Knowledge Graph Construction Research Articles

The Construction of Knowledge Graphs in the Aviation Assembly Domain Based on a Joint Knowledge Extraction Model

The aviation assembly domain, which is a complex system, involves the multi-dimensional information of parts, processes, tools, plants and operation projects. In order to assist the knowledge management from natural language text in the aircraft manufacturing process, this paper proposes the corresponding ontology scheme and the joint knowledge extraction model, which is necessary for construct the knowledge graph in the aviation assembly domain. The model is able to automated end-to-end construct knowledge graph. The proposed model, which is based on reinforcement learning approach and a novel labeling scheme, takes the constraint relationships between entities and relations as an important identification basis. The model does not rely on manual feature setting, while it greatly reduces the training cost. The proposed joint knowledge extraction model was testified from the practical scenarios of the general assembly and component assembly. The experimental results showed that the proposed model showed an excellent performance in the aviation assembly domain, with the F1-score of 89.71% for entities, the F1-score of 91.27% for relations, and the overall average F1-score of 82.41%. Based on the superior performance of the model, the knowledge graph of the general assembly and component assembly, which included 1, 308 pairs of triples composed of five kinds of entities and three kinds of relations, was further constructed in the aviation assembly domain.

Retracted: Knowledge Graph Construction and Application of Power Grid Equipment

Retracted: Knowledge Graph Construction and Application of Power Grid Equipment

Construction and application of Chinese breast cancer knowledge graph based on multi-source heterogeneous data.

The knowledge graph is a critical resource for medical intelligence. The general medical knowledge graph tries to include all diseases and contains much medical knowledge. However, it is challenging to review all the triples manually. Therefore the quality of the knowledge graph can not support intelligence medical applications. Breast cancer is one of the highest incidences of cancer at present. It is urgent to improve the efficiency of breast cancer diagnosis and treatment through artificial intelligence technology and improve the postoperative health status of breast cancer patients. This paper proposes a framework to construct a breast cancer knowledge graph from heterogeneous data resources in response to this demand. Specifically, this paper extracts knowledge triple from clinical guidelines, medical encyclopedias and electronic medical records. Furthermore, the triples from different data resources are fused to build a breast cancer knowledge graph (BCKG). Experimental results demonstrate that BCKG can support knowledge-based question answering, breast cancer postoperative follow-up and healthcare, and improve the quality and efficiency of breast cancer diagnosis, treatment and management.

Construction and Application of Knowledge Graph in Virtual Teaching and Research Section

Construction and Application of Knowledge Graph in Virtual Teaching and Research Section

Synthesizing Event-Centric Knowledge Graphs of Daily Activities Using Virtual Space

Artificial intelligence (AI) is expected to be embodied in software agents, robots, and cyber-physical systems that can understand the various contextual information of daily life in the home environment to support human behavior and decision making in various situations. Scene graph and knowledge graph (KG) construction technologies have attracted much attention for knowledge-based embodied question answering meeting this expectation. However, collecting and managing real data on daily activities under various experimental conditions in a physical space are quite costly, and developing AI that understands the intentions and contexts is difficult. In the future, data from both virtual spaces, where conditions can be easily modified, and physical spaces, where conditions are difficult to change, are expected to be combined to analyze daily living activities. However, studies on the KG construction of daily activities using virtual space and their application have yet to progress. The potential and challenges must still be clarified to facilitate AI development for human daily life. Thus, this study proposes the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">VirtualHome2KG</i> framework to generate synthetic KGs of daily life activities in virtual space. This framework augments both the synthetic video data of daily activities and the contextual semantic data corresponding to the video contents based on the proposed event-centric schema and virtual space simulation results. Therefore, context-aware data can be analyzed, and various applications that have conventionally been difficult to develop due to the insufficient availability of relevant data and semantic information can be developed. We also demonstrate herein the utility and potential of the proposed VirtualHome2KG framework through several use cases, including the analysis of daily activities by querying, embedding, and clustering, and fall risk detection among older adults based on expert knowledge. As a result, we are able to develop a support tool that detects the fall risk with 1.0 precision, 0.6 recall, and 0.75 F1-score and visualize it with an explanation of its rationale. Using the cases explored in this work, we also clarify and classify the challenges that future research on synthetic KG generation systems should resolve in terms of simulation, schema, and human activity. Finally, we discuss the potential solutions for implementing advanced applications to support our daily life.

Knowledge Graph Construction of Chronic Kidney Disease Diagnosis and Treatment with Traditional Chinese Medicine

Background. The purpose of this study is to construct a knowledge graph of chronic kidney disease (CKD) diagnosis and treatment with traditional Chinese medicine (TCM), reorganize its knowledge, and display it. It allows the inheritance, development, and utilization of CKD diagnosis and treatment experiences with TCM in a standard and scientific manner. Methods. First, we constructed a knowledge framework for TCM diagnosis and treatment on the basis of the Chinese Pharmacopoeia, government projected textbook, and the current TCM diagnosis and treatment standards. Then, we collected and sorted the electronic medical records of TCM inpatients, extracting and normalizing the diagnoses, symptoms, syndromes, prescriptions, and other diagnosis and treatment information, creating the knowledge base of TCM diagnosis and treatment for CKD. Finally, we stored TCM diagnosis and treatment CKD knowledge in Neo4j graph database, which refers to the knowledge framework and knowledge base. The frequent patterns and complex network knowledge mining methods are integrated to construct the TCM diagnosis and treatment CKD knowledge graph. Results. The knowledge graph of CKD diagnosis and treatment with TCM was constructed, including 807 nodes and 10476 relationships, which are 273 diagnoses, 130 symptoms, 34 syndromes, 370 Chinese herbal medicine (CHM) nodes, and 5483 diagnosis‐symptom, 1349 diagnosis‐syndrome, 3644 syndrome‐CHM relationships. Conclusion. The knowledge graph provides rich knowledge of TCM diagnosis and treatment of CKD, which is helpful to inherit the clinical experience of TCM diagnosis and treatment of CKD and assist clinical diagnosis and treatment of CKD.

Dynamic knowledge modeling and fusion method for custom apparel production process based on knowledge graph

Compared with ordinary mass-produced apparel products, custom apparel products will generate more data at each stage of their life cycle. Such data is in a highly dynamic state, while the relationship between the data is more complex. However, the current use of traditional relational data to store the whole life cycle data of custom apparel products has several problems of high redundancy, weak correlation, discrete distribution, and certain limitation of storage capacity. Therefore, based on knowledge graph, a dynamic knowledge modeling and fusion method is proposed for the production process of custom apparel. Firstly, an ontology-based knowledge modeling method is designed for custom apparel, which defined three types of ontology modeling methods for the process, resources, and features. On this basis, a knowledge graph construction method based on bi-directional fusion for the custom apparel production system is proposed. With one order as a unit, a knowledge graph facet (KGF) model, as well as the derived knowledge representation, generation and fusion method, is established to realize dynamic knowledge fusion of the custom apparel production process. Finally, taking the suit production process of a custom apparel factory as an example, the corresponding knowledge graph is constructed based on the ontology knowledge model, and the effectiveness of the proposed knowledge fusion method is verified.

Remote sensing knowledge graph construction and its application in typical scenarios

Remote sensing knowledge graph construction and its application in typical scenarios

How To Teach Domain Ontology-based Knowledge Graph Construction? An Irish Experiment

Domains represent concepts which belong to specific parts of the world. The particularized meaning of words linguistically encoding such domain concepts are provided by domain specific resources. The explicit meaning of such words are increasingly captured computationally using domain-specific ontologies, which, even for the same reference domain, are most often than not semantically incompatible. As information systems that rely on domain ontologies expand, there is a growing need to not only design domain ontologies and domain ontology-grounded Knowl­edge Graphs (KGs) but also to align them to general standards and conventions for interoperability. This often presents an insurmountable challenge to domain experts who have to additionally learn the construction of domain ontologies and KGs. Until now, several research methodologies have been proposed by different research groups using different technical approaches and based on scenarios of different domains of application. However, no methodology has been proposed which not only facilitates designing conceptually well-founded ontologies, but is also, equally, grounded in the general pedagogical principles of knowl­edge organization and, thereby, flexible enough to teach, and reproduce vis-à-vis domain experts. The purpose of this paper is to provide such a general, pedagogically flexible semantic knowl­edge modelling methodology. We exemplify the methodology by examples and illustrations from a professional-level digital healthcare course, and conclude with an evaluation grounded in technological parameters as well as user experience design principles.

Transporter proteins knowledge graph construction and its application in drug development

Transporters are the main determinant for pharmacokinetics characteristics of drugs, such as absorption, distribution, and excretion of drugs in humans. However, it is difficult to perform drug transporter validation and structure analysis of membrane transporter proteins by experimental methods. Many studies have demonstrated that knowledge graphs (KG) could effectively excavate potential association information between different entities. To improve the effectiveness of drug discovery, a transporter-related KG was constructed in this study. Meanwhile, a predictive frame (AutoInt_KG) and a generative frame (MolGPT_KG) were established based on the heterogeneity information obtained from the transporter-related KG by the RESCAL model. Natural product Luteolin with known transporters was selected to verify the reliability of the AutoInt_KG frame, its ROC-AUC (1:1), ROC-AUC (1:10), PR-AUC (1:1), PR-AUC (1:10) are 0.91, 0.94, 0.91 and 0.78, respectively. Subsequently, the MolGPT_KG frame was constructed to implement efficient drug design based on transporter structure. The evaluation results showed that the MolGPT_KG could generate novel and valid molecules and that these molecules were further confirmed by molecular docking analysis. The docking results showed that they could bind to important amino acids at the active site of the target transporter. Our findings will provide rich information resources and guidance for the further development of the transporter-related drugs.

Reinforcement learning-based distant supervision relation extraction for fault diagnosis knowledge graph construction under industry 4.0

Fault diagnosis is the key concern in the operation and maintenance of industrial assets. A fault diagnosis knowledge graph (KG) can provide decision support to the engineers to efficiently conduct maintenance tasks. However, as a type of domain KG, it would be time-consuming to manually label the corpus collected from the multi-source including the maintenance log, handbook and article. Meanwhile, the existence of the noisy sentence in the multi-source corpus jeopardises the performance of relation extraction modelling. In order to address this issue, this paper proposes a distant supervision relation extraction (DSRE)-based approach to construct a fault diagnosis KG. In this approach, the ontology of the fault diagnosis KG is firstly designed. Subsequently, a DSRE algorithm named relation-aware-based sentence-level attention enhanced piecewise convolutional neural network with reinforcement learning strategy (PCNN-ATTRA-RL) is proposed. The algorithm can effectively lower the impact of noisy sentences and accurately label the relation of different entities when the labelled data is insufficient. In this algorithm, PCNN-ATTRA is designed as the DSRE classifier to effectively extract the relation between entity pairs. RL is conducted to remove the noisy sentence so as to further improve the performance. An experimental study based on the multi-source corpus collected from the real world reveals that the proposed approach shows merits in comparison with the state-of-the-art algorithms. Meanwhile, a fault diagnosis KG, which can greatly support the decision-making of the engineers in the fault diagnosis, is established via the proposed approach.

Food safety in health: a model of extraction for food contaminants.

Contaminants are the critical targets of food safety supervision and risk assessment. In existing research, food safety knowledge graphs are used to improve the efficiency of supervision since they supply the relationship between contaminants and foods. Entity relationship extraction is one of the crucial technologies of knowledge graph construction. However, this technology still faces the issue of single entity overlap. This means that a head entity in a text description may have multiple corresponding tail entities with different relationships. To address this issue, this work proposes a pipeline model with neural networks for multiple relations enhanced entity pairs extraction. The proposed model can predict the correct entity pairs in terms of specific relations by introducing the semantic interaction between relation identification and entity extraction. We conducted various experiments on our own dataset FC and on the open public available data set DuIE2.0. The results of experiments show our model reaches the state-of-the-art, and the case study indicates our model can correctly extract entity-relationship triplets to release the problem of single entity overlap.

Towards Domain-Specific Knowledge Graph Construction for Flight Control Aided Maintenance

Flight control is a key system of modern aircraft. During each flight, pilots use flight control to control the forces of flight and also the aircraft’s direction and attitude. Whether flight control can work properly is closely related to safety such that daily maintenance is an essential task of airlines. Flight control maintenance heavily relies on expert knowledge. To facilitate knowledge achievement, aircraft manufacturers and airlines normally provide structural manuals for consulting. On the other hand, computer-aided maintenance systems are adopted for improving daily maintenance efficiency. However, we find that grass-roots engineers of airlines still inevitably consult unstructured technical manuals from time to time, for example, when meeting an unusual problem or an unfamiliar type of aircraft. Achieving effective knowledge from unstructured data is inefficient and inconvenient. Aiming at the problem, we propose a knowledge-graph-based maintenance prototype system as a complementary solution. The knowledge graph we built is dedicated for unstructured manuals referring to flight control. We first build ontology to represent key concepts and relation types and then perform entity-relation extraction adopting a pipeline paradigm with natural language processing techniques. To fully utilize domain-specific features, we present a hybrid method consisting of dedicated rules and a machine learning model for entity recognition. As for relation extraction, we leverage a two-stage Bi-LSTM (bi-directional long short-term memory networks) based method to improve the extraction precision by solving a sample imbalanced problem. We conduct comprehensive experiments to study the technical feasibility on real manuals from airlines. The average precision of entity recognition reaches 85%, and the average precision of relation extraction comes to 61%. Finally, we design a flight control maintenance prototype system based on the knowledge graph constructed and a graph database Neo4j. The prototype system takes alarm messages represented in natural language as the input and returns maintenance suggestions to serve grass-roots engineers.

Constructing Product Usage Context Knowledge Graph Using User-Generated Content for User-Driven Customization

Abstract User-driven customization is a particular design paradigm where customers act as co-designers to configure products based on their needs. However, due to insufficient product usage experience, customers may design a product incompatible with their environment and needs. Such incompatibility can negatively affect the performance of some customized features or even cause product failure. As a result, customers may hesitate to customize products because additional complexities and uncertainties are perceived. Product usage context (PUC), as all the environment and application factors that affect customer needs and product performance, can be used to facilitate customer co-design in user-driven customization. Identifying individual customer’s PUC can help customers foresee potential design failures, make more holistic design decisions, and be confident with their designs. Against the background, this paper proposes a PUC knowledge graph (PUCKG) construction method using user-generated content (UGC). The proposed method can convert crowdsourced corner cases into structured PUCKG to support personal PUC prediction, summarization, and reasoning. A case study of robot vacuum cleaners is conducted to validate the efficacy of the proposed method.

A Novel Threat Intelligence Information Extraction System Combining Multiple Models

The increasing number of cyberattacks has made the cybersecurity situation more serious. Thus, it is urgent to use cyber threat intelligence to deal with the complex and changing cyber environment. However, cyber threat intelligence usually exists in an unstructured form, and a huge amount of data poses a great challenge to security analysts. To this end, this paper proposes a novel threat intelligence information extraction system combining multiple models, which contains four key steps: entity extraction, coreference resolution, relation extraction, and knowledge graph construction. In the entity extraction task, a multihead self-attention mechanism is adopted to extract the dependency relationships between words. In the coreference resolution task, contextual information and mention embedding are fused to improve the mention representation. Meanwhile, features of different dimensions are extracted using a convolutional neural network. In the relation extraction task, additional features such as part of speech, mention width, entity type, and distance of entity pairs are incorporated to improve the embedding representation. Finally, a knowledge graph is constructed to explicitly present entities and their relationships. Experimental results indicate that compared with the baseline model, the F1 score of our model is improved by at least 8.87, 9.82, and 10.56 on entity extraction, coreference resolution, and relation extraction, respectively. The knowledge graph in Neo4j demonstrates the effectiveness of our system.

Construction of a fluvial facies knowledge graph and its application in sedimentary facies identification

Lithofacies paleogeography is a data-intensive discipline that involves the interpretation and compilation of sedimentary facies. Traditional sedimentary facies analysis is a labor-intensive task with the added complexity of using unstructured knowledge and unstandardized terminology. Therefore, it is very difficult for beginners or non-geology scholars who lack a systematic knowledge and experience in sedimentary facies analysis. These hurdles could be partly alleviated by having a standardized, structured, and systematic knowledge base coupled with an efficient automatic machine-assisted sedimentary facies identification system. To this end, this study constructed a knowledge system for fluvial facies and carried out knowledge representation. Components include a domain knowledge graph for types of fluvial facies (meandering, braided and other fluvial depositional environments) and their characteristic features (bedforms, grain size distribution, etc.) with visualization, a method for query and retrieval on a graph database platform, a hierarchical knowledge tree-structure, a data-mining clustering algorithm for machine-analysis of publication texts, and an algorithm model for this area of sedimentary facies reasoning. The underlying sedimentary facies identification and knowledge reasoning system is based on expert experience and synthesis of publications. For testing, 17 sets literature publications data that included details of sedimentary facies data (bedforms, grain sizes, etc.) were submitted to the artificial intelligence model, then compared and validated. This testing set of automated reasoning results yielded an interpretation accuracy of about 90% relative to the published interpretations in those papers. Therefore, the model and algorithm provide an efficient and automated reasoning technology, which provides a new approach and route for the rapid and intelligent identification of other types of sedimentary facies from literature data or direct use in the field.

Construction and application of knowledge graph of Treatise on Febrile Diseases

ObjectiveTo establish the knowledge graph of “disease-syndrome-symptom-method-formula” in Treatise on Febrile Diseases (Shang Han Lun,《伤寒论》) for reducing the fuzziness and uncertainty of data, and for laying a foundation for later knowledge reasoning and its application. MethodsUnder the guidance of experts in the classical formula of traditional Chinese medicine (TCM), the method of “top-down as the main, bottom-up as the auxiliary” was adopted to carry out knowledge extraction, knowledge fusion, and knowledge storage from the five aspects of the disease, syndrome, symptom, method, and formula for the original text of Treatise on Febrile Diseases, and so the knowledge graph of Treatise on Febrile Diseases was constructed. On this basis, the knowledge structure query and the knowledge relevance query were realized in a visual manner. ResultsThe knowledge graph of “disease-syndrome-symptom-method-formula” in the Treatise on Febrile Diseases was constructed, containing 6 469 entities and 10 911 relational triples, on which the query of entities and their relationships can be carried out and the query result can be visualized. ConclusionThe knowledge graph of Treatise on Febrile Diseases systematically realizes its digitization of the knowledge system, and improves the completeness and accuracy of the knowledge representation, and the connection between “disease-syndrome-symptom-treatment-formula”, which is conducive to the sharing and reuse of knowledge can be obtained in a clear and efficient way.

Knowledge graph-based method for solutions detection and evaluation in an online problem-solving community

&lt;span lang="EN-US"&gt;Online communities are a real medium for human experiences sharing. They contain rich knowledge of lived situations and experiences that can be used to support decision-making process and problem-solving. This work presents an approach for extracting, representing, and evaluating components of problem-solving knowledge shared in online communities. Few studies have tackled the issue of knowledge extraction and its usefulness evaluation in online communities. In this study, we propose a new approach to detect and evaluate best solutions to problems discussed by members of online communities. Our approach is based on knowledge graph technology and graphs theory enabling the representation of knowledge shared by the community and facilitating its reuse. Our process of problem-solving knowledge extraction in online communities (PSKEOC) consists of three phases: problems and solutions detection and classification, knowledge graph constitution and finally best solutions evaluation. The experimental results are compared to the World Health Organization (WHO) model chapter about Infant and young child feeding and show that our approach succeed to extract and reveal important problem-solving knowledge contained in online community’s conversations. Our proposed approach leads to the construction of an experiential knowledge graph as a representation of the constructed knowledge base in the community studied in this paper.&lt;/span&gt;

Knowledge graph construction and Internet of Things optimisation for power grid data knowledge extraction

Abstract Problems exist in power grid data management that have unclear relationships, weak security and low accuracy. By analysing the knowledge graph construction characteristics of smart grid data information and knowledge extraction, the grid data management platform is reshaped architecturally, and the knowledge graph construction technology is embedded in the grid data management framework. For the aforementioned problems, the knowledge graph construction and Internet of Things optimisation framework of power grid data knowledge extraction are proposed in this article. Firstly, the semantic search (KGSS) algorithm based on the knowledge graph is used. The KGSS algorithm extracts knowledge from structured, semi-structured and unstructured grid data through the massively parallel processing acquisition model and Hadoop database, and constructs knowledge entities, attributes and inter-entity relationships. Then, it optimises and predicts through the knowledge graph construction and Internet of Things optimisation framework extracted from power grid data knowledge. Finally, the experimental results show that the accuracy rate of the KGSS algorithm is 92%. The experimental results also show that it provides new ideas and research directions for power grid data under big data in the future.

Systematic Construction of Knowledge Graphs for Research-Performing Organizations

Research-Performing Organizations (e.g., research centers, universities) usually accumulate a wealth of data related to their researchers, the generated scientific results and research outputs, and publicly and privately-funded projects that support their activities, etc. Even though the types of data handled may look similar across organizations, it is common to see that each institution has developed its own data model to provide support for many of their administrative activities (project reporting, curriculum management, personnel management, etc.). This creates obstacles to the integration and linking of knowledge across organizations, as well as difficulties when researchers move from one institution to another. In this paper, we take advantage of the ontology network created by the Spanish HERCULES initiative to facilitate the construction of knowledge graphs from existing information systems, such as the one managed by the company Universitas XXI, which provides support to more than 100 Spanish-speaking research-performing organizations worldwide. Our effort is not just focused on following the modeling choices from that ontology, but also on demonstrating how the use of standard declarative mapping rules (i.e., R2RML) guarantees a systematic and sustainable workflow for constructing and maintaining a KG. We also present several real-world use cases in which the proposed workflow is adopted together with a set of lessons learned and general recommendations that may also apply to other domains. The next steps include researching in the automation of the creation of the mapping rules, the enrichment of the KG with external sources, and its exploitation though distributed environments.