Multi-source software-defined science and education resource recommendation method and system based on knowledge graph

Abstract

The invention provides a multi-source software-defined science and education resource recommendation method and system based on a knowledge graph, and the method comprises the steps: constructing an artificial intelligence knowledge graph based on the relation between artificial intelligence knowledge entities; obtaining science and education resource data of a science and education institution, extracting knowledge entities in the science and education resource data, and connecting the knowledge entities to the artificial intelligence knowledge graph to obtain a science and education resource knowledge graph; extracting local resource features / user features based on a graph neural network to obtain local resource features and user features of each client; constructing a local knowledge graph based on the science and education resource knowledge graph, and performing model training by taking the local resource features of each client as initial features until the model converges; and inputting the users and the resources into the graph neural network for prediction, and recommending the resources with high scores to each user. According to the scheme, the relationship between knowledge entities in the field of artificial intelligence is effectively extracted, a structured knowledge graph is formed, and the recommendation precision is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of resource recommendation, and in particular to a method and system for recommending scientific and educational resources with multi-source software definition based on a knowledge graph. Background Art

[0002] In the process of education digitization, a huge amount of scientific and educational resources have been generated. These scientific and educational resources have greatly improved the efficiency of learners' resource acquisition. However, there are problems such as complex resources and difficulty in management. In response to this, a software-defined scientific and educational resource management model has been proposed. Through knowledge graph mining, the skill points and knowledge points contained in scientific and educational resources are included, and the knowledge graph is used as a medium to construct a knowledge semantic network of scientific and educational resources. This overcomes the problem of multi-source massive scientific and educational resource management from a semantic level. However, when dealing with massive scientific and educational resources, the software-defined scientific and educational resource model still faces a serious "knowledge wandering" problem, that is, it is difficult for users to obtain the resources they need from massive, multi-source distributed scientific and educational resources.

[0003] A common solution to the problem of knowledge wandering is to build a recommendation system based on collaborative filtering, which is oriented to centralized scenarios and assumes that scientific and educational resources and user access records to resources are concentrated in the same institution. However, in a multi-source distribution scenario, scientific and educational resources of different resources and the interaction information between users and resources are stored in different institutions. For the sake of privacy protection and knowledge security, it is difficult to share data between different institutions, which brings difficulties to the recommendation of scientific and educational resources based on collaborative filtering.

[0004] In response to this, a recommendation scheme based on federated learning was proposed. The model runs in a decentralized federated learning environment, which ensures that the user's data is completely retained on their personal device and helps to train accurate models. On the other hand, in order to better adapt to the data heterogeneity in FL (for example, user data varies greatly in scale and quality), a first-order meta-learning method is introduced to achieve fast device personalization using only a small number of data points. However, most of the schemes aggregate at the model level, which makes it difficult to effectively integrate user preference characteristics existing in different institutions, resulting in low recommendation accuracy. Summary of the invention

[0005] The purpose of the present invention is to provide a multi-source software-defined science and education resource recommendation method and system based on knowledge graph to solve the above problems.

[0006] To achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for recommending multi-source software-defined science and education resources based on a knowledge graph, comprising: Based on artificial intelligence knowledge entities and the relationships between entities, an artificial intelligence knowledge graph is constructed; the scientific and educational resource data of scientific and educational institutions are obtained, knowledge entities in the scientific and educational resource data are extracted, and connected to the artificial intelligence knowledge graph to obtain the scientific and educational resource knowledge graph; Extract local resource features / user features based on graph neural networks to obtain local resource features and user features of each client; Build a local knowledge graph based on the knowledge graph of science and education resources, and use the local resource features of each client as the initial features for model training until the model converges; Users and resources are input into the graph neural network for prediction, and resources with high scores are recommended to each user.

[0007] Optionally, build an AI knowledge graph based on AI knowledge entities and the relationships between entities, including: Build a knowledge corpus in the field of artificial intelligence, use entity recognition algorithms and relationship extraction algorithms to extract knowledge entities and relationships between entities in the field of artificial intelligence, and form a knowledge graph in the field of artificial intelligence; Specific: Collect and annotate text data, divide it into training set, validation set and test set, segment the text, remove stop words and encode it; On a given corpus, the BERT language processing model is used to extract text features, and then the model is trained with the help of , and the performance is evaluated on the validation set. The trained model is then applied to the test set for named entity recognition; Relevant features were extracted, trained using a recurrent neural network, and the model performance was evaluated on a validation set.

[0008] Optionally, obtain the scientific and educational resource data of the scientific and educational institution, extract the knowledge entities in the scientific and educational resource data, connect them to the artificial intelligence knowledge graph, and obtain the scientific and educational resource knowledge graph, including: The metadata, text, video, image, and file data contained in the scientific and educational resources held by each scientific and educational institution are processed, the knowledge entities and their associations are extracted, and they are aligned and connected with the constructed artificial intelligence knowledge graph to build a software-defined scientific and educational resource knowledge graph that integrates artificial intelligence knowledge points and scientific and educational resources: The multimodal entity recognition process starts with collecting and annotating a data set containing text and corresponding images, performing word segmentation and word embedding processing on the text to generate a vector representation, and using a convolutional neural network to extract image features; constructing independent text processing networks and image processing networks, using Transformer or convolutional neural networks to process them respectively and weighted fusion of the processed results to generate a comprehensive feature representation, which is used to output the category of each entity; The learned features are measured by cosine similarity with the knowledge point features in the knowledge graph, and the results with the closest distance are selected for linking to complete the knowledge connection from scientific and educational resources to entities in the KG.

[0009] Optionally, local resource features / user features are extracted based on a graph neural network to obtain local resource features and user features of each client, including: On each client, a user preference network is constructed by graph modeling the "user-resource" preference relationship. The cross entropy loss function is constructed using the preference relationship to train the model. When the model converges, the local resource characteristics and user characteristics of each client are obtained.

[0010] Optionally, a local knowledge graph is built based on the knowledge graph of science and education resources, and the local resource features of each client are used as initial features for model training until the model converges, including: For the scenario of recommending scientific and educational resources, a recommendation network is built based on graph convolutional neural network; Based on the constructed model, a loss function is constructed, and data is input into the model for loss calculation and the model parameters are updated through back propagation until the model converges.

[0011] Optional, model building, including: Feature Embedding Module: At each layer, for each edge type Assign one Dimensional Embedding , and use both edge type embeddings and node embeddings to compute the attention score:

[0012] in Representation Node and nodes The type of edge between is a learnable matrix used to transform type embedding; Residual link module: adds pre-activated residual connections for cross-layer node representation, assuming It is the edge The attention weight, is the activation function. When the feature dimension of the layer changes, the scheme uses a learnable linear transformation Transform the features and perform residual aggregation on the transformed features:

[0013] Similarly, the residual module is also introduced for edge feature learning, as follows:

[0014] Multi-head attention module: introduces a multi-head attention mechanism, using The independent attention modules learn the features separately and concatenate the learned features to obtain the final feature representation. The corresponding update rules are as follows:

[0015]

[0016]

[0017] Final output layer The output of the layer is:

[0018] Preference information prediction: The output features are then input into the prediction module based on the multi-layer perceptron. Specifically, for user features and resource characteristics , after concatenating the features, input them into the multi-layer perceptron to get the predicted score as follows: .

[0019] Optional, model training, including: Construct cross entropy: a set of predicted label results for the output and the true label , construct the cross entropy loss as follows:

[0020] Gradient propagation: Then use the back propagation of the neural network to calculate the gradient and optimize the parameters to evaluate whether the stopping condition is reached. If the model has not converged, continue training until the model converges.

[0021] In a second aspect, the present invention provides a multi-source software-defined science and education resource recommendation system based on a knowledge graph, comprising: The science and education resource knowledge graph acquisition module is used to construct an artificial intelligence knowledge graph based on artificial intelligence knowledge entities and the relationships between entities; obtain the science and education resource data of scientific and educational institutions, extract the knowledge entities in the science and education resource data, connect them to the artificial intelligence knowledge graph, and obtain the science and education resource knowledge graph; The feature extraction module is used to extract local resource features / user features based on the graph neural network to obtain local resource features and user features of each client; The model training module is used to build a local knowledge graph based on the knowledge graph of scientific and educational resources. The local resource features of each client are used as initial features for model training until the model converges. The prediction output module is used to input users and resources into the graph neural network for prediction and recommend high-scoring resources to each user.

[0022] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the multi-source software-defined science and education resource recommendation method based on a knowledge graph when executing the computer program.

[0023] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the multi-source software-defined science and education resource recommendation method based on a knowledge graph.

[0024] Compared with the prior art, the present invention has the following technical effects: By constructing a knowledge corpus in the field of artificial intelligence and using entity recognition algorithms and relationship extraction algorithms, the present invention effectively extracts knowledge entities and relationships between entities in the field of artificial intelligence, forming a structured knowledge graph. This helps to organize and manage knowledge efficiently, and facilitates subsequent retrieval and application.

[0025] The present invention aligns and connects the scientific and educational resources (including metadata, text, video, image, file, etc.) held by various scientific and educational institutions with the constructed artificial intelligence knowledge graph, and constructs a software-defined scientific and educational resource knowledge graph that integrates artificial intelligence knowledge points and scientific and educational resources. This integration method not only realizes resource sharing, but also promotes the deep integration of knowledge and resources.

[0026] The present invention models the preference relationship of "user-resource" through a graph neural network, and uses the preference relationship to construct a cross entropy loss function for model training. The solution can accurately extract the characteristics of users and resources. This helps to more accurately understand user needs and resource characteristics, and provide strong support for subsequent recommendations. The solution uses knowledge graphs as feature propagation media, combined with graph convolutional neural networks, to achieve effective propagation and fusion of resource features and user preference features among different institutions. This feature propagation method not only takes into account the semantic level of features, but also integrates knowledge point features through the attention mechanism to obtain comprehensive knowledge point features.

[0027] The present invention achieves efficient model training by constructing a cross entropy loss function and optimizing the parameters by calculating the gradient through back propagation of the neural network. This training method not only converges quickly but also ensures the stability and accuracy of the model. The local feature update step in the scheme allows the local resource features to be updated according to the global knowledge point features, and the updated features are input into the graph neural network together with the local user features for feature update. This flexible model update mechanism helps to adapt to the ever-changing user needs and resource environment.

[0028] The present invention adopts a method for recommending scientific and educational resources based on federated collaborative filtering. The scheme can input users and resources into a graph neural network for prediction, and recommend resources with higher scores to each user. This recommendation method not only takes into account the personalized needs of users, but also makes full use of scientific and educational resources across institutions to achieve accurate recommendation services. Since the scheme uses the knowledge graph as a feature propagation medium and realizes feature aggregation at the semantic level, it can effectively resist the performance degradation problem of the recommendation model caused by heterogeneous user preferences and heterogeneous resources. This helps to improve the accuracy and stability of recommendations and enhance user experience.

[0029] The present invention uses an open knowledge graph as a barrier to connect the scientific and educational resources and user preference information stored by different educational institutions, and realizes the learning of distributed recommendation models. This design not only ensures the security and privacy of data, but also promotes cross-institutional cooperation and resource sharing.

[0030] In summary, this technical solution realizes cross-institutional scientific and educational resource recommendation services through steps such as building knowledge graphs, extracting features, training models, and optimizing recommendations. This solution is not only efficient, accurate, and flexible, but also fully considers privacy protection and security issues, providing strong technical support for the sharing and utilization of scientific and educational resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of the present invention.

[0032] Figure 2 System model diagram. DETAILED DESCRIPTION

[0033] The present invention is further described below in conjunction with the accompanying drawings: Example 1, please refer to Figure 1 The present invention provides a method for recommending multi-source software-defined science and education resources based on knowledge graph, comprising: Based on artificial intelligence knowledge entities and the relationships between entities, an artificial intelligence knowledge graph is constructed; the scientific and educational resource data of scientific and educational institutions are obtained, knowledge entities in the scientific and educational resource data are extracted, and connected to the artificial intelligence knowledge graph to obtain the scientific and educational resource knowledge graph; Extract local resource features / user features based on graph neural networks to obtain local resource features and user features of each client; Build a local knowledge graph based on the knowledge graph of science and education resources, and use the local resource features of each client as the initial features for model training until the model converges; Users and resources are input into the graph neural network for prediction, and resources with high scores are recommended to each user.

[0034] By constructing an artificial intelligence knowledge graph, this method effectively organizes knowledge entities and the relationships between entities in the field of artificial intelligence, providing a rich knowledge background for subsequent scientific and educational resource recommendations.

[0035] By combining the scientific and educational resource data of scientific and educational institutions with the artificial intelligence knowledge graph, a scientific and educational resource knowledge graph was constructed, realizing the deep integration of knowledge and resources. This integration method not only improves the availability of resources, but also promotes the dissemination and sharing of knowledge.

[0036] Graph neural networks are used to extract local resource features / user features. This method can more accurately capture the complex relationship between resources and users and improve the accuracy and robustness of feature representation.

[0037] By using the local resource features and user features of each client as the initial features for model training, this method can learn more representative features and provide strong support for subsequent recommendations.

[0038] This method uses a model training method based on the knowledge graph of scientific and educational resources, and optimizes the model parameters through continuous iteration until the model converges. This training method not only improves the accuracy of the model, but also enhances the generalization ability of the model.

[0039] By using graph neural networks for prediction, this method can respond to user needs more quickly and provide real-time scientific and educational resource recommendation services.

[0040] Users and resources are input into the graph neural network for prediction, and resources are recommended based on the scores. This method can more accurately match user needs with resource characteristics, improving the accuracy and satisfaction of recommendations.

[0041] Since this method takes into account the integration and utilization of multi-source scientific and educational resources, it can provide users with richer and more comprehensive scientific and educational resource recommendation results.

[0042] By building a unified knowledge graph of scientific and educational resources, this method promotes cooperation and resource sharing among different scientific and educational institutions. This cooperation mode not only improves the efficiency of resource utilization, but also promotes the exchange and dissemination of knowledge. This method provides a common platform and interface for scientific and educational institutions to facilitate data exchange and resource complementarity between them, thereby promoting the coordinated development of science and education.

[0043] In summary, this multi-source software-defined science and education resource recommendation method based on knowledge graph achieves efficient integration and personalized recommendation of science and education resources through steps such as building knowledge graph, extracting features, training models and optimizing recommendations. Its technical effect is not only reflected in the improvement of recommendation accuracy, but also in the promotion of cross-institutional cooperation and resource sharing, providing strong technical support and driving force for the development of science and education.

[0044] Embodiment 2, the present invention provides a method for recommending multi-source software-defined science and education resources based on knowledge graph, specifically comprising:

[0045] The system model is: like Figure 2 As shown, the system includes Different scientific and educational institutions For each institution ,Include Users, Scientific and educational resources and the preference relationship between users and scientific and educational resources ; In addition, there is a knowledge graph in the field of artificial intelligence in the system, which contains a knowledge graph composed of knowledge points related to the field of artificial intelligence The main purpose of the software-defined multi-source collaborative recommendation algorithm for scientific and educational resources based on knowledge graph is to learn the characteristics of users and resources from the user preference relationship network for scientific and educational resources maintained by different scientific and educational institutions and integrate them with the help of artificial intelligence knowledge graph, so as to extract more comprehensive user and resource characteristics and achieve more accurate resource recommendation.

[0046] 1. The software-defined science and education resource knowledge graph based on the knowledge graph mainly includes the following steps: Artificial intelligence knowledge graph construction: Build a knowledge corpus in the field of artificial intelligence, use entity recognition algorithms and relationship extraction algorithms to extract knowledge entities and relationships between entities in the field of artificial intelligence, and form a knowledge graph in the field of artificial intelligence ; Local science and education resource links: For each science and education institution , process different types of data such as metadata, text, video, image, and file contained in the scientific and educational resources it holds, extract the knowledge entities and their associations, align and connect them with the constructed artificial intelligence knowledge graph, and build a software-defined scientific and educational resource knowledge graph that integrates artificial intelligence knowledge points and scientific and educational resources ; Local resource feature / user feature extraction based on graph neural network: On each client, a user preference network is constructed by graph modeling the preference relationship between “user-resource”. ; Use the preference relationship to build a cross entropy loss function and train the model. When the model converges, the local resource characteristics and user characteristics of each client are obtained; Cross-entity feature propagation based on knowledge graph: each entity Utilize local science and education resource collection and shared AI knowledge graph Build a local knowledge graph , using the scientific and educational resource features learned in step (3) as the initial features, input them into the convolutional neural network for feature learning, each for Each entity in , Learn local features ; Subsequently, all institutions share ; Then, each client uses the attention mechanism to fuse the knowledge point features to obtain comprehensive knowledge point features ; Local feature update: Given Update local resource characteristics and associate the updated resource characteristics with Input the graph neural network to complete the local user feature and resource feature update; Model training: Step (4) to step (5) are repeated until the model converges; Recommendation of scientific and educational resources based on federated collaborative filtering: users and resources are input into the graph neural network for prediction, and resources with higher scores are recommended to each user.

[0047] 2. The knowledge graph construction described in 1 mainly includes the following processes: Corpus construction: collect and annotate text data and divide it into training, validation and test sets. Then, tokenize the text, remove stop words and encode it so that the model can understand it.

[0048] Named Entity Recognition: On a given corpus, the BERT language processing model is used to extract text features (, and then the model is trained with the help of , and the performance is evaluated on the validation set, and the parameters are adjusted to improve the effect. The trained model is applied to the test set for named entity recognition.

[0049] Relation Extraction: Extract relevant features, train using a recurrent neural network, and evaluate model performance on a validation set.

[0050] 3. The science and education resource link shown in 1 mainly includes the following steps: Feature extraction of multimodal science and education resources: The multimodal entity recognition process starts with collecting and annotating a data set containing text and corresponding images, performing word segmentation and word embedding processing on the text to generate a vector representation, and using a convolutional neural network to extract image features. In the model design, independent text processing networks and image processing networks are constructed, and Transformer or convolutional neural networks are used for processing respectively, and the processed results are weighted and fused to generate a comprehensive feature representation, which is used to output the category of each entity.

[0051] Entity matching from scientific and educational resources to knowledge graph: The learned features are measured by cosine similarity with the knowledge point features in the knowledge graph, and the closest results are selected for linking to complete the matching from scientific and educational resources to knowledge graph. Knowledge links of entities in .

[0052] 4. The resource feature / user feature extraction based on graph neural network as shown in 1 includes the following steps: Model building: Aiming at the scenario of recommending scientific and educational resources, a recommendation network is built based on graph convolutional neural network; Model training: Based on the constructed model, a loss function is constructed, and data is input into the model for loss calculation and the model parameters are updated through back propagation until the model converges; 5. The model construction shown in 4 mainly includes the following modules: Feature Embedding Module: At each layer, for each edge type Assign one Dimensional Embedding , and use both edge type embeddings and node embeddings to compute the attention score:

[0053] in Representation Node and nodes The type of edge between is a learnable matrix used to transform type embeddings; Residual link module: adds pre-activated residual connections for cross-layer node representation, assuming It is the edge The attention weight, is the activation function. When the feature dimension of the layer changes, the scheme uses a learnable linear transformation Transform the features and perform residual aggregation on the transformed features:

[0054] Similarly, the residual module is also introduced for the learning of edge features, as follows:

[0055] Multi-head attention module: In order to further enhance the learning ability of the model, a multi-head attention mechanism is introduced. The independent attention modules learn the features separately and concatenate the learned features to obtain the final feature representation. The corresponding update rules are as follows:

[0056]

[0057]

[0058] Final output layer The output of the layer is:

[0059] Preference information prediction: The output features are then input into the prediction module based on the multi-layer perceptron. Specifically, for user features and resource characteristics , after concatenating the features, input them into the multi-layer perceptron to get the predicted score as follows:

[0060] 6. Model training as shown in 4 mainly includes the following steps: Construct cross entropy: a set of predicted label results for the output and the true label , construct the cross entropy loss as follows:

[0061] Gradient propagation: Then use the back propagation of the neural network to calculate the gradient and optimize the parameters to evaluate whether the stopping condition is reached. If the model has not converged, repeat step 5 until the model converges.

[0062] In yet another embodiment of the present invention, a multi-source software-defined science and education resource recommendation system based on a knowledge graph is provided, which can be used to implement the multi-source software-defined science and education resource recommendation method based on a knowledge graph. Specifically, the system includes: The science and education resource knowledge graph acquisition module is used to construct an artificial intelligence knowledge graph based on artificial intelligence knowledge entities and the relationships between entities; obtain the science and education resource data of scientific and educational institutions, extract the knowledge entities in the science and education resource data, connect them to the artificial intelligence knowledge graph, and obtain the science and education resource knowledge graph; The feature extraction module is used to extract local resource features / user features based on the graph neural network to obtain local resource features and user features of each client; The model training module is used to build a local knowledge graph based on the knowledge graph of scientific and educational resources. The local resource features of each client are used as initial features for model training until the model converges. The prediction output module is used to input users and resources into the graph neural network for prediction and recommend high-scoring resources to each user.

[0063] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0064] In another embodiment of the present invention, a computer device is provided, the computer device including a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the multi-source software-defined science and education resource recommendation method based on the knowledge graph.

[0065] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the multi-source software-defined science and education resource recommendation method based on the knowledge graph in the above embodiment.

[0066] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0068] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A multi-source software-defined science and education resource recommendation method based on knowledge graph, characterized in that: include: Build an AI knowledge graph based on AI knowledge entities and the relationships between them; Obtain the scientific and educational resource data of scientific and educational institutions, extract the knowledge entities in the scientific and educational resource data, connect them to the artificial intelligence knowledge graph, and obtain the scientific and educational resource knowledge graph; Build a user preference network model, extract local resource features / user features, and obtain local resource features and user features of each client; Build a local knowledge graph based on the knowledge graph of science and education resources, and use the local resource features of each client as the initial features for model training until the model converges; Users and resources are input into the graph neural network for prediction, and resources with high scores are recommended to each user.

2. The method for recommending multi-source software-defined science and education resources based on knowledge graph according to claim 1 is characterized in that: Based on AI knowledge entities and the relationships between entities, AI knowledge graphs are constructed, including: Build a knowledge corpus in the field of artificial intelligence, use entity recognition algorithms and relationship extraction algorithms to extract knowledge entities and relationships between entities in the field of artificial intelligence, and form a knowledge graph in the field of artificial intelligence; Specific: Collect and annotate text data, divide it into training set, validation set and test set, segment the text, remove stop words and encode it; On a given corpus, the BERT language processing model is used to extract text features, and then the model is trained with the help of , and the performance is evaluated on the validation set. The trained model is then applied to the test set for named entity recognition; Relevant features were extracted, trained using a recurrent neural network, and the model performance was evaluated on a validation set.

3. The method for recommending multi-source software-defined science and education resources based on knowledge graph according to claim 1 is characterized in that: Obtain the scientific and educational resource data of scientific and educational institutions, extract the knowledge entities in the scientific and educational resource data, connect them to the artificial intelligence knowledge graph, and obtain the scientific and educational resource knowledge graph, including: The metadata, text, video, image, and file data contained in the scientific and educational resources held by each scientific and educational institution are processed, the knowledge entities and their associations are extracted, and they are aligned and connected with the constructed artificial intelligence knowledge graph to build a software-defined scientific and educational resource knowledge graph that integrates artificial intelligence knowledge points and scientific and educational resources: The multimodal entity recognition process starts with collecting and annotating a data set containing text and corresponding images, performing word segmentation and word embedding processing on the text to generate a vector representation, and using a convolutional neural network to extract image features; constructing independent text processing networks and image processing networks, using Transformer or convolutional neural networks to process them respectively and weighted fusion of the processed results to generate a comprehensive feature representation, which is used to output the category of each entity; The learned features are measured by cosine similarity with the knowledge point features in the knowledge graph, and the results with the closest distance are selected for linking to complete the knowledge connection from scientific and educational resources to entities in the KG.

4. The method for recommending multi-source software-defined science and education resources based on knowledge graph according to claim 1, characterized in that: Build a user preference network model, extract local resource features / user features, and obtain local resource features and user features of each client, including: On each client, a user preference network is constructed by graph modeling the "user-resource" preference relationship. The cross entropy loss function is constructed using the preference relationship to train the model. When the model converges, the local resource characteristics and user characteristics of each client are obtained.

5. The method for recommending multi-source software-defined science and education resources based on knowledge graph according to claim 4 is characterized in that: Based on the knowledge graph of science and education resources, a local knowledge graph is constructed. The local resource features of each client are used as initial features for model training until the model converges, including: For the scenario of recommending scientific and educational resources, a recommendation network is built based on graph convolutional neural network; Based on the constructed model, a loss function is constructed, and data is input into the model for loss calculation and the model parameters are updated through back propagation until the model converges.

6. The method for recommending multi-source software-defined science and education resources based on knowledge graph according to claim 5, characterized in that: Model building, including: Feature Embedding Module: At each layer, for each edge type Assign one Dimensional Embedding , and use both edge type embeddings and node embeddings to compute the attention score: in Representation Node and nodes The type of edge between is a learnable matrix used to transform type embedding; Residual link module: adds pre-activated residual connections for cross-layer node representation, assuming It is the edge The attention weight, is the activation function. When the feature dimension of the layer changes, the scheme uses a learnable linear transformation Transform the features and perform residual aggregation on the transformed features: Similarly, the residual module is also introduced for edge feature learning, as follows: Multi-head attention module: Introducing the multi-head attention mechanism, with the help of The independent attention modules learn the features separately and concatenate the learned features to obtain the final feature representation. The corresponding update rules are as follows: Final output layer The output of the layer is: Preference information prediction: The output features are then input into the prediction module based on the multi-layer perceptron. Specifically, for user features and resource characteristics , after concatenating the features, input them into the multi-layer perceptron to get the predicted score as follows: 。 7. The method for recommending multi-source software-defined science and education resources based on knowledge graph according to claim 5, characterized in that: Model training, including: Construct cross entropy: a set of predicted label results for the output and the true label , construct the cross entropy loss as follows: Gradient propagation: Then use the back propagation of the neural network to calculate the gradient and optimize the parameters to evaluate whether the stopping condition is reached. If the model has not converged, continue training until the model converges.

8. A multi-source software-defined science and education resource recommendation system based on knowledge graph, characterized in that: include: The science and education resource knowledge graph acquisition module is used to build an artificial intelligence knowledge graph based on artificial intelligence knowledge entities and the relationships between entities; Obtain the scientific and educational resource data of scientific and educational institutions, extract the knowledge entities in the scientific and educational resource data, connect them to the artificial intelligence knowledge graph, and obtain the scientific and educational resource knowledge graph; The feature extraction module is used to extract local resource features / user features based on the graph neural network to obtain local resource features and user features of each client; The model training module is used to build a local knowledge graph based on the knowledge graph of scientific and educational resources. The local resource features of each client are used as initial features for model training until the model converges. The prediction output module is used to input users and resources into the graph neural network for prediction and recommend high-scoring resources to each user.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the multi-source software-defined science and education resource recommendation method based on the knowledge graph are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the multi-source software-defined science and education resource recommendation method based on knowledge graph are implemented as described in any one of claims 1 to 7.

Images