Knowledge Graph Construction Research Articles

Construction and application of knowledge graph for construction accidents based on deep learning

PurposeLearning from safety accidents and sharing safety knowledge has become an important part of accident prevention and improving construction safety management. Considering the difficulty of reusing unstructured data in the construction industry, the knowledge in it is difficult to be used directly for safety analysis. The purpose of this paper is to explore the construction of construction safety knowledge representation model and safety accident graph through deep learning methods, extract construction safety knowledge entities through BERT-BiLSTM-CRF model and propose a data management model of data–knowledge–services.Design/methodology/approachThe ontology model of knowledge representation of construction safety accidents is constructed by integrating entity relation and logic evolution. Then, the database of safety incidents in the architecture, engineering and construction (AEC) industry is established based on the collected construction safety incident reports and related dispute cases. The construction method of construction safety accident knowledge graph is studied, and the precision of BERT-BiLSTM-CRF algorithm in information extraction is verified through comparative experiments. Finally, a safety accident report is used as an example to construct the AEC domain construction safety accident knowledge graph (AEC-KG), which provides visual query knowledge service and verifies the operability of knowledge management.FindingsThe experimental results show that the combined BERT-BiLSTM-CRF algorithm has a precision of 84.52%, a recall of 92.35%, and an F1 value of 88.26% in named entity recognition from the AEC domain database. The construction safety knowledge representation model and safety incident knowledge graph realize knowledge visualization.Originality/valueThe proposed framework provides a new knowledge management approach to improve the safety management of practitioners and also enriches the application scenarios of knowledge graph. On the one hand, it innovatively proposes a data application method and knowledge management method of safety accident report that integrates entity relationship and matter evolution logic. On the other hand, the legal adjudication dimension is innovatively added to the knowledge graph in the construction safety field as the basis for the postincident disposal measures of safety accidents, which provides reference for safety managers' decision-making in all aspects.

Knowledge Graph Construction for Social Customer Advocacy in Online Customer Engagement

The rise of online social networks has revolutionized the way businesses and consumers interact, creating new opportunities for customer word-of-mouth (WoM) and brand advocacy. Understanding and managing customer advocacy in the online realm has become crucial for businesses aiming to cultivate a positive brand image and engage with their target audience effectively. In this study, we propose a framework that leverages the pre-trained XLNet- (bi-directional long-short term memory) BiLSTM- conditional random field (CRF) architecture to construct a Knowledge Graph (KG) for social customer advocacy in online customer engagement (CE). The XLNet-BiLSTM-CRF model combines the strengths of XLNet, a powerful language representation model, with BiLSTM-CRF, a sequence labeling model commonly used in natural language processing tasks. This architecture effectively captures contextual information and sequential dependencies in CE data. The XLNet-BiLSTM-CRF model is evaluated against several baseline architectures, including variations of BERT integrated with other models, to compare their performance in identifying brand advocates and capturing CE dynamics. Additionally, an ablation study is conducted to analyze the contributions of different components in the model. The evaluation metrics, including accuracy, precision, recall, and F1 score, demonstrate that the XLNet-BiLSTM-CRF model outperforms the baseline architectures, indicating its superior ability to accurately identify brand advocates and label customer advocacy entities. The findings highlight the significance of leveraging pre-trained contextual embeddings, sequential modeling, and sequence labeling techniques in constructing effective models for constructing a KG for customer advocacy in online engagement. The proposed framework contributes to the understanding and management of customer advocacy by facilitating meaningful customer-brand interactions and fostering brand loyalty.

Research on named entity recognition of Traditional Chinese Medicine chest discomfort cases incorporating domain vocabulary features

Objective:To promote research on knowledge extraction and knowledge graph construction of chest discomfort medical cases in Traditional Chinese Medicine (TCM), this paper focuses on their named entity recognition (NER). The recognition task includes six entity types: “syndrome”, “symptom”, “etiology and pathogenesis”, “treatment method”, “medication”, and “prescription”. Methods:We annotated data in a BIO (B-begin, I-inside, O-outside) manner. For the characteristics of medical case texts, we proposed a custom dictionary method that can be dynamically updated for word segmentation. To compare the effect of the method on the experimental results, we applied the method in the BiLSTM-CRF model and IDCNN-CRF model, respectively. Results:The models using custom dictionaries (BiLSTM-CRF-Loaded and IDCNN-CRF-Loaded) outperformed the models without custom dictionaries (BiLSTM-CRF and IDCNN-CRF) in accuracy, precision, recall, and F1 score. The BiLSTM-CRF-Loaded model yielded F1 scores of 92.59% and 93.23% on the test set and validation set, respectively, surpassing the BERT-BiLSTM-CRF model by 3.59% and 4.87%. Furthermore, when analyzing the results for the six entity categories separately, we found that the use of custom dictionaries has a marked impact, with the categories of “etiology and pathogenesis” and “syndrome” demonstrating the most noticeable improvements. By comparing the F1 scores, we observed that the entity category “medication” yielded the highest performance, reaching F1 scores of 96.04% and 96.48% on the test set and validation set, respectively. Conclusion:We propose a word segmentation method based on a dynamically updated custom dictionary. The method is combined with the BILSTM-CRF and the IDCNN-CRF models, which enhances the model to recognize domain-specific terms and new entities. It can be widely applied in dealing with complex text structures and texts containing domain-specific terms.

A large-scale evaluation of NLP-derived chemical-gene/protein relationships from the scientific literature: Implications for knowledge graph construction.

One area of active research is the use of natural language processing (NLP) to mine biomedical texts for sets of triples (subject-predicate-object) for knowledge graph (KG) construction. While statistical methods to mine co-occurrences of entities within sentences are relatively robust, accurate relationship extraction is more challenging. Herein, we evaluate the Global Network of Biomedical Relationships (GNBR), a dataset that uses distributional semantics to model relationships between biomedical entities. The focus of our paper is an evaluation of a subset of the GNBR data; the relationships between chemicals and genes/proteins. We use Evotec's structured 'Nexus' database of >2.76M chemical-protein interactions as a ground truth to compare with GNBRs relationships and find a micro-averaged precision-recall area under the curve (AUC) of 0.50 and a micro-averaged receiver operating characteristic (ROC) curve AUC of 0.71 across the relationship classes 'inhibits', 'binding', 'agonism' and 'antagonism', when a comparison is made on a sentence-by-sentence basis. We conclude that, even though these micro-average scores are modest, using a high threshold on certain relationship classes like 'inhibits' could yield high fidelity triples that are not reported in structured datasets. We discuss how different methods of processing GNBR data, and the factuality of triples could affect the accuracy of NLP data incorporated into knowledge graphs. We provide a GNBR-Nexus(ChEMBL-subset) merged datafile that contains over 20,000 sentences where a protein/gene-chemical co-occur and includes both the GNBR relationship scores as well as the ChEMBL (manually curated) relationships (e.g., 'agonist', 'inhibitor') -this can be accessed at https://doi.org/10.5281/zenodo.8136752. We envisage this being used to aid curation efforts by the drug discovery community.

BioREx: Improving biomedical relation extraction by leveraging heterogeneous datasets

Biomedical relation extraction (RE) is the task of automatically identifying and characterizing relations between biomedical concepts from free text. RE is a central task in biomedical natural language processing (NLP) research and plays a critical role in many downstream applications, such as literature-based discovery and knowledge graph construction. State-of-the-art methods were used primarily to train machine learning models on individual RE datasets, such as protein–protein interaction and chemical-induced disease relation. Manual dataset annotation, however, is highly expensive and time-consuming, as it requires domain knowledge. Existing RE datasets are usually domain-specific or small, which limits the development of generalized and high-performing RE models. In this work, we present a novel framework for systematically addressing the data heterogeneity of individual datasets and combining them into a large dataset. Based on the framework and dataset, we report on BioREx, a data-centric approach for extracting relations. Our evaluation shows that BioREx achieves significantly higher performance than the benchmark system trained on the individual dataset, setting a new SOTA from 74.4% to 79.6% in F-1 measure on the recently released BioRED corpus. We further demonstrate that the combined dataset can improve performance for five different RE tasks. In addition, we show that on average BioREx compares favorably to current best-performing methods such as transfer learning and multi-task learning. Finally, we demonstrate BioREx’s robustness and generalizability in two independent RE tasks not previously seen in training data: drug-drug N-ary combination and document-level gene-disease RE. The integrated dataset and optimized method have been packaged as a stand-alone tool available at https://github.com/ncbi/BioREx.

ERNIE-based Named Entity Recognition Method for Traffic Accident Cases

Traffic accident case named entity recognition, which helps mine key information in traffic accident texts, plays a vital role in downstream tasks such as the construction of knowledge graphs in road traffic and intelligent policing. In this paper, we construct a named entity recognition model based on the EDE (Entity Data Enhancement)-ERNIE-Bidirectional Gated Recurrent Unit Network (BiGRU)-Conditional Random Field (CRF) to address the current situation of low traffic accident case data and poor recognition of long-text entities. First, the amount of accident case data is enhanced using the entity random substitution method. Next, the text data of traffic accident cases are characterized as a dynamic word vector using the ERNIE pretraining model. Then, the BiGRU network learns the long-distance dependency relationship in the text to enhance the effect of the model on long-text entity recognition. Finally, the result sequence is constrained by the CRF layer to realize the named entity recognition model. The experimental part uses data related to real traffic accident cases in a domestic area. The data enhancement method increases the data volume three times compared to the original data volume. Experimental results show that the EDE-ERNIE-BiGRU-CRF model achieves better F1 values, recall and precision achieved better performance than the entity recognition methods of BERT-BiGRU-CRF, ERNIE-BiGRU-CRF, ERNIE-BiLSTM-CRF, ERNIE-CRF, ERNIE, BiGRU-CRF, ROBERTA-wwm-ext-BiGRU-CRF and verify its effectiveness for entity recognition in traffic accident cases.

Construction of Migraine Knowledge Graph Based on Diagnosis and Treatment Guidelines of Integrative Medicine

AbstractOur objective was to transform the text data in migraine diagnosis and treatment guidelines into a visualized knowledge graph by using knowledge graph technology, visually display the clinical diagnosis and treatment process, and provide assistance for the standardization of diagnosis and treatment of migraine with integrative medicine.Manual extraction, knowledge fusion, and standardization were performed on the text data in the migraine diagnosis and treatment guidelines. Combined with the clinical diagnosis and treatment process, the data of Chinese and Western medicine diagnosis and treatment of migraine were visualized and stored through the Neo4j graph database.A knowledge graph of Chinese and Western medicine diagnosis and treatment of migraine including 616 entities and 615 entity relationships was constructed, which realized the visual display of the diagnosis and treatment process of integrative medicine for migraine including examination, diagnosis, and treatment.Based on the guidelines for the diagnosis and treatment of migraine, this study visualized the diagnosis and treatment process of integrative medicine for migraine through knowledge graph technology, which is of great significance for the clinical implementation of relevant guidelines for the diagnosis and treatment and the standardization of integrative medicine diagnosis and treatment for the dominant diseases in Chinese medicine.

Purpose-Driven Evaluation of Operation and Maintenance Efficiency and Safety Based on DIKWP

In large-scale public security equipment projects, long-term equipment operation often leads to equipment failures and other problems, so it is particularly important to choose the appropriate operation and maintenance (O&M) scheme based on the content of the equipment work orders. However, there are a variety of equipment models in the work orders; not only is the data complex, but also due to the long project cycle, there are often problems such as loss of content, which bring great challenges to the O&M work. This paper defines these problems as “3-No problems”: inconsistency, inaccuracy, and incompleteness. In this paper, an improved DIKWP model is proposed and combined with a random forest classifier to construct data graphs, information graphs, knowledge graphs, and wisdom graphs. Through the above model, the 3-No problem in equipment work orders can be solved, and the importance of each equipment model can be obtained. Eventually, combined with the purpose graph, the selection of models, the bid score calculation, and the selection of O&M schemes are carried out based on the obtained conclusion in a purpose-driven manner to achieve the evaluation of O&M efficiency and safety. Finally, an example is assumed to illustrate the application of the method in actual projects, which provides a certain reference value for the selection of an O&M scheme for large-scale equipment projects.

FGSI: distant supervision for relation extraction method based on fine-grained semantic information

Relation extraction is one of the important steps in building a knowledge graph. Its main objective is to extract semantic relationships from identified entity pairs in sentences, playing a crucial role in semantic understanding and knowledge graph construction. Remote supervised relation extraction aligns knowledge bases with natural language texts and generates labeled data, which alleviates the burden of manually annotating datasets. However, the labeled corpus obtained from remote supervision contains a large amount of noisy data, which greatly affects the training of relation extraction models. In this paper, we propose the hypothesis that key semantic information within the sentence plays a crucial role in entity relation extraction in the task of remote supervised relation extraction. Based on this hypothesis, we divide the sentence into three segments by splitting it according to the positions of entities, starting from within the sentence. Then, using intra-sentence attention mechanisms, we identify fine-grained semantic features within the sentence to reduce the interference of irrelevant noise information. We also improved the intra-bag attention mechanism by setting a threshold gate to filter out low-relevant noisy sentences, minimizing the impact of noise on the relation extraction model, and making full use of available positive semantic information. Experimental results show that the proposed relation extraction model in this paper achieves improvements in precision-recall curve, P@N value, and AUC value compared to existing methods, demonstrating the effectiveness of this model.

Cybersecurity knowledge graphs construction and quality assessment

Cyber-attack activities are complex and ever-changing, posing severe challenges to cybersecurity personnel. Introducing knowledge graphs into the field of cybersecurity helps depict the intricate cybersecurity landscape and provides technical support for threat identification and situational awareness. However, during the process of constructing knowledge graphs, inevitable noise and conflicts may be introduced, leading to misleading inferences and decisions. This paper aims to address the issues of constructing and assessing the quality of cybersecurity knowledge graphs. We manually constructed a dataset of cybersecurity knowledge graphs (CS13K) and expanded the existing cybersecurity ontology, building a more versatile ontology applicable to existing data features. Building upon this, we utilized Neo4j to construct the cybersecurity knowledge graph. Furthermore, we propose an AttTucker model, based on Transformer, for assessing the quality of knowledge graphs. By employing numerous self-attention heads, this model captures latent information among entities and relations. While reducing the dimensionality of knowledge embeddings, the model achieves evaluation results comparable to high-dimensional embeddings. Finally, we incorporate the path-level information between entities in the knowledge graph into the evaluation of knowledge graph quality based on the AttTucker model. Experimental analysis on both generic datasets and cybersecurity datasets demonstrates that our model significantly improves F1 value and accuracy in knowledge graph quality assessment tasks, outperforming other models.

A BERT-Span model for Chinese named entity recognition in rehabilitation medicine.

Due to various factors such as the increasing aging of the population and the upgrading of people's health consumption needs, the demand group for rehabilitation medical care is expanding. Currently, China's rehabilitation medical care encounters several challenges, such as inadequate awareness and a scarcity of skilled professionals. Enhancing public awareness about rehabilitation and improving the quality of rehabilitation services are particularly crucial. Named entity recognition is an essential first step in information processing as it enables the automated extraction of rehabilitation medical entities. These entities play a crucial role in subsequent tasks, including information decision systems and the construction of medical knowledge graphs. In order to accomplish this objective, we construct the BERT-Span model to complete the Chinese rehabilitation medicine named entity recognition task. First, we collect rehabilitation information from multiple sources to build a corpus in the field of rehabilitation medicine, and fine-tune Bidirectional Encoder Representation from Transformers (BERT) with the rehabilitation medicine corpus. For the rehabilitation medicine corpus, we use BERT to extract the feature vectors of rehabilitation medicine entities in the text, and use the span model to complete the annotation of rehabilitation medicine entities. Compared to existing baseline models, our model achieved the highest F1 value for the named entity recognition task in the rehabilitation medicine corpus. The experimental results demonstrate that our method outperforms in recognizing both long medical entities and nested medical entities in rehabilitation medical texts. The BERT-Span model can effectively identify and extract entity knowledge in the field of rehabilitation medicine in China, which supports the construction of the knowledge graph of rehabilitation medicine and the development of the decision-making system of rehabilitation medicine.

SecTKG: A Knowledge Graph for Open-Source Security Tools

As the complexity of cyberattacks continues to increase, multistage combination attacks have become the primary method of attack. Attackers plan and organize a series of attack steps, using various attack tools to achieve specific goals. Extracting knowledge about these tools is of great significance for both defense and tracing of attacks. We have noticed that there is a wealth of security tool-related knowledge within the open-source community, but research in this area is limited. It is challenging to achieve large-scale automated security tool information extraction. To address this, we propose automated knowledge graph construction architecture, named SecTKG, for open-source security tools. Our approach involves designing a security tool ontology model to describe tools, users, and relationships, which guides the extraction of security tool knowledge. In addition, we develop advanced entity recognition and classification methods, ensuring efficient and accurate knowledge extraction. As far as we know, this work is the first to construct the large-scale security tool knowledge graph, containing 4 million entities and 10 million relationships. Furthermore, we investigate the tendencies and particularities of security tools based on the SecTKG and developed a security tool influence-measuring application. The research fills a gap in the field of automated security tools’ knowledge extraction and provides a foundation for future research and practical applications.

MHlinker: Research on a Joint Extraction Method of Fault Entity Relationship for Mine Hoist

Triplet extraction is the key technology to automatically construct knowledge graphs. Extracting the triplet of mechanical equipment fault relationships is of great significance in constructing the fault diagnosis of a mine hoist. The pipeline triple extraction method will bring problems such as error accumulation and information redundancy. The existing joint learning methods cannot be applied to fault texts with more overlapping relationships, ignoring the particularity of professional knowledge in the field of complex mechanical equipment faults. Therefore, based on the Chinese pre-trained language model BERT Whole Word Masking (BERT-wwm), this paper proposes a joint entity and relation extraction model MHlinker (Mine Hoist linker, MHlinker) for the mine hoist fault field. This method uses BERT-wwm as the underlying encoder. In the entity recognition stage, the classification matrix is constructed using the multi-head extraction paradigm, which effectively solves the problem of entity nesting. The results show that this method enhances the model’s ability to extract fault relationships as a whole. When the small-scale manually labeled mine hoist fault text data set is tested, the extraction effect of entities and relationships is significantly improved compared with several baseline models.

Retracted: Information Extraction and Knowledge Graph Construction for Enterprises in China’s Free Trade Zone

Retracted: Information Extraction and Knowledge Graph Construction for Enterprises in China’s Free Trade Zone

Impacts of three approaches on collaborative knowledge building, group performance, behavioural engagement, and socially shared regulation in online collaborative learning

AbstractBackgroundOnline collaborative learning has been widely adopted in the field of education. However, learners often find it difficult to engage in collaboratively building knowledge and jointly regulating online collaborative learning.ObjectivesThe study compared the impacts of the three learning approaches on collaborative knowledge building, group performance, socially shared regulation, behavioural engagement, and cognitive load in an online collaborative learning context. The first is the automatic construction of knowledge graphs (CKG) approach, the second is the automatic analysis of topic distribution (ATD) approach, and the third one is the traditional online collaborative learning (OCL) approach without any analytic feedback.MethodsA total of 144 college students participated in a quasi‐experimental study, where 48 students learned with the CKG approach, 48 students used the ATD approach, and the remaining 48 students adopted the OCL approach.Results and ConclusionsThe findings revealed that the CKG approach could encourage collaborative knowledge building, socially shared regulation, and behavioural engagement in building knowledge better than the ATD and OCL approaches. Both the CKG and ATD approaches could better improve group performance than the OCL approach. Furthermore, the CKG approach did not increase learners' cognitive load, but the ATD approach did.ImplicationsThis study has theoretical and practical implications for utilising learning analytics in online collaborative learning. Furthermore, deep neural network models are powerful for constructing knowledge graphs and analysing topic distribution.

TCFLTformer: TextCNN-Flat-Lattice Transformer for Entity Recognition of Air Traffic Management Cyber Threat Knowledge Graphs

With the development of the air traffic management system (ATM), the cyber threat for ATM is becoming more and more serious. The recognition of ATM cyber threat entities is an important task, which can help ATM security experts quickly and accurately recognize threat entities, providing data support for the later construction of knowledge graphs, and ensuring the security and stability of ATM. The entity recognition methods are mainly based on traditional machine learning in a period of time; however, the methods have problems such as low recall and low accuracy. Moreover, in recent years, the rise of deep learning technology has provided new ideas and methods for ATM cyber threat entity recognition. Alternatively, in the convolutional neural network (CNN), the convolution operation can efficiently extract the local features, while it is difficult to capture the global representation information. In Transformer, the attention mechanism can capture feature dependencies over long distances, while it usually ignores the details of local features. To solve these problems, a TextCNN-Flat-Lattice Transformer (TCFLTformer) with CNN-Transformer hybrid architecture is proposed for ATM cyber threat entity recognition, in which a relative positional embedding (RPE) is designed to encode position text content information, and a multibranch prediction head (MBPH) is utilized to enhance deep feature learning. TCFLTformer first uses CNN to carry out convolution and pooling operations on the text to extract local features and then uses a Flat-Lattice Transformer to learn temporal and relative positional characteristics of the text to obtain the final annotation results. Experimental results show that this method has achieved better results in the task of ATM cyber threat entity recognition, and it has high practical value and theoretical contribution. Besides, the proposed method expands the research field of ATM cyber threat entity recognition, and the research results can also provide references for other text classification and sequence annotation tasks.

HKG: A Novel Approach for Low Resource Indic Languages to Automatic Knowledge Graph Construction

Knowledge graph (KG), a visual representation of text data as a semantic network, holds enormous promise for the development of more intelligent robots. It leads to significant potential solutions for many tasks like question answering, recommendation, and information retrieval. However, this area is confined to using English text only. Since low-resource languages are now being used in the world of AI, it is necessary to develop a semantic network for them as well. In this research work, the authors provide state-of-the-art techniques for automatic knowledge graph construction for the Hindi language, which is still unexplored in ontology. Constructing a knowledge graph faces several hurdles and obstacles in the linguistic domain, primarily when it deals with the Hindi language. With an emphasis on the Indian perspective, this research intends to introduce a novel approach ‘HKG’ for knowledge graph construction framework for Hindi. It also implements the LSTM model to evaluate the accuracy of newly constructed knowledge graphs and compute different evaluation metrics such as accuracy and F1-score. This knowledge graph evaluates the accuracy of 87.50 using Doc2Vec word embedding with a train-test split of 7:3.

Research on the Construction and Application of Knowledge Graph of Digital Resources in Vocational Colleges

<p>With the development of digital education, colleges and universities are facing challenges in managing and utilizing digital resources. As an effective way of knowledge organization and representation, Knowledge graph can transform digital resources into structured entities, attributes and relationship forms, and provide personalized learning support and resource recommendation. By analyzing the characteristics, construction status and existing problems of digital resources in vocational colleges, this paper puts forward the overall plan and methods of digital resources knowledge graph construction, including data collection and sorting, knowledge graph construction, verification and optimization, and gives the general process design of knowledge graph construction; Then, this paper discusses the typical application scenarios of digital resources knowledge graph in vocational colleges, such as learning resource recommendation, path planning, teaching assistance and resource sharing; Finally, the challenges in this field, including data quality, knowledge graph updating and maintenance, privacy and security, are discussed, and the future trends and research directions are prospected. The research results are of great significance for promoting the informatization and intelligent development of vocational college education.</p> <p> </p>

Research on the Construction and Application of Knowledge Graph in the Ceramic Field Based on Natural Language Processing

There are problems of knowledge deficiency and effective unified expression of knowledge in the process of relevant knowledge data acquired by workers in the ceramic domain. In this study, the authors designed relevant experiments to construct ceramic field knowledge graphs to solve these problems. In the experiments of named entity recognition and relationship recognition, the authors compared the performance of several models in OwnThink and ceramics field datasets. The experimental results showed that the BiLSTM-CRF model is the best for named entity recognition and the TextCNN model is the best for relationship recognition in ceramics field datasets. Therefore, the first used the BiLSTM-CRF model to complete the naming entity recognition and then combined with the TextCNN model to complete the relationship recognition to construct the ceramic field knowledge graph. Then, they applied the constructed graph to the ceramic knowledge Q&A service to provide accurate data retrieval service for ceramic domain workers.

Construction and application of knowledge graph for grid dispatch fault handling based on pre-trained model

With the construction of new power systems, the power grid has become extremely large, with an increasing proportion of new energy and AC/DC hybrid connections. The dynamic characteristics and fault patterns of the power grid are complex; additionally, power grid control is difficult, operation risks are high, and the task of fault handling is arduous. Traditional power-grid fault handling relies primarily on human experience. The difference in and lack of knowledge reserve of control personnel restrict the accuracy and timeliness of fault handling. Therefore, this mode of operation is no longer suitable for the requirements of new systems. Based on the multi-source heterogeneous data of power grid dispatch, this paper proposes a joint entity–relationship extraction method for power-grid dispatch fault processing based on a pre-trained model, constructs a knowledge graph of power-grid dispatch fault processing and designs, and develops a fault-processing auxiliary decision-making system based on the knowledge graph. It was applied to study a provincial dispatch control center, and it effectively improved the accident processing ability and intelligent level of accident management and control of the power grid.