Narrow Results

Knowledge graphs have demonstrated significant impact in the power grid domain, facilitating various applications such as defect diagnosis and grid management. However, their reasoning capabilities have not been fully exploited. In this paper, we explore the utilization of knowledge graphs for power grid defect diagnosis. We construct an electrical equipment defect knowledge graph and predict missing links, which is also known as Knowledge Graph Completion (KGC). However, we notice the long-tail problem in electrical equipment knowledge graph. To tackle this challenge, we propose a novel text-based model named SPALME (Structure Prompt Augmented Language Model Embedding) that incorporates structural information as prompts. Our model leverages the power of pre-trained language models, allowing it to comprehend the semantic information of entities and relationships in the knowledge graph. Additionally, by integrating structural information as prompts during the learning process, our model gains a deeper understanding of the graph’s topological structure efficiently, effectively capturing intricate dependencies between grid equipments. We evaluate our approach on various datasets. The results demonstrate that our model consistently outperforms baseline methods on the majority of the datasets.

Residents’ healthcare consumption involves many aspects such as residents’ expectations, medical institutions’ reputation, and residents’ trust, resulting in a large difference between the evaluation results and the actual value, and low residents’ satisfaction. Therefore, a method for evaluating residents’ satisfaction with healthcare consumption based on data mining and knowledge mapping is proposed. Under the framework and connotation of evaluation indicators, the evaluation indicator system of residents’ satisfaction with healthcare consumption is constructed to obtain evaluation indicators; the AHP method was used to calculate the weight of the above indicators of residents’ satisfaction with healthcare consumption; combined with the index weight, the improved hierarchical clustering method in data mining is used to cluster the evaluation indexes of residents’ satisfaction with healthcare consumption; according to the clustering results, an evaluation model was built through the knowledge map to evaluate the residents’ satisfaction with healthcare consumption. The experimental results show that the evaluation value of residents’ satisfaction with healthcare consumption is basically consistent with the actual value, and residents’ satisfaction is high.

Graphs provide essential means for organizing and analyzing complex equipment data. Although link prediction techniques have been widely applied to enhance knowledge graphs, existing methods still show room for improvement in accuracy, especially when dealing with sparse data. To address this, we introduce ELPGPT (Large Language Models Enhancing Link Prediction in Electrical Equipment Knowledge Graph), a novel approach that integrates large language models into link prediction to enhance the accuracy of relation prediction within electrical equipment knowledge graphs. The core of the ELPGPT method lies in the combination of large language models with traditional knowledge graph link prediction techniques. By leveraging the deep semantic understanding capabilities of large language models, this method effectively extracts relational features and enhances the handling of sparse data. Additionally, we employ a Retrieval-Augmented Generation (RAG) approach, which, by integrating external data sources, further enhances the precision and relevance of predictions. Experiments on the Electrical Equipment Knowledge Graph (EEKG) demonstrate that ELPGPT significantly improves performance across several metrics, including Hit@k, Mean Rank (MR), and Mean Reciprocal Rank (MRR). These results validate the effectiveness and potential applications of this method in the domain of link prediction for electrical equipment knowledge graphs.

The stable operation of the power system is closely related to the national economy and people’s livelihoods. Therefore, the timely detection, qualitative assessment, and handling of major equipment defects are crucial. The classification of defect levels in main electrical equipment is a fundamental task in this process, which is often manually completed, supplemented by knowledge bases or expert systems. However, this approach is time-consuming, labor-intensive, involves challenging human–machine interaction, and relies on expert experience. Conversational large language models, such as ChatGPT, ERNIE Bot, ChatGLM, have garnered widespread recognition in various domains. However, these models may have errors in the reasoning process, resulting in biased or even erroneous outputs, which is referred to as the “hallucinations”. The hallucinations’ problem of large language models poses challenges in specific fields. To mitigate the hallucinations in large language models, researchers often seek to incorporate domain-specific knowledge into these models through methods like fine-tuning or prompt learning. In order to enhance model performance while minimizing computational costs, this study adopts the prompt learning approach. Specifically, we propose a large language model prompt learning framework based on knowledge graphs, aiming to provide the large language model with reasoning support by leveraging specific information stored within the knowledge graph and receive explainable reasoning result. Experimental results demonstrate that our module achieved superior results on the power defect dataset compared to the non-prompt method.

There is an abundance of materials for use in professional music courses, but it can be 1 difficult for consumers to quickly and efficiently obtain the specific knowledge they require. Additionally, there is a general lack of data collected on online learning, which renders the recommendation effect of music course resources insufficient. In this study, we use technologies connected to the knowledge graph in the field of online education in order to create a system capable of recommending acceptable educational materials for use in professional music classes. In order to construct a recommendation model using multi-task feature learning, knowledge graphs are embedded within tasks, and high-order connections between latent features and entities are constructed across tasks using cross-compression units. It is possible to achieve success by recommending relevant course materials for individual students based on their requirements, interests and present skill levels. In terms of its ability to generate suggestions, the proposed knowledge spectrogram-based teaching resource recommendation system for professional music courses outperforms four baseline models on a number of publicly available datasets. This method has some practical utility in the domain of course resource suggestion, and its training time is less than that of the comparison model.

In digital platforms, abnormal events involve multiple data sources and complex information types, and the difficulty of tracking them increases due to the similarity and interaction between components, operations, and user behavior. Therefore, in order to achieve precise tracking and efficient processing of abnormal events, and thereby improve the stability and security of the platform, a digital platform abnormal event tracking method based on a knowledge graph is proposed. First, using data mining and association rule techniques, abnormal event data in the digital platform are effectively collected and integrated. Subsequently, the data are input into a model that integrates residual atrous convolutional neural networks and conditional random fields to achieve precise identification of key entities. On the basis of entity recognition, the correlation between entities is extracted and a knowledge graph architecture for abnormal events is constructed, providing a solid foundation for subsequent deep analysis. Through a visual interface, the knowledge graph of abnormal events can be intuitively displayed, making it easy for users to quickly understand the full picture of the event. At the same time, the knowledge graph subgraph matching algorithm is adopted, combined with flow graph indexing and optimal matching sequence, to achieve accurate tracking and recognition of abnormal events. The experimental results show that this method can effectively track abnormal events in the digital platform. The first detection time is relatively short, with a mishandling time of 8.3s and data duplication of 7.9s. The continuous tracking time is long, with a security vulnerability of 50min. The false alarm rate is low, with the highest being 2.1% for data duplication, and the false miss rate is also low, with the highest being 0.8% for mishandling. This method can identify the number of abnormal events, which helps to understand the stability and health status of the platform. By timely and effectively preventing abnormal events, the frequency of their occurrence can be reduced, and the overall security and stability of the platform can be improved.

With the deep integration of embedded network technology and data analysis technology, the content analysis and dissemination optimization of platform media have ushered in unprecedented technological innovations. The traditional information dissemination model often relies on manually designed feature extraction methods, such as keyword-based matching, TF-IDF and other statistical methods. These methods are limited in efficiency and accuracy when dealing with large-scale, high-dimensional data. Embedded network technology can automatically extract high-level and abstract features from raw text data, significantly improving the accuracy and efficiency of feature extraction. In this context, based on the essence of embedded networks, this paper innovatively integrates and reconstructs the core elements of traditional information dissemination models, and successfully constructs a new knowledge graph model of the current situation of news dissemination. This model fully utilizes the powerful advantages of embedded networks in feature extraction and learning capabilities. It can not only accurately depict the complex dynamic changes that occur over time in news events, but also deeply reveal the potential mechanisms and laws of news dissemination. In the experimental verification phase, the model demonstrated excellent performance. Especially in identifying sudden news feature words, the average recall rate, accuracy and F-score of the model reached about 45%, 35% and 40%, respectively. This result not only indicates a significant improvement in the accuracy of the model in feature word detection, but also fully validates the enormous potential of embedded networks in the field of news communication analysis.

Art design is essentially an expression of visual language, which creates expressive works through the combination and arrangement of elements such as color, shape and texture. However, the organization of elements often depends on subjective experience and intuition, and lacks scientific quantitative analysis. Therefore, this paper proposes a self-organization method of artistic design elements based on visual similarity calculation. Determine the visual similarity function, construct the self-organizing model of art design elements, construct the knowledge map of art design elements based on entities, attributes and relationships, consider differences in data presentation between different data sources, calculate the weights of numerical values, fit the curves of data and art design elements, output the results after fitting, and edge process the data in art design elements. The optimization objective function of art design elements is established. On this basis, the self-organizing optimization scheme is obtained based on visual similarity calculation, and the optimization solution is carried out according to the scheme. After many iterations, the self-organizing method of art design elements is realized. The experimental results show that the relative deviation of this method is small, and the visual similarity measure is over 90%. After applying this method, the entropy value is increased to 7.3, and the effect is better.

What kind of people to train, how to train them and for whom to train are the fundamental issues and eternal themes of education. The rapid advancement of artificial intelligence (AI) technology in recent years, as exemplified by deep learning and knowledge graphs, has opened up new avenues for innovation in education and modifications to teaching strategies. One of the most crucial subjects in the world of education nowadays is how to employ intelligent technology to encourage students to study intelligently. In the age of AI, smart learning is the fundamental meaning of education. The construction of smart learning models is the key and foundation for implementing smart learning, and it is also a bottleneck issue in research in this field. For the problem that it is difficult to characterize the intrinsic mechanism of intelligent learning, we propose the E-GPPE-C model of intelligent learning by utilizing AI technology, which can explain the operation mechanism, elements and characteristics of intelligent learning. Learning environment, learning route, learning assessment, learner image, educational knowledge map, as well as learning community make up the model. The base layer, service layer, support layer, application layer and key layer are all included in the model at the same time. We suggested the implementation approach of E-GPPE-C model from four perspectives: learning path suggestion, learner picture construction, learning community construction, and educational knowledge graph construction. These methods are based on algorithms linked to AI. The findings of this study lay the groundwork for the development of smart learning and the use of AI in the field of education, and provide a reference for subsequent research on smart learning models.

In the current landscape, the Internet of Things (IoT) finds its utility across diverse sectors, including finance, healthcare, and beyond. However, security emerges as the principal obstacle impeding the advancement of IoT. Given the intricate nature of IoT cybersecurity, traditional security protocols fall short when addressing the unique challenges within the IoT domain. Security strategies anchored in the cybersecurity knowledge graph present a robust solution to safeguard IoT ecosystems. The foundation of these strategies lies in the intricate networks of the cybersecurity knowledge graph, with Named Entity Recognition (NER) serving as a crucial initial step in its implementation. Conventional cybersecurity entity recognition approaches IoT grapple with the complexity of cybersecurity entities, characterized by their sophisticated structures and vague meanings. Additionally, these traditional models are inadequate at discerning all the interrelations between cybersecurity entities, rendering their direct application in IoT security impractical. This paper introduces an innovative Cybersecurity Entity Recognition Model, referred to as CERM, designed to pinpoint cybersecurity entities within IoT. CERM employs a hierarchical attention mechanism that proficiently maps the interdependencies among cybersecurity entities. Leveraging these mapped dependencies, CERM precisely identifies IoT cybersecurity entities. Comparative evaluation experiments illustrate CERM’s superior performance over the existing entity recognition models, marking a significant advancement in the field of IoT security.

Firstly, this paper designs the process of personalized recommendation method based on knowledge graph, and constructs user interest model. Second, the traditional personalized recommendation algorithms are studied and their advantages and disadvantages are analyzed. Finally, this paper focuses on the combination of knowledge graph and collaborative filtering recommendation algorithm. They are effective to solve the problem where $K$ value is difficult to be determined in the clustering process of traditional collaborative filtering recommendation algorithm as well as data sparsity and cold start, utilizing the ample semantic relation in knowledge graph. If we use RDF data, which is distributed by the E and P (Exploration and Development) database based on the petroleum E and P, to verify the validity of the algorithm, the result shows that collaborative filtering algorithm based on knowledge graph can build the users’ potential intentions by knowledge graph. It is enlightening to query the information of users. In this way, it expands the mind of users to accomplish the goal of recommendation. In this paper, a collaborative filtering algorithm based on domain knowledge atlas is proposed. By using knowledge graph to effectively classify and describe domain knowledge, the problems are solved including clustering and the cold start in traditional collaborative filtering recommendation algorithm. The better recommendation effect has been achieved.

To improve the recognition ability of clinical named entity recognition (CNER) in a limited number of Chinese electronic medical records, it provides meaningful support for clinical advanced knowledge extraction. In this paper, using CCKS2019 Chinese electronic medical record as an experimental data source, a fusion model enhanced by knowledge graph (KG) is proposed, and the model is applied to specific Chinese CNER tasks. This study consists of three main parts: single-mode model construction and comparison experiment, KG enhancement experiment, and model fusion experiment. The model has achieved good performance in CNER from the results. The accuracy rate, recall rate, and F1 value are 83.825%, 84.705%, and 84.263%, respectively, which is the global optimal, which proves the effectiveness of the model. This provides a good help for further research of medical information.

The embedding of Knowledge Graphs (KGs) in hyperbolic space has recently received great attention in the field of deep learning because it can provide more accurate and concise representations of hierarchical structures compared to Euclidean spaces and complex spaces. Although hyperbolic space embeddings have shown significant improvements over Euclidean spaces and complex space embeddings in handling the task of KG embedding, they still face challenges related to the uneven distribution and insufficient alignment of high-dimensional sparse data. To address this issue, we propose the CONHyperKGE model, which leverages contrastive learning to optimize the embedding distribution in hyperbolic space. This approach enables better capture of hierarchical structures, improved handling of symmetry, and enhanced treatment of sparse matrices. Our proposed method is evaluated on four standard KG Embedding (KGE) datasets: WN18RR, FB15k-237, Kinship, and UMLS. After extensive experimental verification, our method has improved its performance on all four datasets. Notably, on the low-dimensional Kinship dataset, our method achieves an average Mean Reciprocal Rank (MRR) improvement of 2% over the original method, while on the high-dimensional WN18RR dataset, an average MRR improvement of 1% is observed compared to the original method.

The advent of the Internet has led to the emergence of multi-source heterogeneous knowledge graphs, which have become a crucial means of storing and disseminating knowledge. Node importance estimation is a technique that is employed extensively in a number of fields, including recommender systems, intelligent search and resource allocation. This study introduces a Multi-perspective attention mechanism Fusion Algorithm for the mapping of multi-perspective features of knowledge graphs to Node Importance Estimation (MFA-NIE). First, structural embedding features, relational predicate features, and attribute features (both textual and quantitative) are established for the nodes. Subsequently, an enhanced attention mechanism is employed to extract, compress, and fuse these features. The fused hidden layer vector is employed in the design of a key-based attention mechanism, which enables the propagation of messages from neighboring nodes to the source node. This process results in the iterative updating of the source node’s hidden features. Finally, TOPSIS centrality, based on the topology of the source node, is employed to dynamically adjust the mapping between the fused features and node importance. Experiments were conducted on real-world, large-scale, multi-source, heterogeneous knowledge graphs, comparing the MFA-NIE algorithm with traditional and advanced baseline algorithms, including PR, PPR, GENI, RGTN, CLINE, MCRL, and others. The results demonstrate that the MFA-NIE algorithm significantly improves effectiveness and accuracy, showcasing its superiority, versatility, and practical application value.

This paper presents an in-depth study and analysis of online education course recommendations through a knowledge graph combined with reinforcement learning, and proposes a deep learning-based joint extraction method of course knowledge entities and relations in the education domain. This joint extraction method can extract both course knowledge entities and their relationships from the unstructured text of online courses, thus alleviating the problem of error propagation. On the other hand, since some parameters in the joint model can be shared by the entity identification task and the relationship classification task, this helps the model to capture the interaction between the two subtasks. Similar courses are judged based on the extracted course knowledge points, while course knowledge chains are generated based on the relationships between course knowledge points. In terms of user learning behavior, by analyzing user online learning behavior data, this paper uses five variables, namely the number of learning hours, the number of discussions, the number of visits, the number of task points completed, and the number of learning courses, to judge and cluster user similarity using an information entropy-based learner behavior weight assignment method. Based on the course knowledge map, this paper firstly constructs a learner model with four dimensions of basic learner profile, cognitive level, learning style, and historical learning records. Secondly, it predicts the target knowledge points of learners based on their learning data using the Armorial algorithm and maps them in the knowledge map, then uses natural language processing related techniques to find the conceptual similarity between knowledge points and proposes a deep recommendation strategy based on the knowledge graph correlations. At the same time, the recommended courses based on learners’ behavioral data are more relevant and accurate, which greatly improves learners’ efficiency and satisfaction in the learning process.

The financial risk warning methods for enterprises have always been a practical concern. In digital society, the computational intelligence has brought more spirit to this demand. This paper first introduces the current situation of the development of Knowledge graph technology, describes the deep learning fusion method based on Knowledge graph, and expresses the feasibility of this study. Then, according to the requirements of Knowledge graph, it completes the method fusion of core data training and extraction, and completes the adaptive deep learning design for the Beautiful SCOP database, and establishes a STDE-FG financial risk early warning model. Through empirical analysis, the shortcomings of this model were identified, and a comparison of optimized and optimized results was completed. Two aspects of phenomenon can be found from experimental results. For one thing, the accuracy of the unoptimized STDE-FG early warning model has been improved by 37.5–55.3% compared to traditional prediction models, but the prediction value during legal person changes has a greater error than traditional prediction values. For another, the optimized STDE-FG early warning model has also improved its accuracy in predicting new investments and equity changes, with improvements of 17–32% and 16–28%, respectively, with significant changes. This model will have a positive impact on improving enterprise risk management capabilities and reducing financial risk costs.

Financial fraud detection has been an urgent technical demand in cyberspace. It highly relies on clear extraction and deep representation toward complex relationships inside financial social networks. As consequence, this study combines both knowledge graph and deep learning to deal with such issue. Thus, an intelligent financial fraud detection model based on knowledge graph guidance and deep neural network is proposed in this paper. First, a new knowledge graph based on financially related systems is constructed, which includes multiple entities and relationships. Then, an adversarial learning-based neural network structure is formulated to extract financial attributes. Finally, the detection results can be output according to the extracted factors. Empirically, the proposal is implemented on a real-world dataset for performance evaluation. The experimental results show that it has higher accuracy and effectiveness compared to traditional fraud detection methods. The proposed detection model can not only identify known fraudulent behaviors, but also predict potential fraud patterns based on consumer habits, thereby improving the security and reliability of financial transactions. It can also update the knowledge graph in real-time, enabling it to cope with emerging fraud methods and variants.

With the increasing number of financial transactions, financial fraud has become increasingly serious for financial institutions and the public. The core idea of this model is to integrate multiple neural network structures and utilize their respective advantages to improve the performance of fraud detection. Firstly, we employed the convolutional neural network with interpretable blocks (CNNIB) convolutional neural network (CNN) to extract key features from the data to capture patterns and patterns in fraud cases. Secondly, we introduced the autoencoder generative adversarial network (AE-GAN) adversarial network to perform feature analysis on sequence data to capture temporal features in transaction sequences. Finally, we used differential detection for classification to determine whether transactions were fraudulent. An independent detection module was established to accelerate the recognition of financial fraud, and parameter indicators were optimized. Finally, a hybrid neural network model was established. The experimental results indicate that our model has achieved significant results in quickly detecting financial fraud; compared with traditional single neural network models, hybrid neural network models have significant improvements in accuracy and efficiency. In addition, we conducted in-depth analysis of the model and revealed its performance stability under different training set sizes and data distributions. Our research findings provide an effective tool for financial institutions to quickly identify financial fraud.

Understanding user’s search intent in vertical websites like IT service crowdsourcing platform relies heavily on domain knowledge. Meanwhile, searching for services accurately on crowdsourcing platforms is still difficult, because these platforms do not contain enough information to support high-performance search. To solve these problems, we build and leverage a knowledge graph named ITServiceKG to enhance search performance of crowdsourcing IT services. The main ideas are to (1) build an IT service knowledge graph from Wikipedia, Baidupedia, CN-DBpedia, StuQ and data in IT service crowdsourcing platforms, (2) use properties and relations of entities in the knowledge graph to expand user query and service information, and (3) apply a listwise approach with relevance features and topic features to re-rank the search results. The results of our experiments indicate that our approach outperforms the traditional search approaches.

Question Answering systems over Knowledge Graphs (KG) answer natural language questions using facts contained in a knowledge graph, and Simple Question Answering over Knowledge Graphs (KG-SimpleQA) means that the question can be answered by a single fact. Entity linking, which is a core component of KG-SimpleQA, detects the entities mentioned in questions, and links them to the actual entity in KG. However, traditional methods ignore some information of entities, especially entity types, which leads to the emergence of entity ambiguity problem. Besides, entity linking suffers from out-of-vocabulary (OOV) problem due to the limitation of pre-trained word embeddings. To address these problems, we encode questions in a novel way and encode the features contained in the entities in a multilevel way. To evaluate the enhancement of the whole KG-SimpleQA brought by our improved entity linking, we utilize a relatively simple approach for relation prediction. Besides, to reduce the impact of losing the feature during the encoding procedure, we utilize a ranking algorithm to re-rank (entity, relation) pairs. According to the experimental results, our method for entity linking achieves an accuracy of 81.8% that beats the state-of-the-art methods, and our improved entity linking brings a boost of 5.6% for the whole KG-SimpleQA.