Dynamic Vulnerability Knowledge Graph Construction via Multi-Source Data Fusion and Large Language Model Reasoning

Weaponry equipment names belong to an important military naming entity that is difficult to identify because of features, such as complex components, miscellaneous, and scarce annotation corpus. Here, the automatic recognition of weaponry equipment names is specifically explored, a NER (Named Entity Recognition) algorithm is proposed based on BI-LSTM-CRF (Bi-directional Long Short Term Memory Conditional Random Field), thereby demonstrating the effectiveness of domain features in domain-specific entity recognition. Firstly, Chinese characters are represented by word embedding and input into the model. Then, the input feature vector sequence is processed by BI-LSTM (Bi-directional Long Short Term Memory) NN (Neural Network) to extract context semantic learning features. Finally, the learned features are connected to the linear CRF (Conditional Random Field), the NEs (Named Entities) in the equipment support field are labeled, and the NER results are obtained and output. The experimental results show that the accuracy of the NER algorithm based on the BI-LSTM-CRF model is 92.02%, the recall rate is 93.21%, and the F1 value reaches 93.88%. The effect of this model is better than the BI-LSTM NN model and LSTM-CRF (Long Short Term Memory Conditional Random Field) NN model. The proposed model provides some references for entity recognition in the field of equipment support.

Traditional QA systems often rely on shallow semantic retrieval and single-source knowledge, making them insufficient for handling cross-domain queries and multi-hop reasoning. To address these limitations, this study proposes a novel QA framework that integrates multi-source heterogeneous data fusion with knowledge graph-based reasoning. The framework first introduces a multi-channel alignment and fusion module that unifies heterogeneous knowledge sources through entity alignment, relation extraction, and confidence-weighted attribute fusion, constructing a coherent knowledge graph. On this basis, a graph augmentation strategy enhances structural connectivity and semantic completeness. A deep reasoning module, combining relation-aware graph neural networks with query-conditioned multi-hop attention, enables both accurate inference and interpretable reasoning paths. Finally, a joint decoder simultaneously outputs natural language answers and supporting reasoning chains, improving explainability. Extensive experiments conducted on WikiHop, HotpotQA, and ComplexWebQuestions demonstrate the superiority of our model. Compared to strong baselines such as GRAFT-Net, HGN, and KG-QA-Base, our framework achieves consistent improvements of 4–6% in Exact Match (EM) and 5–7% in F1 score. More importantly, Path-Precision improves by 10–12 percentage points, highlighting the ability to generate reliable reasoning evidence. This research not only provides a feasible technical pathway for building interpretable QA systems with deep understanding, but also carries important theoretical and practical implications for advancing the cognitive capabilities of general artificial intelligence.

A knowledge graph method for hazardous chemical management: Ontology design and entity identification

IoT devices generate substantial amounts of measurements and use many different formats to store this data. In order to make IoT devices interoperable, a number of ontologies have been developed, such as the Smart Applications REFerence (SAREF) ontology, to create knowledge graphs that can represent all kinds of measurements from IoT devices. We call the resulting knowledge graphs: IoT measurement knowledge graphs. In this thesis, we set out to investigate what differentiates IoT measurement knowledge graphs from regular knowledge graphs. In the first half, we describe in detail how to create IoT measurement knowledge graphs from real-world measurement data. In the second half, we investigate what happens when we use the graphs in different scenarios, with different methods and applications. In order to generate an IoT measurement knowledge graph, we create a mapping to transform the measurement data coming from IoT devices. We explore multiple ways to create this mapping and evaluate the resulting IoT measurement knowledge graph with competency questions. Using our mapping, we create OfficeGraph, by transforming IoT measurement data recorded over a year from 444 IoT devices located in an office building. This IoT measurement knowledge graph is validated by answering competency questions created with the support of the building owners, showing that we can answer questions we were not able to answer without it. Besides the entities, literals, and relations in knowledge graphs, the combination of these, the context of entities, provides additional knowledge. Therefore, if we want to use entities in knowledge graphs to train machine learning models, it would be a waste to take only the entities from the graph, because this would leave out information. Representation models, such as RDF2Vec and Graph Convolutional Networks (GCNs), can be used to learn (embedding) representations for entities that take context into account, creating a representation based on which relations, entities, and literals occur near the entity in the graph. We learn over IoT measurement knowledge graphs using multiple representation models and experiment with the effect of making more knowledge available to the representation models through semantic enrichment. This is done by making implicit information, such as (e.g.) consecutive measurements, explicitly available, by adding a relation between two measurements. Results show that the semantic enrichment has a positive effect on the learnability, based on the evaluation score, of the entity representations. Due to the dynamic nature of IoT measurement knowledge graphs, it is to be expected that new measurements are made after the initial IoT measurement knowledge graphs are created. Therefore, we investigate the possibility of estimating representations for new entities that are based on the existing entity representations. We introduce the embedding estimation method, which used the numerical attributes of entities, the measurement values, to find entities similar to the new entity. Then by averaging the embedding representations of those entities, it creates a new, estimated, embedding for the new entity. We perform experiments to test the embedding estimation method, and show that there is a trade-off between the amount of time saved by not re-training the entire pipeline, but also a decrease in accuracy, with the estimated embeddings. This thesis offers a focused research into IoT measurement knowledge graph. We provide insight into how IoT measurement knowledge graph can be created and how they differ from regular knowledge graphs, specifically in being numerical, dynamic, and shallow knowledge graphs. We suggest and validate remedies to the shallowness of IoT measurement knowledge graphs, through the semantic enrichments. Furthermore we show how the numerical aspect can be a strength, through the embedding estimation method, which can help with the dynamic nature of IoT measurement knowledge graph.

In the rapidly evolving field of cybersecurity, the integration of multi-source, heterogeneous, and fragmented data into a coherent knowledge graph has garnered considerable attention. Such a graph elucidates semantic interconnections, thereby facilitating sophisticated analytical decision support. Central to the construction of a cybersecurity knowledge graph is Named Entity Recognition (NER), a critical technology that converts unstructured text into structured data. The efficacy of NER is pivotal, as it directly influences the integrity of the knowledge graph. The task of NER in cybersecurity, particularly within the Chinese linguistic context, presents distinct challenges. Chinese text lacks explicit space delimiters and features complex contextual dependencies, exacerbating the difficulty in discerning and categorizing named entities. These linguistic characteristics contribute to errors in word segmentation and semantic ambiguities, impeding NER accuracy. This paper introduces a novel NER methodology tailored for the Chinese cybersecurity corpus, termed CSBERT-IDCNN-BiLSTM-CRF. This approach harnesses Iterative Dilated Convolutional Neural Networks (IDCNN) for extracting local features, and Bi-directional Long Short-Term Memory networks (BiLSTM) for contextual understanding. It incorporates CSBERT, a pre-trained model adept at processing few-shot data, to derive input feature representations. The process culminates with Conditional Random Fields (CRF) for precise sequence labeling. To compensate for the scarcity of publicly accessible Chinese cybersecurity datasets, this paper synthesizes a bespoke dataset, authenticated by data from the China National Vulnerability Database, processed via the YEDDA annotation tool. Empirical analysis affirms that the proposed CSBERT-IDCNN-BiLSTM-CRF model surpasses existing Chinese NER frameworks, with an F1-score of 87.30% and a precision rate of 85.89%. This marks a significant advancement in the accurate identification of cybersecurity entities in Chinese text, reflecting the model’s robust capability to address the unique challenges presented by the language’s structural intricacies.

As the U.S. Capitol riots of January 6, 2021 attest, conspiracy theories can lead to civil unrest. Many "netizens" of the radical online fora that host these conversations are not themselves radicalized. However, the limited in-line context necessary to evaluate their legitimacy, along with readers’ predisposition to believe stories that reinforce their existing worldviews, can create interpretations of real-world events that conflict with fact. Recent work proposes automated computational methods to reconstruct the missing contexts of conspiracy theories. While such work has successfully exposed several recent conspiracy theories, a robust real-time system that builds on this success at scale is needed. This paper presents one such implementation with: (a) A plug-and-play module for adding and removing heterogeneous text sources, (b) A scalable infrastructure that caters to the constantly expanding knowledge space, (c) Automation to parse real-time stories, and (d) An intuitive interface with a feedback module for users to directly evaluate the coherence of the generated context. The system returns a dynamic infinite-vocabulary Knowledge Graph (KG) that represents the directed relationships (edges) between critical actors (nodes) that feature in conspiracy theories. Our current implementation features 6 heterogeneous data sources accessed for > 5000 posts/day with a low search-latency (< 5ms for querying > 100, 000 relationships). Evaluation (with Amazon Mechanical Turk (AMT)) suggests our visualization captures well the coherence of the resultant conspiracy theories, with a positive skew (> 21.0) toward positive ratings.

To improve the effect of college English teaching, combines multi-source data (MSD) fusion technology to build a college English blended teaching system. Moreover, through the research on the functions of smarter classrooms and the analysis and exploration of blended teaching, this paper designs a college English blended teaching system based on MSD fusion. In addition, this paper analyzes the bandwidth-tunable optical routing module of the interference-coupled series double-ring involved in multi-data fusion. Finally, this paper studies the working principle and structural design of the module, and constructs a college English blended teaching system structure based on MSD fusion. From the evaluation results, it can be seen that the college English blended teaching system based on MSD fusion proposed in this paper can effectively improve the quality of English teaching.

Most of the biomedical knowledge the research community has acquired during the past few decades has been deposited in scientific literature as unstructured text. Converting the unstructured text into the structured form will enable novel methodologies and applications for scientific discovery that can fully harness the power of the existing knowledge. To this end, two fundamental questions need to be addressed: named entity recognition (NER) and relation extraction (RE). NER deals with identifying the concepts or entities in texts, such as diseases, genes/proteins, chemical compounds, etc. while RE aims to extract the relations among these entities. Together, the extracted information forms a knowledge graph (KG) where the nodes are entities in the texts and the edges represent their relationships. KGs can link concepts within existing research to allow researchers to find connections that may have been difficult to discover without them. The LitCoin Natural Language Processing (NLP) Challenge was recently organized by NCATS of NIH and NASA to spur innovation by rewarding the most creative and high-impact uses of biomedical text to create KGs. Our team participated in the challenge and ranked first place. We have applied the methods we developed for the LitCoin NLP challenge to all PubMed abstracts and constructed the largest-scale biomedical KG to date. We show that powerful and versatile query functions can be implemented on top of the KG to enable highly specific and accurate knowledge retrieval and inference of causal and indirect relationships. Citation Format: Xin Sui, Yuan Zhang, Feng Pan, Donghu Sun, Menghan Chung, Jinfeng Zhang. Constructing the largest-scale knowledge graph using all PubMed abstracts and its application for highly specific and accurate knowledge retrieval. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5421.

To address the technical challenges in the educational domain named entity recognition (NER), such as ambiguous entity boundaries and difficulties with nested entity identification, this study proposes an enhanced semantic BERT model (ES-BERT). The model innovatively adopts an education domain, vocabulary-assisted semantic enhancement strategy that (1) applies the term frequency–inverse document frequency (TF-IDF) algorithm to weight domain-specific terms, and (2) fuses the weighted lexical information with character-level features, enabling BERT to generate enriched, domain-aware, character–word hybrid representations. A complete bidirectional long short-term memory-conditional random field (BiLSTM-CRF) recognition framework was established, and a novel focal loss-based joint training method was introduced to optimize the process. The experimental design employed a three-phase validation protocol, as follows: (1) In a comparative evaluation using 5-fold cross-validation on our proprietary computer-education dataset, the proposed ES-BERT model yielded a precision of 90.38%, which is higher than that of the baseline models; (2) Ablation studies confirmed the contribution of domain-vocabulary enhancement to performance improvement; (3) Cross-domain experiments on the 2016 knowledge base question answering datasets and resume benchmark datasets demonstrated outstanding precision of 98.41% and 96.75%, respectively, verifying the model’s transfer-learning capability. These comprehensive experimental results substantiate that ES-BERT not only effectively resolves domain-specific NER challenges in education but also exhibits remarkable cross-domain adaptability.

Question answering (QA) systems are increasingly deployed across domains. However, their reliability is undermined when retrieved evidence is incomplete, noisy, or uncertain. Existing knowledge graph (KG) based QA frameworks typically represent facts as static and deterministic, failing to capture the evolving nature of information and the uncertainty inherent in reasoning. We present a demonstration of uncertainty-aware dynamic KGs, a framework that combines (i) dynamic construction of evolving KGs, (ii) confidence scoring and uncertainty-aware retrieval, and (iii) an interactive interface for reliable and interpretable QA. Our system highlights how uncertainty modeling can make QA more robust and transparent by enabling users to explore dynamic graphs, inspect confidence-annotated triples, and compare baseline versus confidence-aware answers. The target users of this demo are clinical data scientists and clinicians, and we instantiate the framework in healthcare: constructing personalized KGs from electronic health records, visualizing uncertainty across patient visits, and evaluating its impact on a mortality prediction task. This use case demonstrates the broader promise of uncertainty-aware dynamic KGs for enhancing QA reliability in high-stakes applications.

Data-driven, knowledge-grounded neural conversation models are capable of generating more informative responses. However, these models have not yet demonstrated that they can zero-shot adapt to updated, unseen knowledge graphs. This paper proposes a new task about how to apply dynamic knowledge graphs in neural conversation model and presents a novel TV series conversation corpus (DyKgChat) for the task. Our new task and corpus aids in understanding the influence of dynamic knowledge graphs on responses generation. Also, we propose a preliminary model that selects an output from two networks at each time step: a sequence-to-sequence model (Seq2Seq) and a multi-hop reasoning model, in order to support dynamic knowledge graphs. To benchmark this new task and evaluate the capability of adaptation, we introduce several evaluation metrics and the experiments show that our proposed approach outperforms previous knowledge-grounded conversation models. The proposed corpus and model can motivate the future research directions.

As a new generation technology representative of knowledge engineering, knowledge graph is a large-scale semantic network, which has natural advantages in extracting knowledge from multi-source heterogeneous information, complex and highly correlated knowledge representation and reasoning. Based on the analysis of the application status of the grid day-ahead scheduling optimization decision-making technology and the demand for improving the intelligent processing capability, the key technologies and methods for the application of knowledge graph in the grid day-ahead scheduling optimization decision-making are proposed. The key technologies, application ideas and process methods of knowledge graphs are analyzed from the aspects of the design of knowledge ontology framework in the field of day-to-day dispatching of power grids, high-quality phrase mining and entity recognition, relation extraction and knowledge fusion, and scene-based dynamic knowledge graph update. Finally, the application and challenges of knowledge graph in the field of grid day-ahead scheduling in the future are summarized and prospected.

Nowadays, the earthquake has become a very serious topic. The earthquake-related information always appears first in social media. Constructing an earthquake knowledge graph can help dealing with earthquake news social media text data. This paper proposed the BiLSTM-CRF (Bi-directional Long Short Term Memory-Conditional Random Field) model to construct earthquake knowledge graph using news text data. The BiLSTM-CRF model identified the entities and then writes entities and their types to the table so that the entities and relationships between entities can be extracted for earthquake. The entities and relationships between entities have been combined with the form of RDF (Resource Description Framework) to construct earthquake knowledge graph on Neo4j database.

The application of mobile intelligent terminal in the environment is very complex, and its own computing capacity is also very limited, so it is vulnerable to malicious attacks. The security classification of mobile intelligent terminals can effectively ensure the security of their use. Therefore, a security classification method for mobile intelligent terminals based on multi-source data fusion is proposed. The Boolean value is used to count the multi-source data of the mobile intelligent terminal, and the word frequency method is used to calculate the weight of the multi-source data of the mobile intelligent terminal. The D-S evidence theory is used to complete the multi-source data fusion of the mobile intelligent terminal and implement the multi-source data fusion processing of the mobile intelligent terminal. On this basis, the security level permission value of mobile intelligent terminal is calculated to achieve the security level division of mobile intelligent terminal based on multi-source data fusion. The experimental results show that the accuracy of mobile intelligent terminal security classification is higher than 96% and the classification time is less than 3.8 ms after the application of the proposed method. Therefore, the security level of mobile intelligent terminals after the application of this method is high, and the security performance of mobile intelligent terminals is strong, which can effectively improve the accuracy of security classification and shorten the time of security classification.

In today's rapidly expanding data landscape, knowledge extraction from unstructured text is vital for real-time analytics, temporal inference, and dynamic memory frameworks.However, traditional static knowledge graph (KG) construction often overlooks the dynamic and time-sensitive nature of real-world data, limiting adaptability to continuous changes.Moreover, recent zero-or few-shot approaches that avoid domain-specific fine-tuning or reliance on prebuilt ontologies often suffer from instability across multiple runs, as well as incomplete coverage of key facts.To address these challenges, we introduce ATOM 1 (AdapTive and OptiMized), a few-shot and scalable approach that builds and continuously updates Temporal Knowledge Graphs (TKGs) from unstructured texts.ATOM splits input documents into minimal, self-contained "atomic" facts, improving extraction exhaustivity and stability.Then, it constructs atomic TKGs from these facts, employing a dual-time modeling that distinguishes between when information is observed and when it is valid.The resulting atomic TKGs are subsequently merged in parallel.Empirical evaluations demonstrate that ATOM achieves 18% higher exhaustivity, 33% better stability, and over 90% latency reduction compared to baseline methods, demonstrating a strong scalability potential for dynamic TKG construction.