Modeling representation method, device and equipment of teacher practical knowledge and medium

Abstract

This invention relates to the field of knowledge modeling technology, and discloses a method, apparatus, equipment, and medium for modeling and representing teachers' practical knowledge. The method includes collecting online professional development data of target teachers and extracting knowledge elements from it; determining the knowledge blocks and knowledge types corresponding to the knowledge elements based on a pre-defined knowledge framework; constructing a single-layer hypergraph model corresponding to each knowledge type based on the attribution relationships of the knowledge elements; and integrating the single-layer hypergraph models corresponding to each knowledge type based on the attribution relationships of the knowledge elements to obtain a multi-layer hypergraph model. This method provides a structured representation of teachers' practical knowledge elements, knowledge blocks, and knowledge types. By constructing single-layer, multi-layer, and superimposed hypergraph models, it integrates previously fragmented data, achieving a visual representation of the complex nested structure and dynamic activation process of practical knowledge. This provides a structured foundation for the quantitative analysis, dynamic tracking, and intelligent application of teachers' practical knowledge.

Description

Technical Field

[0001] This invention relates to the field of knowledge modeling technology, specifically to methods, devices, equipment, and media for modeling and representing teachers' practical knowledge. Background Technology

[0002] Teachers' practical knowledge refers to the cognitive system formed by teachers through reflection and refinement of their own teaching experience, which is actually used in their daily work and guides their teaching actions. It is rooted in specific and complete educational scenarios and possesses characteristics such as contextuality, personalization, tacit understanding, reflectivity, and actionability. Teachers' practical knowledge is considered a key bridge connecting teaching theory and practice, and is crucial for teachers' professional identity, teaching innovation, and professional development. According to existing research, teachers' practical knowledge mainly includes six core types: educational beliefs, self-knowledge, interpersonal knowledge, strategic knowledge, technical knowledge, and contextual knowledge. However, current mainstream teacher training and professional development support systems primarily focus on imparting explicit knowledge such as subject teaching knowledge and educational theories, lacking effective means to develop, represent, and utilize teachers' contextualized practical knowledge, creating a supply-demand mismatch that restricts the depth and effectiveness of teachers' professional development. Currently, research on teachers' practical knowledge representation mainly falls into two categories: one is qualitative in-depth description methods, which, while able to reflect the contextual nesting of knowledge, suffer from limitations such as low scalability and difficulty in large-scale application; the other is quantitative statistical and modeling methods, which are prone to problems such as isolated, fragmented, and flattened knowledge representations, failing to recreate the complex interconnected forms of knowledge. A few studies have attempted to construct teacher knowledge graphs using natural language processing technology, but the lack of a mature and systematic classification framework as support results in insufficient accuracy and completeness of knowledge representation.

[0003] In terms of network modeling techniques, traditional multi-layer network modeling often uses ordinary graph structures to represent the relationships between entities. Although it has the advantage of being simple and intuitive, it has obvious limitations in dealing with high-order collaborative relationships between multiple entities and is difficult to adapt to the diverse and complex nested structure characteristics of teachers' practical knowledge. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and medium for modeling and representing teachers' practical knowledge, in order to solve the problems of fragmentation, flattening, and difficulty in depicting high-order relationships and dynamic evolution in the existing technology of teachers' practical knowledge representation.

[0005] In a first aspect, the present invention provides a method for modeling and representing teachers' practical knowledge, the method comprising: Collect online professional development data of the target teachers and extract knowledge elements from the online professional development data; Based on a preset knowledge framework, at least one knowledge block corresponding to the knowledge element and the knowledge type corresponding to the knowledge block are determined. The preset knowledge framework includes knowledge type, knowledge block and knowledge element. Each knowledge block belongs to a knowledge type and a knowledge block includes one or more knowledge elements. Each knowledge element belongs to one or more knowledge blocks. Based on the attribution relationship of the knowledge elements, a single-layer hypergraph model corresponding to each knowledge type is constructed. The knowledge elements in the single-layer hypergraph model are hypergraph nodes, a single knowledge block is a hyperedge, and each knowledge block hyperedge connects all the knowledge elements it contains. Based on the attribution relationship of the knowledge elements, the single-layer hypergraph models corresponding to each knowledge type are integrated to obtain a multi-layer hypergraph model, wherein the multi-layer hypergraph model includes cross-layer hyperedges connecting at least two knowledge types. Based on the online training data, multiple knowledge units with timestamps are obtained. Each knowledge unit is modeled as a knowledge unit hyperedge that connects all knowledge elements. The hyperedges of each knowledge unit are associated with the multi-layer hypergraph model in the order of timestamps to generate a time-series hypergraph model. The knowledge units generated by multiple target teachers for the same practical problem are superimposed to construct a superimposed hypergraph model.

[0006] The modeling representation method for teachers' practical knowledge provided in this embodiment includes: collecting online professional development data of target teachers and extracting knowledge elements from the online professional development data; determining at least one knowledge block corresponding to the knowledge element and the knowledge type corresponding to the knowledge block based on a preset knowledge framework, wherein the preset knowledge framework includes knowledge type, knowledge block, and knowledge element, each knowledge block belongs to a knowledge type, and each knowledge block includes one or more knowledge elements, and each knowledge element belongs to one or more knowledge blocks; and constructing a single-layer hypergraph model corresponding to each knowledge type based on the attribution relationship of the knowledge elements, wherein the knowledge elements in the single-layer hypergraph model are hypergraph nodes. Each knowledge block is represented by a hyperedge, and each knowledge block hyperedge connects all the knowledge elements it contains. Based on the attribution relationships of these knowledge elements, single-layer hypergraph models corresponding to each knowledge type are integrated to obtain a multi-layer hypergraph model. This multi-layer hypergraph model includes cross-layer hyperedges connecting at least two knowledge types. Multiple knowledge units carrying timestamps are obtained based on online training data. Each knowledge unit is modeled as a knowledge unit hyperedge connecting all knowledge elements, and these hyperedges are associated with the multi-layer hypergraph model in time-stamp order to generate a temporal hypergraph model. The knowledge unit hyperedges generated by multiple target teachers for the same practical problem are superimposed to construct a superimposed hypergraph model. This method uses online training as an application scenario. By constructing a three-level framework, it achieves a structured representation of teachers' practical knowledge elements, knowledge blocks, and knowledge types. By constructing single-layer, multi-layer, and superimposed hypergraph models, it integrates the originally fragmented data, enabling a visual expression of the complex nested structure and dynamic activation process of practical knowledge. This provides a unified and accurate structured foundation for the quantitative analysis, dynamic tracking, and intelligent application of teachers' practical knowledge.

[0007] In one optional implementation, constructing a single-layer hypergraph model corresponding to each knowledge type based on the attribution relationship of the knowledge elements includes: Identify all knowledge elements belonging to the target knowledge type, in order to determine the knowledge elements and knowledge blocks corresponding to the target knowledge type; From the online training data, identify all knowledge elements belonging to any knowledge block corresponding to the target knowledge type; Each knowledge element is mapped to a hypergraph node, and each knowledge block is mapped to a hyperedge, wherein each hyperedge connects all knowledge elements corresponding to the hyperedge.

[0008] In one alternative implementation, the same knowledge element belongs to one or more knowledge blocks corresponding to the target knowledge type.

[0009] In one optional implementation, a multi-layer hypergraph model is obtained by integrating the single-layer hypergraph models corresponding to each knowledge type based on the attribution relationship of the knowledge elements, including: The correlation relationships between knowledge elements corresponding to different knowledge types are extracted from the online training data to obtain cross-layer correlation relationships; Based on the cross-layer association relationship, a cross-layer hyperedge is generated, and the cross-layer hyperedge connects at least two knowledge elements corresponding to different knowledge types; By combining the aforementioned cross-layer hyperedges with the single-layer hypergraph models corresponding to each knowledge type, a multi-layer hypergraph model is obtained.

[0010] In one optional implementation, the process of dividing online training data into multiple knowledge units carrying timestamps, modeling each knowledge unit as a knowledge unit hyperedge connecting all knowledge elements, and associating each knowledge unit hyperedge with the multi-layer hypergraph model in timestamp order to generate a temporal hypergraph model includes: The online training data is divided into multiple knowledge units based on a preset granularity, and each knowledge unit carries a timestamp. Identify the knowledge elements included in the knowledge unit, and determine the knowledge type corresponding to the knowledge element based on the preset knowledge framework; Each knowledge unit is modeled as a knowledge unit hyperedge, wherein the knowledge unit hyperedge connects all the knowledge elements included in the knowledge unit; Based on the timestamp order of the knowledge units, the hyperedges of the knowledge units are sequentially associated with the multi-layer hypergraph model to generate the temporal hypergraph model of the target teacher.

[0011] In one optional implementation, the step of superimposing the knowledge unit hyperedges generated by multiple target teachers for the same practical problem to construct a superimposed hypergraph model includes: The set of knowledge unit hyperedges corresponding to the practical problem is obtained by aggregating multiple knowledge unit hyperedges generated by multiple target teachers for the same practical problem. Each knowledge unit hyperedge in the knowledge unit hyperedge set is superimposed onto the same hypergraph structure to construct the superimposed hypergraph model corresponding to the practical problem; The superimposed hypergraph model uses all the knowledge elements involved in the set of knowledge unit hyperedges as nodes and each knowledge unit hyperedge as a hyperedge. The knowledge unit hyperedges of different teachers are presented in parallel in the same hypergraph structure, which is used to represent the state of group knowledge convergence around the practical problem.

[0012] In an optional implementation, the method further includes: Based on a preset update cycle, newly added knowledge unit hyperedges are superimposed onto the superimposed hypergraph model to update the superimposed hypergraph model.

[0013] Secondly, the present invention provides a modeling and representation device for teachers' practical knowledge, the device comprising: The data acquisition module is used to collect online professional development data of the target teachers and extract knowledge elements from the online professional development data; The data correspondence module is used to determine at least one knowledge block corresponding to the knowledge element and the knowledge type corresponding to the knowledge block based on a preset knowledge framework. The preset knowledge framework includes knowledge type, knowledge block and knowledge element. Each knowledge block belongs to a knowledge type and a knowledge block includes one or more knowledge elements. Each knowledge element belongs to one or more knowledge blocks. A single-layer modeling module is used to construct a single-layer hypergraph model corresponding to each knowledge type based on the attribution relationship of the knowledge elements. The knowledge elements in the single-layer hypergraph model are hypergraph nodes, a single knowledge block is a hyperedge, and each knowledge block hyperedge connects all the knowledge elements it contains. A multi-layer modeling module is used to integrate single-layer hypergraph models corresponding to each knowledge type based on the attribution relationship of the knowledge elements to obtain a multi-layer hypergraph model, wherein the multi-layer hypergraph model includes cross-layer hyperedges connecting at least two knowledge types. The temporal hypergraph modeling module is used to divide the online training data into multiple knowledge units with timestamps, model each knowledge unit as a knowledge unit hyperedge connecting all knowledge elements, and associate each knowledge unit hyperedge with the multi-layer hypergraph model in the order of timestamps to generate a temporal hypergraph model. The superimposed hypergraph modeling module is used to superimpose the hyperedges of knowledge units generated by multiple target teachers for the same practical problem in order to construct a superimposed hypergraph model.

[0014] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the modeling and representation method of teacher practical knowledge described in the first aspect or any corresponding embodiment thereof.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the modeling representation method of teacher practical knowledge described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a method for modeling and representing teachers' practical knowledge according to an embodiment of the present invention. Figure 2 This is a schematic diagram of a preset knowledge framework according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a multilayer structure representation model according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a single-layer hypergraph and a multi-layer hypergraph according to an embodiment of the present invention; Figure 5 This is a schematic diagram of a temporal hypergraph and an overlay hypergraph according to an embodiment of the present invention; Figure 6 This is a structural block diagram of a modeling and representation device for teachers' practical knowledge according to an embodiment of the present invention. Figure 7 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Teachers' practical knowledge refers to the understanding of education and teaching that teachers truly believe in and demonstrate through reflection and refinement of their own teaching experience. Rooted in vivid, concrete, and complete educational scenarios, teachers' practical knowledge is characterized by its contextuality, personalization, tacit understanding, reflectiveness, and action-orientation. It is widely considered more important than theoretical knowledge and indispensable for teachers' professional identity, teaching innovation, and professional development. In terms of types, teachers' practical knowledge includes six categories: educational beliefs, self-knowledge, interpersonal knowledge, strategic knowledge, technical knowledge, and contextual knowledge. Current mainstream training content focuses primarily on subject teaching knowledge and educational theories, lacking the development and application of teachers' practical knowledge. This mismatch between supply and demand severely restricts teachers' professional development. For teachers, practical knowledge is not only a bridge connecting teaching theory and practice but also reflects their subjectivity and irreplaceability. Fully exploring and utilizing teachers' practical knowledge helps empower and enhance the teaching profession.

[0020] Knowledge representation is a crucial foundation for extracting, analyzing, and utilizing teachers' practical wisdom. Representing teachers' practical knowledge as structured information that computers can understand helps enrich and develop support pathways for teachers' professional development in the digital age. Examples include visually presenting the development status of teachers' practical knowledge at the individual, community, or regional level and providing facilitative suggestions; constructing knowledge bases geared towards solving real-world educational problems; and designing intelligent intervention measures based on teachers' knowledge status during online professional development.

[0021] Current research on the representation of teachers' practical knowledge largely focuses on qualitative descriptions or quantitative statistics and modeling. The former, while possessing contextual nesting, suffers from low scalability, while the latter is prone to problems such as isolated, fragmented, and flattened knowledge representation. A few studies have attempted to construct teacher knowledge graphs using natural language processing techniques, but a mature classification framework is still lacking. The deep integration of knowledge graphs, hypergraphs, and multilayer networks holds promise for innovative breakthroughs in the representation of teachers' practical knowledge. Traditional multilayer network modeling typically uses ordinary graph structures to represent relationships between entities. While simple and intuitive, this approach has limitations in handling higher-order relationships. In contrast, hyperedges and hypergraphs can represent non-linear relationships between knowledge elements and possess the ability to model higher-order relationships. Therefore, they can more flexibly and accurately represent the collaborative relationships between multiple knowledge entities, helping to present the diverse and complex nested structures of teachers' practical knowledge.

[0022] Knowledge representation focuses on how to concretely store and encode knowledge models in computers using formalized symbols. Teachers' practical knowledge possesses both individual characteristics and public attributes. Taking online teacher professional development as an example, professional development communities contain both personalized practical knowledge from individual teachers and shared practical knowledge from a group of teachers around a specific practical topic. Individual teacher practical knowledge can be extracted from the posts and replies on various practical topics in which that individual participates, while group practical knowledge is extracted from all posts and replies by teachers on a specific topic. By processing the text of teachers' posts and replies, we can obtain the elements of teachers' practical knowledge and the relationships between these elements, as well as the structural relationships between knowledge types, chunks, and elements.

[0023] Based on this, this invention takes online professional development as an application scenario and explores a method for representing the practical knowledge of individual and group teachers based on hypergraph modeling. Specifically, the single-layer hypergraph for categorized knowledge and the multi-layer hypergraph for overall knowledge aim to represent the practical knowledge of teachers ultimately formed within the professional development community, and can also be used for the visualization of the teacher practical knowledge ontology; the temporal hypergraph and overlay hypergraph, reflecting individual thinking and collective wisdom, aim to represent the procedural knowledge state of the professional development community, and can be used to represent the dynamic knowledge evolution of the community.

[0024] According to an embodiment of the present invention, a modeling representation method for teachers' practical knowledge is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] This embodiment provides a method for modeling and representing teachers' practical knowledge. Figure 1 This is a flowchart of a method for modeling and representing teachers' practical knowledge according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Collect online professional development data of the target teachers and extract knowledge elements from the online professional development data.

[0026] This embodiment uses online teacher professional development as its application context, collecting textual or multimodal data generated by target teachers during the professional development process. Online professional development data includes, but is not limited to, post content, reply interactions, dialogue rounds, and reflection logs. After collection, the data is segmented into independent units according to the granularity of posts, replies, dialogue rounds, or reflection logs. The timestamps and topic identifiers corresponding to each unit are retained. These units are then cleaned and aligned to form standardized data that can be used for subsequent processing.

[0027] Based on machine learning algorithms or fine-tuning of pre-trained models, standardized data is used for entity recognition, automatically extracting knowledge elements and identifying the relationships between these elements. These knowledge elements are teacher-related practical knowledge. For example, from a teacher's post, "In after-school extended services, I will design differentiated activities based on students' learning preferences and use online collaboration tools to improve participation," knowledge elements such as "after-school extended services," "student learning preferences," "differentiated activity design," "online collaboration tools," and "improving participation" can be extracted.

[0028] Step S102: Based on the preset knowledge framework, determine at least one knowledge block corresponding to the knowledge element and the knowledge type corresponding to the knowledge block.

[0029] The preset knowledge framework consists of three parts: knowledge type, knowledge block, and knowledge element. Each knowledge block belongs to a knowledge type, and each knowledge block includes one or more knowledge elements, and each knowledge element belongs to one or more knowledge blocks.

[0030] Knowledge type refers to the highest-level classification predefined based on the inherent attributes and functional categories of teachers' practical knowledge. It is a macro-level knowledge domain abstracted from teachers' educational and teaching practices, and constitutes the top-level framework for systematically modeling and classifying practical knowledge.

[0031] Knowledge chunks refer to meso-level knowledge units that belong to a specific knowledge type and are aggregated through synergistic relationships among multiple knowledge elements that are closely related semantically, logically, or functionally. They constitute the modular cognitive structure that enables teachers to solve specific sub-problems and cope with typical situations.

[0032] Knowledge elements refer to the smallest semantic units that can be identified and extracted from teachers' practical discourse or texts, representing specific concepts, viewpoints, skills, or situations. They are the atomic basic entities that constitute teachers' practical knowledge structure.

[0033] Specifically, the pre-defined knowledge framework is as follows: Figure 2 The three-tiered knowledge framework shown is "Knowledge Type - Knowledge Block - Knowledge Element". Each knowledge type consists of multiple knowledge blocks, and each knowledge block includes multiple knowledge elements. Furthermore, a single knowledge element can belong to multiple knowledge blocks. For example, the "Self-Knowledge" type includes knowledge blocks such as career cognition, self-assessment, and self-efficacy. Similarly, the "Career Cognition" knowledge block includes knowledge elements such as teacher role cognition, professional development motivation, and professional identity, while the "Self-Assessment" knowledge block includes knowledge elements such as evaluation criteria, evaluation perspectives, and teacher role cognition. The "Teacher Role Cognition" knowledge element belongs to multiple knowledge blocks. Table 1 shows the conceptual framework of teachers' practical knowledge types. Table 1. Conceptual Framework of Teachers' Practical Knowledge Types

[0034] Based on the above framework, the knowledge elements extracted in step S101 are matched and categorized to determine the knowledge block to which each knowledge element belongs and the knowledge type to which the knowledge block belongs. For example, the knowledge blocks corresponding to "student learning preferences" are determined to be "student insights" and "teaching strategy adaptation", and the corresponding knowledge types are interpersonal knowledge (K3) and strategy knowledge (K4), respectively; the knowledge block corresponding to "differentiated activity design" is "teaching strategies", and the corresponding knowledge type is strategy knowledge (K4); the knowledge block corresponding to "online collaboration tools" is "tool application", and the corresponding knowledge type is technical knowledge (K5).

[0035] like Figure 3 The multi-layered structural representation model shown reflects the cross-layered relational structure of knowledge ontology, i.e., the complex connections between knowledge types. In the teacher's knowledge structure, each layer represents a knowledge type (e.g., educational beliefs, self-knowledge, etc.), and different graphics represent knowledge elements belonging to different knowledge types. The lines reflect the relationships between knowledge elements. Within the same layer, knowledge elements belong to the same knowledge type, and there is a subordinate relationship between knowledge elements and knowledge blocks. It should be noted that knowledge elements that do not belong to the same knowledge block may also have a relationship. For example, in terms of strategic knowledge, a teacher's understanding of the subject content K4-1 will lead them to choose a certain teaching strategy K4-2, so there is a relationship between K4-1 and K4-2. In different layers, guided by educational beliefs (K1-1), and combined with the classroom teaching environment (K6-1) and students' learning preferences (K3-1), teachers select appropriate technical means (K5-1) to implement the established teaching strategy (K4-2). In this process, cross-layer connections are formed between knowledge elements K1-1, K3-1, K4-2, K5-1, and K6-1. In short, the knowledge elements in the teacher's practical knowledge structure exhibit both intra-layer and cross-layer relationships. Before hypergraph representation, machine learning algorithms or pre-trained models are used for fine-tuning to achieve automatic identification and storage of the "type-chunk-element" structure of teacher's practical knowledge and the relationships between them.

[0036] Step S103: Based on the attribution relationship of knowledge elements, construct a single-layer hypergraph model corresponding to each knowledge type.

[0037] In a single-layer hypergraph model, knowledge elements are hypergraph nodes, a single knowledge block is a hyperedge, and each knowledge block's hyperedge connects all the knowledge elements it contains.

[0038] A single-layer hypergraph model is used to represent different types of teachers' practical knowledge. In a single-layer hypergraph model, knowledge elements belonging to the same knowledge type are mapped as hypergraph nodes, and knowledge blocks belonging to the same knowledge type are mapped as hyperedges. Each knowledge block's hyperedge connects all the knowledge element nodes it contains. Taking the "Self-Knowledge (K2)" type as an example, a single-layer hypergraph model can be constructed, where the node set includes all knowledge elements under this knowledge type, and each hyperedge in the hyperedge set corresponds to a knowledge block (such as "Self-Identity," "Self-Assessment," and "Self-Efficacy"), connecting all the knowledge element nodes belonging to that knowledge block.

[0039] Step S104: Based on the attribution relationship of knowledge elements, integrate the single-layer hypergraph models corresponding to each knowledge type to obtain a multi-layer hypergraph model.

[0040] In the multi-layered hypergraph of teachers' practical knowledge, the relationships between layers are represented by a set of cross-layer hyperedges. Specifically, a single-layered hypergraph model integrating various knowledge types serves as a different knowledge layer, and cross-layer hyperedges are constructed based on the cross-layer relationships between knowledge elements of different knowledge types extracted from online teacher training data. Each cross-layer hyperedge contains knowledge element nodes from at least two different knowledge type layers and can be used to represent the connections between two, three, or more knowledge types. For example, when a teacher selects a teaching strategy (K4-2), they need to consider the classroom teaching environment (K6-1) in contextual knowledge; at this time, the vertex... and A cross-layer hyperedge can be formed between them. A multi-layer hypergraph model includes cross-layer hyperedges connecting at least two knowledge types.

[0041] Step S105: Based on the online training data, multiple knowledge units with timestamps are obtained. Each knowledge unit is modeled as a knowledge unit hyperedge that connects all knowledge elements. The hyperedges of each knowledge unit are associated with the multi-layer hypergraph model in the order of timestamps to generate a time-series hypergraph model.

[0042] Using a single post, a single reply, a single dialogue round, or a complete reflection log published by a teacher as the basic granularity, the professional development data is divided into multiple knowledge units, and each knowledge unit is assigned a timestamp indicating its creation time. Each knowledge unit, as a fragment of a teacher's knowledge output at a specific moment, carries the practical knowledge activated at that point in time.

[0043] For each knowledge unit, natural language processing technology is used to identify the knowledge elements it contains, and the knowledge block and knowledge type to which each knowledge element belongs are determined according to a preset knowledge framework. Subsequently, each knowledge unit is modeled as a knowledge unit hyperedge, which connects all the knowledge element nodes identified in the knowledge unit, thereby completely preserving the knowledge activation pattern represented by the knowledge unit.

[0044] For individual target teachers, based on a multi-layered hypergraph model, the hyperedges of their corresponding knowledge units are sequentially associated with the model according to the chronological order of their timestamps, forming a series of time-evolving hypergraph structures, known as temporal hypergraph models. These temporal hypergraph models represent the dynamic growth and evolution path of the target teacher's practical knowledge structure over time.

[0045] Step S106 involves superimposing the knowledge unit hyperedges generated by multiple target teachers for the same practical problem to construct a superimposed hypergraph model.

[0046] In the online professional development community, teachers conduct discussions and exchanges on specific practical issues, and each teacher contributes their practical knowledge fragments by posting and replying.

[0047] For a specific practical problem, all posts and replies from participating teachers on that problem are extracted from the training platform, and these posts are taken as knowledge units. Each knowledge unit is modeled as a knowledge unit hyperedge, and all knowledge unit hyperedges generated by all teachers on that problem are collected to form a set of knowledge unit hyperedges specific to that practical problem.

[0048] A superimposed hypergraph model is constructed based on the set of knowledge unit hyperedges. The node set of the superimposed hypergraph model is the deduplicated set of all knowledge elements involved in all knowledge unit hyperedges, and the hyperedge set of the model is the set of each original knowledge unit hyperedge. In the superimposed hypergraph model, knowledge unit hyperedges of different teachers are presented and superimposed in parallel within the same hypergraph structure, which not only preserves the thinking activation patterns of each teacher but also reveals the connections and overlaps between the contributions of different teachers.

[0049] The modeling representation method for teachers' practical knowledge provided in this embodiment includes: collecting online professional development data of target teachers and extracting knowledge elements from the online professional development data; determining at least one knowledge block corresponding to the knowledge element and the knowledge type corresponding to the knowledge block based on a preset knowledge framework, wherein the preset knowledge framework includes knowledge type, knowledge block and knowledge element, each knowledge block belongs to a knowledge type and a knowledge block includes one or more knowledge elements, and each knowledge element belongs to one or more knowledge blocks; constructing a single-layer hypergraph model corresponding to each knowledge type based on the attribution relationship of knowledge elements, wherein the knowledge elements in the single-layer hypergraph model are hypergraph nodes, a single knowledge block is a hyperedge, and each knowledge block hyperedge connects all the knowledge elements it contains; integrating the single-layer hypergraph models corresponding to each knowledge type based on the attribution relationship of knowledge elements to obtain a multi-layer hypergraph model, wherein the multi-layer hypergraph model includes cross-layer hyperedges connecting at least two knowledge types. This method takes online professional development as its application scenario. By constructing a three-level framework, it enables the structured representation of teachers' practical knowledge elements, knowledge blocks, and knowledge types. By constructing single-layer hypergraph models, multi-layer hypergraph models, and superimposed hypergraph models, it integrates the originally fragmented data and realizes the visual expression of the complex nested structure and dynamic activation process of practical knowledge. This provides a unified and accurate structured foundation for the quantitative analysis, dynamic tracking, and intelligent application of teachers' practical knowledge.

[0050] In some alternative implementations, step S103 includes: Step S201: Determine all knowledge elements belonging to the target knowledge type, so as to determine the knowledge elements and knowledge blocks corresponding to the target knowledge type.

[0051] For any knowledge type to be modeled, all knowledge elements belonging to that knowledge type are selected to form a node set under that knowledge type. At the same time, based on the preset knowledge block definition under that knowledge type, all knowledge blocks associated with that type are determined, forming the basis for constructing the hyperedge set.

[0052] Step S202: Identify all knowledge elements belonging to the target knowledge type from the online training data.

[0053] For each knowledge block under a knowledge type, identify all knowledge elements included in the knowledge block from the already selected knowledge element nodes.

[0054] Furthermore, the same knowledge element belongs to one or more knowledge blocks corresponding to the target knowledge type.

[0055] Step S203: Map each knowledge element to a hypergraph node and each knowledge block to a hyperedge.

[0056] Each hyperedge connects all the knowledge elements it corresponds to. A hyperedge can connect two or more nodes simultaneously, representing the collaborative relationship between knowledge elements, i.e., multiple knowledge elements are associated with the same knowledge block. Each knowledge element is instantiated as a vertex in the hypergraph, and each knowledge block is instantiated as a hyperedge, thus completing the construction of a single-layer hypergraph model for the target knowledge type.

[0057] Specifically, a hypergraph consists of multiple vertices. and super edge Composition, can be represented as The single-layer hypergraph for teachers' practical knowledge is defined as follows: Single-layer hypergraph model Representing different types of teacher practical knowledge, hyperborder For the knowledge blocks corresponding to this knowledge type, the nodes connected by the hyperedge For knowledge elements.

[0058] With "self-knowledge" Taking the practical knowledge type of ") as an example, such as Figure 4 The single-layer hypergraph model shown on the left: "Self-knowledge" comprises three knowledge modules, namely... Three hyperedges; each hyperedge contains multiple vertices, i.e., knowledge elements. Among them, The hyperedge representing a knowledge block as "self-identified" is formed by... composition; The hyperedge representing a knowledge block as "self-evaluation" is formed by... composition; The hyperedge representing a knowledge block as "self-efficacy" is formed by... Composition. Based on this construction process, the practical knowledge of teachers at each level ( Corresponding hypergraph models can be built separately: ,

[0059] In some alternative implementations, step S104 includes: Step S301: Extract the relationships between knowledge elements corresponding to different knowledge types from the online training data to obtain cross-level relationships.

[0060] In the process of knowledge extraction from online professional development data, it is not only necessary to identify the knowledge elements and their types, but also to analyze and extract the semantic or logical connections between knowledge elements of different knowledge types. For example, from a teacher's statement, "I often use interactive whiteboards (technical knowledge element) to stimulate students' interest (strategic knowledge element) because I believe that technology can make learning more intuitive (educational belief element)," we can extract the cross-level connections between technical knowledge, strategic knowledge, and educational beliefs.

[0061] Step S302: Generate cross-layer hyperedges based on cross-layer association relationships.

[0062] Each cross-layer hyperedge connects knowledge elements corresponding to at least two different knowledge types. For each extracted cross-layer relationship, a corresponding cross-layer hyperedge is created. Each cross-layer hyperedge contains all knowledge element nodes involved in the relationship, and these nodes must belong to at least two different knowledge types.

[0063] Step S303: Combine the cross-layer hyperedge with the single-layer hypergraph model corresponding to each knowledge type to obtain the multi-layer hypergraph model.

[0064] After constructing single-layer hypergraph models for all knowledge types (K1~K6), these models are spatially or logically stacked to form the basic architecture of a multi-layer network, where each layer corresponds to one knowledge type. Subsequently, cross-layer hyperedges are added to this basic architecture. These cross-layer hyperedges, acting as bridges connecting nodes in different knowledge layers, are integrated into the overall graph structure. Through this integration process, a multi-layer hypergraph model of teachers' practical knowledge is ultimately generated.

[0065] Specifically, such as Figure 4 As shown in the multi-layered hypergraph on the right, this type of hypergraph contains different types of knowledge, thus constituting a heterogeneous graph with a heterogeneous network structure. In the multi-layered hypergraph of teachers' practical knowledge, the connections between layers can be represented by a set of cross-layer hyperedges:

[0066] This is a set of cross-layer hyperedges representing different knowledge types, which can be used to represent the relationships between nodes in two-, three-, or multi-layer knowledge type hypergraphs. (Subscript) Used to distinguish the sets of cross-layer hyperedges obtained in different contexts, for example express The set of hyperedges between two layers. Indicates the first A cross-layer super-edge, Specifically, it is expressed as follows:

[0067] in, For this cross-layer superedge The number of knowledge element nodes included; Indicates the first The knowledge layer to which each node belongs Knowledge elements For knowledge layer The first Each node. Furthermore, any cross-layer hyperedge. It contains knowledge element nodes from at least two different types of knowledge. For example, when a teacher selects a teaching strategy K4-2 for a particular subject, they need to combine it with the classroom teaching environment K6-1 in the contextual knowledge. At this time, the hypergraph of strategy knowledge K4 and contextual knowledge K6 will have a cross-layer relationship, i.e., vertices. and A cross-layer hyperedge is formed between them, denoted as More complexly, when considering the selection of teaching strategies K4-2, teachers not only need to analyze the classroom teaching environment K6-1, but also need to pay attention to students' learning preferences K3-1, learning abilities K3-2, and select appropriate technologies K5-1, etc. At this point, more complex cross-layer relationships will emerge between K3, K4, K5, and K6, and the corresponding cross-layer hyperedges can be represented as follows: .

[0068] Through hypergraph modeling and multi-level subgraph ensemble, the multi-level hypergraph model can express the complex internal connections, hierarchical forms, and overall network structure of teachers' practical knowledge structure. Its model representation is as follows:

[0069] in, Representing the knowledge layer The sub-supergraph on, For a set of hyperedges spanning multiple layers, the function This represents the process of integrating and constructing sub-hypergraphs and cross-layer hyperedges at each knowledge layer.

[0070] In some optional implementations, step S105 above includes: Step S401: Divide the online training data into multiple knowledge units based on a preset granularity, with each knowledge unit carrying a timestamp.

[0071] The preset granularity can be flexibly set according to the scenarios in which teachers' online professional development data is generated. For example, the preset granularity can be a single post, a single reply, a single dialogue round, or a teaching reflection log in online professional development, ensuring that each knowledge unit can fully reflect the teacher's practical thinking and knowledge expression in a specific scenario. During the division process, a unique timestamp is added to each knowledge unit to accurately record the time when the corresponding practice occurred (e.g., posting time, reflection record time, etc.). At the same time, topic tags can be linked to clarify the practical problem or professional development theme to which the knowledge unit belongs.

[0072] Step S402: Identify the knowledge elements included in the knowledge unit, and determine the knowledge type corresponding to the knowledge elements based on the preset knowledge framework.

[0073] Natural language processing can be used to process knowledge units, identify the knowledge elements they contain, and determine the knowledge block to which each identified knowledge element belongs and the knowledge type above it based on a pre-defined knowledge framework. For example, if two elements, "using gamified teaching" and "improving student participation," are identified from a certain knowledge unit, they can be determined to belong to the teaching strategy block (strategic knowledge K4) and the student learning preference block (interpersonal knowledge K3), respectively.

[0074] Step S403: Model each knowledge unit as a knowledge unit hyperedge.

[0075] In this context, a knowledge unit's hyperedge connects all the knowledge elements it encompasses. All identified knowledge elements within a knowledge unit are treated as nodes, and a hyperedge connects all these elements.

[0076] Step S404: Based on the timestamp order of knowledge units, the hyperedges of knowledge units are sequentially associated with the multi-layer hypergraph model to generate the temporal hypergraph model of the target teacher.

[0077] First, a multi-layered knowledge hypergraph model of the target teacher is constructed. Then, according to the chronological order of the timestamps of all knowledge units generated by the target teacher, the corresponding knowledge unit hyperedges are sequentially associated with the static multi-layered hypergraph model to form a hypergraph that evolves according to time steps, namely the time-series hypergraph model.

[0078] Specifically, with the continued advancement of online professional development, teachers' shared and created practical knowledge is constantly accumulating, meaning that teachers' practical knowledge structure is in a dynamic and evolving state. For an individual teacher, taking a single post or reply as a knowledge unit, by analyzing the teacher's knowledge units across all practical questions, their practical knowledge structure can be abstracted. When answering specific practical questions, teachers' subjective value judgments about the questions activate knowledge elements related to educational beliefs within their knowledge structure, thereby activating other layers of knowledge elements. Hyperedge modeling of knowledge units can reconstruct the implicit thinking activation process when teachers participate in discussions of practical questions or apply practical knowledge to solve problems. In other words, these activated knowledge elements and their relationships constitute a hyperedge that runs through all levels of the knowledge structure; this hyperedge is the knowledge unit.

[0079] like Figure 5 As shown in the temporal hypergraph, the hyperedges of knowledge units contain various types of knowledge elements, which may originate from one or more knowledge subgraphs (knowledge types). For example, a teacher's post "Design of after-school extended service activities" is the first... Each knowledge unit acts as a hyperedge, connecting educational goals, understanding of educational policies, teacher role positioning, student learning preferences, teaching strategies, technology applications, and school environment-related aspects. The first knowledge element. Based on this, the first... The hyperedge model of a knowledge unit can be represented as:

[0080] in, For the post The number of knowledge element nodes involved; Indicates the first The knowledge layer to which each node belongs , For knowledge layer The first Each node.

[0081] The knowledge unit also carries the temporal information of posting and replying. The following description, based on time steps, outlines the dynamic process of individual teacher's cognitive activation. A time step is the smallest unit of measurement for the sampling frequency and time scale of sequential data; that is, the time interval between one observation point and the next, such as a day or a week. Accordingly, the dynamic state of change in teachers' practical knowledge structure can be represented as:

[0082] in, Indicates the first A practical knowledge structure for each time step; Indicates the first A practical knowledge structure for each time step; This represents the change in practical knowledge at that time step, i.e., zero or several knowledge units. .

[0083] In some optional implementations, step S106 above includes: collecting multiple knowledge unit hyperedges generated by multiple target teachers for the same practical problem to obtain a set of knowledge unit hyperedges corresponding to the practical problem; and superimposing each knowledge unit hyperedge in the set of knowledge unit hyperedges into the same hypergraph structure to construct a superimposed hypergraph model corresponding to the practical problem. Among them, the superimposed hypergraph model takes all the knowledge elements involved in the set of knowledge unit hyperedges as nodes and each knowledge unit hyperedge as a hyperedge. The knowledge unit hyperedges of different teachers are presented in parallel in the same hypergraph structure, which is used to represent the state of group knowledge convergence around practical problems.

[0084] Because different teachers activate different knowledge elements and their relationships during knowledge sharing, by analyzing the knowledge units posted by all teachers under a specific practical problem, we can abstract the group practical knowledge structure of that practical problem, i.e., the superimposed hypergraph model. Here, a knowledge unit can be a post or reply addressing a specific problem. For example... Figure 5 As shown in the superimposed hypergraph, by superimposing the hyperedges of all knowledge units under any practical problem, we can obtain the superimposed hypergraph of practical knowledge of the teacher group, which is used to reflect the practical knowledge of teachers shared within the topic group.

[0085] For a specific practical problem, the superposition hypergraph of the practical knowledge of the teaching group can be represented as:

[0086] in, This represents the set of knowledge elements in an overlay hypergraph. Indicates the extracted first Each knowledge element. Denotes the set of superedges of a superimposed hypergraph. This indicates the first post published by the teacher under this practical problem. Each knowledge unit (hyperedge). Overlay hypergraphs can both preserve the teacher's original thought activation through hyperedges and identify repeatedly used or frequently applied knowledge elements in the overlay graph. Furthermore, based on the group of practical problems, overlay hypergraphs can connect knowledge elements that were originally scattered in different knowledge units, thus enabling practitioners to recognize the potential relevance of non-overlapping parts in the overlay graph when solving practical problems.

[0087] In some alternative implementations, the method further includes: overlaying newly added knowledge unit hyperedges onto the overlay hypergraph model based on a preset update cycle, so as to update the overlay hypergraph model.

[0088] As time progresses, the number of knowledge units published by teachers increases. Using a preset update cycle as the update unit, new knowledge units are added to the existing graph structure (i.e., the hypergraph model) in the form of hyperedges. This hypergraph model can be a superimposed hypergraph model, used to dynamically update the superimposed hypergraph of the teacher group, thereby reflecting the process of collective wisdom gathering around a specific practical problem. Based on this, the dynamic change state of the teacher group's knowledge superimposed hypergraph can be represented as:

[0089] in, Indicates the first A superimposed hypergraph of group practical knowledge at each time step; Indicates the first A superimposed hypergraph of group practical knowledge at each time step This represents the change in practical knowledge at that time step, i.e., zero or several knowledge units. .

[0090] The modeling representation method for teachers' practical knowledge provided in this embodiment constructs a hypergraph model that can visualize the complex nested structure and dynamic activation process of practical knowledge, offering a new approach to solving the challenges of representing high-order knowledge associations and dynamic characteristics left by traditional methods. Specifically, multi-layered hypergraph modeling based on knowledge block hyperedges helps reveal the structural integrity and network connectivity of teachers' practical knowledge. The application of temporal hypergraphs and superimposed hypergraphs effectively represents the dynamic generation, group collaboration, and intelligent regression of teachers' practical knowledge in the internet space. The use of large-model fine-tuning technology to train an automated recognition model for teachers' practical knowledge enables efficient extraction and continuous updating from raw training texts to structured knowledge, providing a computable data foundation for digital training quality evaluation, significantly reducing manual coding costs and improving the objectivity, stability, and generalizability of the evaluation. The introduction of visual learning analytics technology dynamically presents the practical knowledge hypergraph to individuals and groups, enhancing community motivation and training efficacy through group perception and training progress feedback, promoting high-quality knowledge exchange and continuous participation.

[0091] This embodiment provides a method for modeling and representing teachers' practical knowledge, which includes the following steps: Step a: Collect online professional development data of the target teachers and extract practical knowledge elements from it; Step b: Based on the preset three-level framework of "type-chunk-element", determine the knowledge chunks and knowledge types corresponding to the knowledge elements; Step c: Based on the attribution relationship of knowledge elements, construct a single-layer hypergraph model corresponding to each knowledge type; Step d: Represent the relationship between nodes in a certain layer of knowledge hypergraph and nodes in other layers of knowledge hypergraph using hyperedges to obtain cross-layer knowledge hyperedges; Step e involves integrating and connecting all the obtained single-layer and cross-layer knowledge hypergraphs to form a multi-layer hypergraph model. Step f: Construct a hyperedge using a post or reply as a knowledge unit, and overlay the knowledge units of the target individual teacher or group to form an overlay hypergraph; Step g: Based on a specific time step, the new knowledge units are added to the existing graph structure in the form of hyperedges, and the hypergraph model is dynamically updated.

[0092] This embodiment also provides a modeling and representation device for teachers' practical knowledge, which is used to implement the above embodiments and implementation methods, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0093] This embodiment provides a modeling and representation device for teachers' practical knowledge, such as... Figure 6 As shown, it includes: The data acquisition module is used to collect online professional development data of the target teachers and extract knowledge elements from the online professional development data; The data correspondence module is used to determine at least one knowledge block corresponding to the knowledge element and the knowledge type corresponding to the knowledge block based on a preset knowledge framework. The preset knowledge framework includes knowledge type, knowledge block and knowledge element. Each knowledge block belongs to a knowledge type and a knowledge block includes one or more knowledge elements. Each knowledge element belongs to one or more knowledge blocks. A single-layer modeling module is used to construct a single-layer hypergraph model corresponding to each knowledge type based on the attribution relationship of the knowledge elements. The knowledge elements in the single-layer hypergraph model are hypergraph nodes, a single knowledge block is a hyperedge, and each knowledge block hyperedge connects all the knowledge elements it contains. A multi-layer modeling module is used to integrate single-layer hypergraph models corresponding to each knowledge type based on the attribution relationship of the knowledge elements to obtain a multi-layer hypergraph model, wherein the multi-layer hypergraph model includes cross-layer hyperedges connecting at least two knowledge types. The temporal hypergraph modeling module is used to divide the online training data into multiple knowledge units with timestamps, model each knowledge unit as a knowledge unit hyperedge connecting all knowledge elements, and associate each knowledge unit hyperedge with the multi-layer hypergraph model in the order of timestamps to generate a temporal hypergraph model. The superimposed hypergraph modeling module is used to superimpose the hyperedges of knowledge units generated by multiple target teachers for the same practical problem in order to construct a superimposed hypergraph model.

[0094] In some alternative implementations, the single-layer modeling module includes: The first element determination unit is used to determine all knowledge elements belonging to the target knowledge type, so as to determine the knowledge elements and knowledge blocks corresponding to the target knowledge type. The second element determination unit is used to determine all knowledge elements belonging to any knowledge block corresponding to the target knowledge type from the online training data. The first hyperedge determination unit is used to map each knowledge element to a hypergraph node and each knowledge block to a hyperedge, wherein each hyperedge connects all knowledge elements corresponding to the hyperedge.

[0095] In some alternative implementations, the same knowledge element belongs to one or more knowledge blocks corresponding to the target knowledge type.

[0096] In some alternative implementations, the multi-layer modeling module includes: The association determination unit is used to extract the association relationships between knowledge elements corresponding to different knowledge types from the online training data to obtain cross-layer association relationships; A cross-layer hyperedge determination unit is used to generate a cross-layer hyperedge based on the cross-layer association relationship, wherein the cross-layer hyperedge connects at least two knowledge elements corresponding to different knowledge types. A multi-layer modeling unit is used to combine the cross-layer hyperedge with the single-layer hypergraph model corresponding to each knowledge type to obtain a multi-layer hypergraph model.

[0097] In some optional implementations, the temporal hypergraph modeling module is used to divide the online training data into multiple knowledge units based on a preset granularity, with each knowledge unit carrying a timestamp; identify the knowledge elements included in the knowledge unit, and determine the knowledge type corresponding to the knowledge elements based on the preset knowledge framework; model each knowledge unit as a knowledge unit hyperedge, wherein the knowledge unit hyperedge connects all the knowledge elements included in the knowledge unit; and associate the knowledge unit hyperedges sequentially with the multi-layer hypergraph model based on the timestamp order of the knowledge units to generate the temporal hypergraph model of the target teacher.

[0098] In some alternative implementations, the overlay hypergraph modeling module is used for: Multiple knowledge unit hyperedges generated by multiple target teachers for the same practical problem are aggregated to obtain a set of knowledge unit hyperedges corresponding to the practical problem. Each knowledge unit hyperedge in the set of knowledge unit hyperedges is superimposed on the same hypergraph structure to construct a superimposed hypergraph model corresponding to the practical problem. The superimposed hypergraph model uses all knowledge elements involved in the set of knowledge unit hyperedges as nodes and each knowledge unit hyperedge as a hyperedge. The knowledge unit hyperedges of different teachers are presented in parallel in the same hypergraph structure to represent the state of group knowledge convergence around the practical problem.

[0099] In some optional implementations, the apparatus further includes a time-series update module for updating the superimposed hypergraph model by overlaying newly added knowledge unit hyperedges onto the superimposed hypergraph model based on a preset update cycle.

[0100] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0101] In this embodiment, the modeling and representation device for teachers' practical knowledge is presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0102] This invention also provides a computer device having the aforementioned modeling and representation apparatus for teachers' practical knowledge.

[0103] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 7 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 7 Take a processor 10 as an example.

[0104] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0105] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0106] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0107] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0108] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0109] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0110] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0111] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the invention.

Claims

1. A method for modeling and representing teachers' practical knowledge, characterized in that, The method includes: Collect online professional development data of the target teachers and extract knowledge elements from the online professional development data; Based on a preset knowledge framework, at least one knowledge block corresponding to the knowledge element and the knowledge type corresponding to the knowledge block are determined. The preset knowledge framework includes knowledge type, knowledge block and knowledge element. Each knowledge block belongs to a knowledge type and a knowledge block includes one or more knowledge elements. Each knowledge element belongs to one or more knowledge blocks. Based on the attribution relationship of the knowledge elements, a single-layer hypergraph model corresponding to each knowledge type is constructed. The knowledge elements in the single-layer hypergraph model are hypergraph nodes, a single knowledge block is a hyperedge, and each knowledge block hyperedge connects all the knowledge elements it contains. Based on the attribution relationship of the knowledge elements, the single-layer hypergraph models corresponding to each knowledge type are integrated to obtain a multi-layer hypergraph model, wherein the multi-layer hypergraph model includes cross-layer hyperedges connecting at least two knowledge types. Based on the online training data, multiple knowledge units with timestamps are obtained. Each knowledge unit is modeled as a knowledge unit hyperedge that connects all knowledge elements. The hyperedges of each knowledge unit are associated with the multi-layer hypergraph model in the order of timestamps to generate a time-series hypergraph model. The knowledge units generated by multiple target teachers for the same practical problem are superimposed to construct a superimposed hypergraph model.

2. The modeling and representation method for teachers' practical knowledge according to claim 1, characterized in that, The construction of a single-layer hypergraph model corresponding to each knowledge type based on the attribution relationship of the knowledge elements includes: Identify all knowledge elements belonging to the target knowledge type, in order to determine the knowledge elements and knowledge blocks corresponding to the target knowledge type; From the online training data, identify all knowledge elements belonging to any knowledge block corresponding to the target knowledge type; Each knowledge element is mapped to a hypergraph node, and each knowledge block is mapped to a hyperedge, wherein each hyperedge connects all knowledge elements corresponding to the hyperedge.

3. The modeling and representation method for teachers' practical knowledge according to claim 2, characterized in that, The same knowledge element belongs to one or more knowledge blocks corresponding to the target knowledge type.

4. The modeling and representation method for teachers' practical knowledge according to claim 1, characterized in that, Based on the attribution relationships of the knowledge elements, single-layer hypergraph models corresponding to each knowledge type are integrated to obtain multi-layer hypergraph models, including: The correlation relationships between knowledge elements corresponding to different knowledge types are extracted from the online training data to obtain cross-layer correlation relationships; Based on the cross-layer association relationship, a cross-layer hyperedge is generated, and the cross-layer hyperedge connects at least two knowledge elements corresponding to different knowledge types; By combining the aforementioned cross-layer hyperedges with the single-layer hypergraph models corresponding to each knowledge type, a multi-layer hypergraph model is obtained.

5. The modeling and representation method for teachers' practical knowledge according to claim 1, characterized in that, The process involves dividing the online training data into multiple knowledge units carrying timestamps, modeling each knowledge unit as a knowledge unit hyperedge connecting all knowledge elements, and associating each knowledge unit hyperedge with the multi-layer hypergraph model in timestamp order to generate a temporal hypergraph model, including: The online training data is divided into multiple knowledge units based on a preset granularity, and each knowledge unit carries a timestamp. Identify the knowledge elements included in the knowledge unit, and determine the knowledge type corresponding to the knowledge element based on the preset knowledge framework; Each knowledge unit is modeled as a knowledge unit hyperedge, wherein the knowledge unit hyperedge connects all the knowledge elements included in the knowledge unit; Based on the timestamp order of the knowledge units, the hyperedges of the knowledge units are sequentially associated with the multi-layer hypergraph model to generate the temporal hypergraph model of the target teacher.

6. The modeling and representation method for teachers' practical knowledge according to claim 1, characterized in that, The method of superimposing hyperedges of knowledge units generated by multiple target teachers for the same practical problem to construct a superimposed hypergraph model includes: The set of knowledge unit hyperedges corresponding to the practical problem is obtained by aggregating multiple knowledge unit hyperedges generated by multiple target teachers for the same practical problem. Each knowledge unit hyperedge in the knowledge unit hyperedge set is superimposed onto the same hypergraph structure to construct the superimposed hypergraph model corresponding to the practical problem; The superimposed hypergraph model uses all the knowledge elements involved in the set of knowledge unit hyperedges as nodes and each knowledge unit hyperedge as a hyperedge. The knowledge unit hyperedges of different teachers are presented in parallel in the same hypergraph structure, which is used to represent the state of group knowledge convergence around the practical problem.

7. The modeling and representation method for teachers' practical knowledge according to claim 6, characterized in that, The method further includes: Based on a preset update cycle, newly added knowledge unit hyperedges are superimposed onto the superimposed hypergraph model to update the superimposed hypergraph model.

8. A modeling and representation device for teachers' practical knowledge, characterized in that, The device includes: The data acquisition module is used to collect online professional development data of the target teachers and extract knowledge elements from the online professional development data; The data correspondence module is used to determine at least one knowledge block corresponding to the knowledge element and the knowledge type corresponding to the knowledge block based on a preset knowledge framework. The preset knowledge framework includes knowledge type, knowledge block and knowledge element. Each knowledge block belongs to a knowledge type and a knowledge block includes one or more knowledge elements. Each knowledge element belongs to one or more knowledge blocks. A single-layer modeling module is used to construct a single-layer hypergraph model corresponding to each knowledge type based on the attribution relationship of the knowledge elements. The knowledge elements in the single-layer hypergraph model are hypergraph nodes, a single knowledge block is a hyperedge, and each knowledge block hyperedge connects all the knowledge elements it contains. A multi-layer modeling module is used to integrate single-layer hypergraph models corresponding to each knowledge type based on the attribution relationship of the knowledge elements to obtain a multi-layer hypergraph model, wherein the multi-layer hypergraph model includes cross-layer hyperedges connecting at least two knowledge types. The temporal hypergraph modeling module is used to divide the online training data into multiple knowledge units with timestamps, model each knowledge unit as a knowledge unit hyperedge connecting all knowledge elements, and associate each knowledge unit hyperedge with the multi-layer hypergraph model in the order of timestamps to generate a temporal hypergraph model. The superimposed hypergraph modeling module is used to superimpose the hyperedges of knowledge units generated by multiple target teachers for the same practical problem in order to construct a superimposed hypergraph model.

9. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the modeling representation method of teacher practical knowledge as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the modeling representation method of teacher practical knowledge as described in any one of claims 1 to 7.

Images