of each behavioral feature in the behavioral feature set based on the time information, obtaining the effective value data of each behavioral feature in the behavioral feature set; filter the behavioral features in the behavioral feature set based on the effective value data, obtain the target behavioral features that meet the effective conditions in the behavioral feature set, and form a target behavioral feature set; analyze the students' mastery of knowledge points in the knowledge point learning grid based on the target behavioral feature set, and determine the set of unmastered knowledge points in the knowledge point learning grid; identify the box-selection behavior from the target behavioral feature set, and classify the learning content selected by the box-selection behavior to obtain the second question information and second note information of students learning knowledge points in the set of unmastered knowledge points.

[0176] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0177] Example 5: Based on the knowledge point review path where the student reviews learned knowledge points in the knowledge point learning grid, the knowledge points to be reviewed indicated by the knowledge point review path are determined; the knowledge point network corresponding to the knowledge point to be reviewed is extracted from the knowledge graph corresponding to the knowledge point learning grid, the knowledge point network to be reviewed includes at least one prerequisite knowledge point and at least one related knowledge point corresponding to the knowledge point to be reviewed; based on the student's mastery of the knowledge point to be reviewed, the at least one prerequisite knowledge point, and the at least one related knowledge point, the knowledge point review path is updated to obtain the target knowledge point review path corresponding to the knowledge point to be reviewed; based on the target knowledge point review path, the student's target knowledge point to be reviewed is determined, and recommendation information for the target knowledge point to be reviewed is generated to recommend the student to review the target knowledge point to be reviewed.

[0178] Example 51: Determine the knowledge point mastery level indicator of the knowledge point to be reviewed from the knowledge point network; when the knowledge point mastery level indicator of the knowledge point to be reviewed is not mastered, determine the first knowledge point mastery level indicator of at least one prerequisite knowledge point and the second knowledge point mastery level indicator of at least one related knowledge point in the knowledge point network to be reviewed; based on the first knowledge point mastery level indicator and the second knowledge point mastery level indicator, update the knowledge point review path to obtain the target knowledge point review path corresponding to the knowledge point to be reviewed.

[0179] Example 52: Based on the mastery level identifier of the first knowledge point and the mastery level identifier of the second knowledge point, determine the set of first knowledge points that the student has mastered from at least one prerequisite knowledge point and at least one related knowledge point; remove the set of first knowledge points from the network of knowledge points to be reviewed, and use the knowledge points to be reviewed as the starting point of the review path to update the network of knowledge points to be reviewed, so as to obtain the target knowledge point review path corresponding to the knowledge points to be reviewed.

[0180] Example 53: Based on the mastery level indicators of the first and second knowledge points, determine the set of second knowledge points that the student has not mastered from at least one prerequisite knowledge point and at least one related knowledge point; determine the learning priority information of the knowledge points in the second knowledge point set; based on the learning priority information, select the first target knowledge point that meets the priority condition from the second knowledge point set; use the first target knowledge point as the starting point of the review path, update the network of knowledge points to be reviewed, and obtain the review path of the target knowledge point.

[0181] Example 54: Determine the mastery probability data and knowledge point difficulty data for each knowledge point in the second knowledge point set; evaluate the learning priority of each knowledge point in the second knowledge point set based on the mastery probability data and knowledge point difficulty data to obtain the learning priority information of each knowledge point in the second knowledge point set; determine the knowledge point with the highest learning priority information in the second knowledge point set as the first target knowledge point.

[0182] Example 55: When the knowledge point mastery level indicator of the knowledge point to be reviewed is marked as "mastered", the knowledge point traversal range is determined based on the knowledge point to be reviewed; the knowledge points are traversed within the knowledge point traversal range to obtain the third set of knowledge points that the student has not mastered; the set of prerequisite knowledge points and the set of related knowledge points corresponding to the third set of knowledge points are determined in the knowledge graph; the second target knowledge point that meets the priority condition is determined from the third set of knowledge points, the set of prerequisite knowledge points, and the set of related knowledge points; the knowledge point to be reviewed is removed from the knowledge point network to be reviewed, and the second target knowledge point is used as the starting point of the review path to update the knowledge point network to obtain the target knowledge point review path.

[0183] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0184] Example 6: In response to obtaining the third learning behavior data of the student reviewing the target knowledge point to be reviewed, the first mastery level identifier of the target knowledge point to be reviewed is updated; the update influence range of the mastery level of the target knowledge point in the knowledge graph corresponding to the knowledge point learning grid is determined, and a set of knowledge points to be updated is formed based on the knowledge points covered by the update influence range; the mastery level data of the knowledge points in the set of knowledge points to be updated is updated, and the second mastery level identifier of the knowledge points in the set of knowledge points to be updated is updated according to the updated mastery level data; the knowledge point learning grid is updated to a knowledge point learning grid based on the second mastery level identifier, and the target review content of the student is determined according to the knowledge point learning grid.

[0185] Example 61: Based on the target prerequisite relationships and target relevance relationships of target knowledge points in the knowledge graph, determine the direct dependencies of target knowledge points, and determine the direct impact range based on the direct dependencies; based on the indirect connection relationships between target knowledge points and other knowledge points in the knowledge graph, determine the indirect dependencies of target knowledge points, and determine the indirect impact range based on the indirect dependencies; determine the set of directly impacted knowledge points covered by the direct impact range, and the set of indirect impacted knowledge points covered by the indirect impact range; generate a set of knowledge points to be updated based on the set of directly impacted knowledge points and the set of indirect impacted knowledge points.

[0186] Example 62: Determine the first indirect dependency relationship established by a target knowledge point through an indirect knowledge point in the knowledge graph, and the second indirect dependency relationship connected by multiple indirect knowledge points; based on the first influence decay degree corresponding to the first indirect dependency relationship, determine the first influence range of the target knowledge point based on the first indirect dependency relationship in the knowledge graph; based on the second influence decay degree corresponding to the second indirect dependency relationship, determine the second influence range of the target knowledge point based on the second indirect dependency relationship in the knowledge graph; determine the indirect influence range based on the first influence range and the second influence range.

[0187] Example 63: Based on direct and indirect dependencies, determine the dependency strength data between knowledge points in the set of knowledge points to be updated and the target knowledge points; identify the importance data of knowledge points in the set of knowledge points to be updated through the target model, which is trained based on students' historical behavioral characteristics and their mastery of historical knowledge points; determine the update priority information for updating knowledge points in the set of knowledge points to be updated based on dependency strength data, importance data, and mastery level data; update the mastery level data according to the update priority information, and update the second mastery level label of the knowledge points in the set of knowledge points to be updated based on the updated mastery level data.

[0188] Example 64: Determine the knowledge point update order list corresponding to the knowledge point set to be updated according to the update priority information, so as to determine the update order of knowledge points in the knowledge point set to be updated; for the first target knowledge point in the knowledge point set to be updated, determine the centrality adjustment coefficient corresponding to the first target knowledge point based on the connection strength data of the first target knowledge point in the knowledge graph, the distance data between the first target knowledge point and other knowledge points, and the degree centrality coefficient. The first target knowledge point is any knowledge point in the knowledge point set to be updated; update the mastery data of the first target knowledge point based on the centrality adjustment coefficient and the change in the mastery data of the target knowledge point; update the second mastery label of the knowledge points in the knowledge point set to be updated based on the updated mastery data of the knowledge points in the knowledge point set to be updated.

[0189] Example 65: When the connection strength data in the centrality adjustment coefficient is greater than the connection strength threshold and the change in the mastery level data is less than the first change threshold, the first target knowledge point is identified as a key knowledge point, and the second mastery level identifier of the first target knowledge point is marked as an unmastered identifier; when the degree centrality coefficient in the centrality adjustment coefficient is greater than the degree centrality threshold and the mastery level data is greater than the second mastery level threshold, the first target knowledge point is identified as a basic knowledge point, and the second mastery level identifier of the first target knowledge point is marked as a mastered identifier.

[0190] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0191] Example 7: Obtain fourth learning behavior data of students learning knowledge points in the knowledge point learning grid, and obtain third mastery level identifiers of knowledge points in the knowledge point learning grid; determine second mastery level data of students learning knowledge points in the knowledge point learning grid based on the fourth learning behavior data, and evaluate second knowledge point status data of knowledge points in the knowledge point learning grid based on the second mastery level data; determine abnormal knowledge points from the knowledge point learning grid based on the first knowledge point status data corresponding to the second mastery level data and the second knowledge point status data; update the knowledge graph corresponding to the knowledge point learning grid based on the abnormal knowledge points to obtain an updated target knowledge graph, which is used to generate the knowledge point learning grid.

[0192] Example 71: Based on the first knowledge point status data and the second knowledge point status data, perform a status data difference analysis to evaluate the degree of difference between the knowledge point mastery status displayed in the knowledge point learning grid and the student's mastery status of the knowledge points in the knowledge point learning grid; based on the fourth learning behavior data, determine the question information and note information of the student's learning of the knowledge points in the knowledge point learning grid, and determine the student's learning status information of the knowledge points in the knowledge point learning grid based on the question information, note information, and the second mastery level data; based on the learning status information and the degree of difference, identify the knowledge points with abnormal status from the knowledge point learning grid, and update the knowledge graph corresponding to the knowledge point learning grid based on the knowledge points with abnormal status to obtain the updated target knowledge graph.

[0193] Example 72: Based on note information, determine the frequency of student note updates within a target time range, and evaluate the student's learning activity data for knowledge points in the knowledge point learning grid within the target time range based on the update frequency; based on note information and question information, determine the frequency of student questions about knowledge points in the knowledge point learning grid, and evaluate the student's difficulty in understanding knowledge points in the knowledge point learning grid based on the question frequency; if the learning activity data is greater than the activity threshold and / or the difficulty in understanding data is greater than the difficulty threshold and / or the second mastery level data is less than the mastery level threshold, determine the student's learning status information for knowledge points in the knowledge point learning grid as abnormal learning status information.

[0194] Example 73: When the student's learning status information for knowledge points in the knowledge point learning grid is abnormal, the stability data of knowledge points in the knowledge point learning grid in the knowledge graph is evaluated based on the betweenness centrality data and proximity centrality data of knowledge points in the knowledge point learning grid; the credibility data of abnormal learning status information is determined based on the stability data and the degree of difference; abnormal knowledge points are identified from the knowledge point learning grid based on the credibility data, learning status information, and degree of difference; the knowledge graph corresponding to the knowledge point learning grid is updated based on the abnormal knowledge points to obtain the updated target knowledge graph.

[0195] Example 74: Divide the fourth learning behavior data of students in the knowledge point learning grid into at least one learning behavior data set, and generate a behavior feature set corresponding to at least one learning behavior data set; determine the time information corresponding to each behavior feature in the behavior feature set, and evaluate the effectiveness of each behavior feature in the behavior feature set based on the time information to obtain the effective value data of each behavior feature in the behavior feature set; filter the behavior features in the behavior feature set based on the effective value data to obtain the target behavior features in the behavior feature set that meet the effective conditions, and form a target behavior feature set; identify the box selection behavior from the target behavior feature set, and classify the learning content selected by the box selection behavior to obtain the question information and note information of students learning knowledge points in the abnormal knowledge point set.

[0196] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0197] Example 8: Determine the state correction content corresponding to the abnormal knowledge point; based on the correction content, perform state correction on the abnormal knowledge point in the knowledge point learning grid, and determine the mastery level impact data after the abnormal knowledge point has been state corrected; determine the influence range of the mastery level impact data in the knowledge graph corresponding to the knowledge point learning grid based on the mastery level impact data, and update the knowledge graph within the influence range.

[0198] Example 81: When the first mastery level identifier is a mastery identifier, determine the question information and note information of the student's learning of knowledge points in the knowledge point learning grid based on learning behavior data; evaluate the student's learning needs for knowledge points with abnormal status based on question information and note information, and obtain the learning intention intensity data corresponding to the knowledge points with abnormal status; determine the first mastery level data corresponding to the knowledge points with abnormal status based on the first mastery level identifier; when the learning intention intensity data is greater than the learning intention intensity threshold and the first mastery level data is less than the mastery level threshold, determine the first non-mastery identifier as the second mastery level identifier; determine the first state correction content corresponding to the knowledge points with abnormal status based on the mastery identifier and the first non-mastery identifier.

[0199] Example 82: When the first mastery level identifier is the first non-mastery identifier, the student's question information and note information for learning knowledge points in the knowledge point learning grid are determined based on learning behavior data; the frequency of questions the student has about knowledge points with abnormal status is determined based on the note information and question information, and the student's difficulty in understanding knowledge points with abnormal status is evaluated based on the question frequency; the student's score data for the questions corresponding to the knowledge points with abnormal status is determined; when the difficulty in understanding data is greater than the difficulty in understanding threshold and the score data is less than the score threshold, the second non-mastery identifier is determined as the second mastery level identifier; based on the first non-mastery identifier and the second non-mastery identifier, the second status correction content corresponding to the knowledge points with abnormal status is determined.

[0200] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0201] Example 9: Obtain the student's historical learning data; based on the student's historical learning data, determine the student's learning ability data and the student's learning status information for the knowledge points in the knowledge point learning grid; based on the learning ability data and the learning status information, determine the student's learning plan type, and determine the set of knowledge points to be learned in the knowledge point learning grid according to the learning plan type; generate the student's learning path in the knowledge point learning grid based on the set of knowledge points to be learned; determine the set of learning materials that match the learning path from the learning materials, so as to recommend that the student learn the set of knowledge points to be learned based on the set of learning materials.

[0202] Example 91: Extract students' learning characteristics from their historical learning data, and determine their historical learning status for the corresponding historical knowledge points based on these characteristics. The learning characteristics include at least one of learning speed, learning memory, and answering characteristics. Determine students' learning ability data based on their historical learning status. Determine the mastery probability data and centrality data of knowledge points in the knowledge point learning grid, and determine the intensity of students' learning intention for the knowledge points in the knowledge point learning grid based on their historical learning data. Construct a learning status matrix for students' knowledge points in the knowledge point learning grid based on the mastery probability data, centrality data, and intensity of learning intention data. This learning status matrix represents the students' learning status information for the knowledge points in the knowledge point learning grid.

[0203] Example 92: Based on learning ability data and learning status information, determine the time limit of the student's learning plan, and generate at least one learning task information corresponding to the student according to the learning plan time limit; match the at least one learning task information with the knowledge graph corresponding to the knowledge point learning grid to map the at least one learning task information to at least one candidate knowledge point set in the knowledge point learning grid; determine the priority data of the knowledge points in the at least one candidate knowledge point set based on mastery probability data, centrality data, and learning intention intensity data; and form a learning knowledge point set based on the priority data and the knowledge points in the at least one candidate knowledge point set that meet the priority conditions.

[0204] Example 93: Based on the dependencies of knowledge points in the knowledge graph corresponding to the knowledge point learning grid, generate a first knowledge point sequence corresponding to the knowledge points in the set of knowledge points to be learned. The dependencies include prerequisite relationships and relevance relationships. Determine the learning speed information corresponding to the first knowledge point sequence. If the learning speed is greater than the speed threshold, determine the parallel knowledge points corresponding to the first knowledge point sequence, and generate a learning path based on the parallel knowledge points and the first knowledge point sequence. If the learning speed is less than or equal to the speed threshold, generate a learning path based on the first knowledge point sequence.

[0205] Example 94: Based on the prerequisite relationships of knowledge points in the set of knowledge points to be learned in the knowledge graph, determine the set of prerequisite knowledge points corresponding to the set of knowledge points to be learned; generate an initial knowledge point sequence based on the set of knowledge points to be learned, and insert the knowledge points in the set of prerequisite knowledge points into the preceding positions of the knowledge points in the set of knowledge points to be learned in the initial knowledge point sequence to obtain the first knowledge point sequence.

[0206] Example 95: Based on at least one first material feature in the content dimension and at least one second material feature in the question dimension, a feature vector corresponding to the learning material is constructed; the feature vector and student ability data are subjected to correlation matching and similarity matching to obtain a comprehensive matching result of the feature vector and student ability data, and candidate learning materials suitable for the student are selected from the learning materials according to the comprehensive matching result; the student's learning duration is determined based on the student's ability data, and at least one target learning plan is generated for the student according to the learning duration and the learning path to be learned; a set of learning materials matching each of the at least one target learning plan is determined from the learning materials.

[0207] Example 96: Determine the students' already-learned plans in at least one target learning plan, and the set of questions that the students have already learned in the already-learned plans; based on the students' learning of the set of questions they have already learned, analyze the students' mastery data of the knowledge points corresponding to the set of questions they have already learned; update the students' unlearned plans and the set of learning materials corresponding to the unlearned plans in at least one target learning plan based on the mastery data.

[0208] Furthermore, as Figure 1 and Figure 3 The specific implementation of the method shown in this embodiment provides a knowledge point recommendation device based on an AI agent, such as... Figure 4 As shown, the device includes: a determination module 31, a mapping module 32, a generation module 33, and an update module 34.

[0209] The determination module 31 is configured to obtain learning behavior data of students learning knowledge points in the set of unmastered knowledge points in the knowledge point learning grid from the learning companion system, and determine the question information and note information of students learning knowledge points in the set of unmastered knowledge points based on the learning behavior data.

[0210] The mapping module 32 is configured to map learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph.

[0211] The generation module 33 is configured to generate student learning content data based on question information and note information, and to perform multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information of the set of unmastered knowledge points.

[0212] The update module 34 is configured to update the set of unmastered knowledge points based on the student's target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, and recommend the set of unmastered knowledge points to the student.

[0213] In some examples of this embodiment, the generation module 33 is specifically configured to generate student learning content data based on question information and note information; perform similarity matching based on the first semantic embedding vector corresponding to the learning content data and the second semantic embedding vector corresponding to the learning knowledge point data to match the content similarity between the learning content data and the learning knowledge point data, and obtain a first similarity matching result; perform similarity matching based on the context data corresponding to the learning content data and the adjacent knowledge point data corresponding to the learning knowledge point data to match the overall similarity between the learning content data and the learning knowledge point data in the knowledge graph, and obtain a second similarity matching result; perform similarity matching based on the first position data of the learning content data in the textbook and the second position data of the learning knowledge point data in the textbook to match the position similarity between the learning content data and the learning knowledge point data, and obtain a third similarity matching result; and generate knowledge point location information for the set of unmastered knowledge points based on the first similarity matching result, the second similarity matching result, and the third similarity matching result.

[0214] In some examples of this embodiment, the generation module 33 is further configured to perform a fusion analysis based on the first similarity matching result, the second similarity matching result, and the third similarity matching result to evaluate the accuracy of the location of knowledge points in the set of unmastered knowledge points, and obtain location reliability data of learning content data and learning knowledge point data; select unmastered knowledge points that meet the confidence conditions from the set of unmastered knowledge points based on the location reliability data to form a set of location knowledge points; and generate knowledge point location information of the set of unmastered knowledge points based on the prerequisite relationships and relevance relationships of knowledge points in the set of location knowledge points in the knowledge graph.

[0215] In some examples of this embodiment, the generation module 33 is further configured to: determine a first set of knowledge points consisting of prerequisite knowledge points corresponding to the set of knowledge points in the knowledge graph, and a second set of knowledge points using the knowledge points in the set of knowledge points as prerequisite knowledge points, based on the prerequisite relationships of knowledge points in the set of knowledge points in the knowledge graph; extract the knowledge point dependency relationship chain corresponding to the set of unmastered knowledge points from the knowledge graph based on the set of knowledge points, the first set of knowledge points, and the second set of knowledge points; determine a third set of knowledge points in the knowledge graph related to the set of knowledge points based on the relevance relationships of knowledge points in the set of knowledge points in the knowledge graph; extract the knowledge point related relationship chain corresponding to the set of unmastered knowledge points based on the set of knowledge points and the third set of knowledge points; and generate knowledge point positioning information of the set of unmastered knowledge points based on the knowledge point dependency relationship chain and the knowledge point related relationship chain.

[0216] In some examples of this embodiment, the mapping module 32 is specifically configured to determine the knowledge point information corresponding to the learning behavior data, match the knowledge point information in the knowledge graph, and link the knowledge point information to the graph nodes in the knowledge graph according to the matching results; and generate the student's learning knowledge point data in the knowledge graph based on the graph knowledge point information corresponding to the graph nodes linked with the knowledge point information.

[0217] In some examples of this embodiment, the update module 34 is specifically configured to: evaluate students' learning needs for knowledge points in the set of unmastered knowledge points based on question information and note information, and obtain learning intention intensity data corresponding to knowledge points in the knowledge point learning grid; identify students' target learning intentions for knowledge points in the set of unmastered knowledge points based on the learning intention intensity data, question information, and note information; update the set of unmastered knowledge points based on the target learning intentions and knowledge point location information to obtain a target set of unmastered knowledge points; generate the target set of unmastered knowledge points and the target learning path corresponding to the target set of unmastered knowledge points; and generate recommendation information for the target set of unmastered knowledge points and the target learning path, so that students can master the knowledge points in the target set of unmastered knowledge points based on the target set of unmastered knowledge points and the target learning path.

[0218] In some examples of this embodiment, the determining module 31 is specifically configured to: obtain learning behavior data of students learning knowledge points in the set of unmastered knowledge points in the knowledge point learning grid from the learning companion system; divide the students' learning behavior data in the knowledge point learning grid into at least one learning behavior data set and generate a behavioral feature set corresponding to at least one learning behavior data set; determine the time information corresponding to each behavioral feature in the behavioral feature set, and evaluate the effectiveness of each behavioral feature in the behavioral feature set based on the time information to obtain the effective value data of each behavioral feature in the behavioral feature set; filter the behavioral features in the behavioral feature set based on the effective value data to obtain the target behavioral features that meet the effective conditions in the behavioral feature set, and form a target behavioral feature set; analyze the students' mastery of knowledge points in the knowledge point learning grid based on the target behavioral feature set to determine the set of unmastered knowledge points in the knowledge point learning grid; identify the box selection behavior from the target behavioral feature set, and classify the learning content selected by the box selection behavior to obtain the question information and note information of the students learning knowledge points in the set of unmastered knowledge points.

[0219] It should be noted that other corresponding descriptions of the functional units involved in the knowledge point recommendation device based on AI intelligent agents provided in this embodiment can be found in [reference needed]. Figure 1 and Figure 3 The corresponding description in [the document] will not be repeated here.

[0220] Based on the above, Figure 1 and Figure 3 Accordingly, this embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figure 1 and Figure 3 The method shown.

[0221] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0222] like Figure 5 The diagram shown is a hardware structure schematic of an electronic device according to the present invention, comprising:

[0223] At least one processor 401; and,

[0224] Memory 402 is communicatively connected to at least one processor 401; wherein,

[0225] The memory 402 stores instructions that can be executed by at least one processor, such that the at least one processor can perform the knowledge point recommendation method based on the AI ​​agent as described above.

[0226] Figure 5 Take a processor 401 as an example.

[0227] The electronic device may also include an input device 403 and a display device 404.

[0228] The processor 401, memory 402, input device 403, and display device 404 can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0229] Memory 402, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the knowledge point recommendation method based on AI intelligent agents in the embodiments of this application, for example, Figure 1 and Figure 3 The method flow is shown. The processor 401 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 402, thereby realizing the knowledge point recommendation method based on AI intelligent agents in the above embodiments.

[0230] Memory 402 may include a program storage area and a data storage area. The program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the AI ​​agent-based knowledge point recommendation method. Furthermore, memory 402 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 402 may optionally include memory remotely located relative to processor 401, and these remote memories may be connected via a network to the apparatus performing the AI ​​agent-based knowledge point recommendation method. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0231] The input device 403 can receive user clicks and generate signal inputs related to user settings and function control for the knowledge point recommendation method based on the AI ​​intelligent agent. The display device 404 may include a display screen or other display device.

[0232] One or more modules are stored in memory 402, and when run by one or more processors 401, the knowledge point recommendation method based on AI intelligent agent in any of the above method embodiments is executed.

[0233] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0234] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0235] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0236] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platform, or it can be implemented by hardware. Compared with existing technologies, this embodiment achieves precise collection of core learning-related data by acquiring students' learning behavior data on unmastered knowledge points in the knowledge point learning grid from the learning companion system and determining question and note information, providing a reliable data foundation for subsequent knowledge point association matching. By mapping the learning behavior data to the knowledge graph corresponding to the knowledge point learning grid, a deep correspondence between the learning behavior data and the knowledge graph structure is achieved, providing graph-level support for knowledge point location. By generating learning content data based on question and note information and performing multi-dimensional information matching with learning knowledge point data, precise location of unmastered knowledge points is achieved, improving the accuracy of knowledge point location. By updating and recommending the set of unmastered knowledge points based on students' learning intentions and knowledge point location information, precise matching between the target set of unmastered knowledge points and students' actual learning needs is achieved. By performing similarity matching based on the first and second semantic embedding vectors, context data and adjacent knowledge point data, and first and second position data respectively, multi-dimensional precise matching between learning content data and learning knowledge point data is achieved. The system provides comprehensive matching criteria for generating knowledge point location information. By fusing and analyzing the first, second, and third similarity matching results, location reliability data is obtained. Knowledge points meeting the confidence criteria are selected to form a set of location knowledge points, and location information is generated based on prior and relevance relationships, achieving reliable generation of knowledge point location information and improving its credibility. By determining the first, second, and third knowledge point sets, and extracting knowledge point dependency and relevance chains, structured generation of location information for unmastered knowledge point sets is achieved. By determining the knowledge point information corresponding to learning behavior data and matching links in the knowledge graph, learning knowledge point data is generated based on the linked graph knowledge point information, achieving reliable mapping between learning behavior data and knowledge graph nodes, and improving the accuracy of learning knowledge point data. By obtaining learning intent intensity data based on question and note information and identifying the target learning intent, the target unmastered knowledge point set is updated, and a target learning path and recommendation information are generated, achieving precise matching between knowledge point recommendations and student learning intent, and improving the targeting and effectiveness of recommendations.

[0237] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0238] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A knowledge point recommendation method based on AI intelligent agents, characterized in that, include: The learning behavior data of students learning knowledge points in the set of knowledge points they have not mastered in the knowledge point learning grid is obtained from the learning companion system. Based on the learning behavior data, the question information and note information of the students learning knowledge points in the set of knowledge points they have not mastered are determined. The learning behavior data is mapped into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph. Based on the question information and the note information, the student's learning content data is generated, and the learning content data is matched with the learning knowledge point data in multiple dimensions to generate the knowledge point location information of the set of unmastered knowledge points. Based on the student's target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, the set of unmastered knowledge points is updated to obtain the target set of unmastered knowledge points, and the target set of unmastered knowledge points is recommended to the student. Specifically, the step of generating the student's learning content data based on the question information and the note information, and performing multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information for the set of unmastered knowledge points includes: The student's learning content data is generated based on the question information and the note information; Similarity matching is performed based on the first semantic embedding vector corresponding to the learning content data and the second semantic embedding vector corresponding to the learning knowledge point data to match the content similarity between the learning content data and the learning knowledge point data, and a first similarity matching result is obtained. Similarity matching is performed based on the context data corresponding to the learning content data and the adjacent knowledge point data corresponding to the learning knowledge point data to match the overall similarity of the learning content data and the learning knowledge point data in the knowledge graph, and a second similarity matching result is obtained. A similarity match is performed based on the first position data of the learning content data in the textbook and the second position data of the learning knowledge point data in the textbook to match the position similarity of the learning content data and the learning knowledge point data, and a third similarity match result is obtained. Based on the first similarity matching result, the second similarity matching result, and the third similarity matching result, knowledge point location information of the set of unmastered knowledge points is generated.

2. The method according to claim 1, characterized in that, The step of generating knowledge point location information for the set of unmastered knowledge points based on the first similarity matching result, the second similarity matching result, and the third similarity matching result includes: A fusion analysis is performed based on the first similarity matching result, the second similarity matching result, and the third similarity matching result to evaluate the accuracy of locating knowledge points in the set of unmastered knowledge points, and to obtain the location reliability data of the learning content data and the learning knowledge point data. Based on the location confidence data, select unacknowledged knowledge points that meet the confidence conditions from the set of unacknowledged knowledge points to form a location knowledge point set; Based on the prior and relevance relationships of knowledge points in the set of knowledge points in the knowledge graph, the knowledge point location information of the set of unmastered knowledge points is generated.

3. The method according to claim 2, characterized in that, The process of generating knowledge point location information for the set of unmastered knowledge points based on the prior and relevance relationships of knowledge points in the location knowledge point set within the knowledge graph includes: Based on the prerequisite relationships of knowledge points in the set of location knowledge points in the knowledge graph, a first set of knowledge points consisting of prerequisite knowledge points corresponding to the set of location knowledge points in the knowledge graph is determined, and a second set of knowledge points using the knowledge points in the set of location knowledge points as prerequisite knowledge points is determined. Based on the location knowledge point set, the first knowledge point set, and the second knowledge point set, extract the knowledge point dependency chain corresponding to the unmastered knowledge point set from the knowledge graph; Based on the correlation relationship of knowledge points in the set of location knowledge points in the knowledge graph, a third set of knowledge points related to the set of location knowledge points in the knowledge graph is determined, and the knowledge point related relationship chain corresponding to the set of unmastered knowledge points is extracted based on the set of location knowledge points and the third set of knowledge points. Based on the knowledge point dependency relationship chain and the knowledge point related relationship chain, knowledge point location information of the set of unmastered knowledge points is generated.

4. The method according to claim 1, characterized in that, The step of mapping the learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph includes: The knowledge point information corresponding to the learning behavior data is determined, the knowledge point information is matched in the knowledge graph, and the knowledge point information is linked to the graph nodes in the knowledge graph according to the matching results. Based on the graph knowledge point information corresponding to the graph nodes linked with knowledge point information, the learning knowledge point data of the student in the knowledge graph is generated.

5. The method according to claim 1, characterized in that, The process of updating the set of unmastered knowledge points based on the student's target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid to obtain a target set of unmastered knowledge points, and recommending the target set of unmastered knowledge points to the student, includes: Based on the question information and the note information, the student's learning needs for the knowledge points in the set of unmastered knowledge points are evaluated, and the learning intention intensity data corresponding to the knowledge points in the knowledge point learning grid are obtained. Based on the learning intention intensity data, the question information, and the note information, the student's target learning intention for the knowledge points in the set of unmastered knowledge points is identified. The set of unmastered knowledge points is updated based on the target learning intention and the knowledge point location information to obtain the target unmastered knowledge point set, and the target unmastered knowledge point set and the target learning path corresponding to the target unmastered knowledge point set are generated. The system generates a set of knowledge points that the target student has not mastered and recommended information for the target learning path, so that the student can master the knowledge points in the set of knowledge points that the target student has not mastered based on the set of knowledge points that the target student has not mastered and the target learning path.

6. The method according to claim 1, characterized in that, The process involves acquiring learning behavior data from the learning support system, showing students' learning activities on knowledge points in the set of unmastered knowledge points within the knowledge point learning grid. Based on this learning behavior data, the process determines the student's question information and note information for learning the knowledge points in the set of unmastered knowledge points, including: The learning behavior data of students learning knowledge points in the set of knowledge points they have not mastered in the knowledge point learning grid is obtained from the learning companion system; The student's learning behavior data in the knowledge point learning grid is divided into at least one learning behavior data set, and a set of behavioral features corresponding to the at least one learning behavior data set is generated. Determine the time information corresponding to each behavioral feature in the behavioral feature set, and evaluate the effectiveness of each behavioral feature in the behavioral feature set based on the time information to obtain the effective value data of each behavioral feature in the behavioral feature set; Based on the effective value data, the behavioral features in the behavioral feature set are filtered to obtain the target behavioral features that meet the effective conditions in the behavioral feature set, and the target behavioral features are combined into a target behavioral feature set. Based on the target behavior feature set, analyze the student’s mastery of the knowledge points in the knowledge point learning grid, and determine the set of knowledge points that the student has not mastered in the knowledge point learning grid. Identify box selection behavior from the target behavior feature set, and classify the learning content selected by the box selection behavior to obtain the question information and note information of the student learning the knowledge points in the set of unmastered knowledge points.

7. A knowledge point recommendation device based on AI intelligent agents, characterized in that, include: The determination module is configured to obtain learning behavior data of students learning knowledge points in the set of unmastered knowledge points in the knowledge point learning grid from the learning companion system, and determine the question information and note information of the students learning knowledge points in the set of unmastered knowledge points based on the learning behavior data. The mapping module is configured to map the learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph. The generation module is configured to generate the student's learning content data based on the question information and the note information, and to perform multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information of the set of unmastered knowledge points. The update module is configured to update the set of unmastered knowledge points to obtain a target set of unmastered knowledge points based on the student's target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, and recommend the target set of unmastered knowledge points to the student. Specifically, the step of generating the student's learning content data based on the question information and the note information, and performing multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information for the set of unmastered knowledge points includes: The student's learning content data is generated based on the question information and the note information; Similarity matching is performed based on the first semantic embedding vector corresponding to the learning content data and the second semantic embedding vector corresponding to the learning knowledge point data to match the content similarity between the learning content data and the learning knowledge point data, and a first similarity matching result is obtained. Similarity matching is performed based on the context data corresponding to the learning content data and the adjacent knowledge point data corresponding to the learning knowledge point data to match the overall similarity of the learning content data and the learning knowledge point data in the knowledge graph, and a second similarity matching result is obtained. A similarity match is performed based on the first position data of the learning content data in the textbook and the second position data of the learning knowledge point data in the textbook to match the position similarity of the learning content data and the learning knowledge point data, and a third similarity match result is obtained. Based on the first similarity matching result, the second similarity matching result, and the third similarity matching result, knowledge point location information of the set of unmastered knowledge points is generated.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

9. An electronic device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

Images