Enhancing Relational Triple Extraction in Specific Domains:Semantic Enhancement and Synergy of Large Language Models and Small Pre-Trained Language Models

In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.

Cyber Resilience through Real-Time Threat Analysis in Information Security

This paper examines how cybersecurity is developing and how it relates to more conventional information security. Although information security and cyber security are sometimes used synonymously, this study contends that they are not the same. The concept of cyber security is explored, which goes beyond protecting information resources to include a wider variety of assets, including people [1]. Protecting information assets is the main goal of traditional information security, with consideration to the human element and how people fit into the security process. On the other hand, cyber security adds a new level of complexity, as people might unintentionally contribute to or become targets of cyberattacks. This aspect presents moral questions since it is becoming more widely accepted that society has a duty to protect weaker members of society, including children [1]. The study emphasizes how important cyber security is on a larger scale, with many countries creating plans and laws to counteract cyberattacks. Nevertheless, a lot of these sources frequently neglect to define the differences or the relationship between information security and cyber security [1]. The paper focus on differentiating between cybersecurity and information security on a larger scale. The study also highlights other areas of cybersecurity which includes defending people, social norms, and vital infrastructure from threats that arise from online in addition to information and technology protection. It contends that ethical issues and the human factor are becoming more and more important in protecting assets in the digital age, and that cyber security is a paradigm shift in this regard [1].

Comprehensive security risk factor identification for small reservoirs with heterogeneous data based on grey relational analysis model

Identification of security risk factors for small reservoirs is the basis for implementation of early warning systems.The manner of identification of the factors for small reservoirs is of practical significance when data are incomplete.The existing grey relational models have some disadvantages in measuring the correlation between categorical data sequences.To this end,this paper introduces a new grey relational model to analyze heterogeneous data.In this study,a set of security risk factors for small reservoirs was first constructed based on theoretical analysis,and heterogeneous data of these factors were recorded as sequences.The sequences were regarded as random variables,and the information entropy and conditional entropy between sequences were measured to analyze the relational degree between risk factors.Then,a new grey relational analysis model for heterogeneous data was constructed,and a comprehensive security risk factor identification method was developed.A case study of small reservoirs in Guangxi Zhuang Autonomous Region in China shows that the model constructed in this study is applicable to security risk factor identification for small reservoirs with heterogeneous and sparse data.

Spatio-temporal Data Model Based on Relational Database System

In this paper,the entity_relation data model for integrating spatio_temporal data is designed.In the design,spatio_temporal data can be effectively stored and spatiao_temporal analysis can be easily realized.

A Real-time Data Model Based on Temporal Data

Real-time database systems contain not only transaction timing constraints, but also data timing constraints. This paper discusses the temporal characteristics of data in real-time databases and offers a definition of absolute and relative temporal consistency. In real-time database systems, it is often the case that the policies of transaction schedules only consider the deadline of real-time transactions, making it insufficient to ensure temporal correctness of transactions. A policy is given by considering both the deadlines of transactions and the “data deadline” to schedule real-time transactions. A real-time relational data model and a real-time relational algebra based on the characteristics of temporal data are also proposed. In this model, the temporal data has not only corresponding values, but also validity intervals corresponding to the data values. At the same time, this model is able to keep historical data values. When validity interval of a relation is [NOW, NOW], real-time relational algebra will transform to traditional relational algebra.

Developing a Data Modelling Tool to Visualize the Transformation of an ER Diagram into a Relational Schema

In this paper, the authors present the development of a data modelling tool that visualizes the transformation process of an ＂Entity-Relationship＂ Diagram （ERD） into a relational database schema. The authors＇ focus is the design of a tool for educational purposes and its implementation on e-learning database course. The tool presents two stages of database design. The first stage is to draw ERD graphically and validate it. The drawing is done by a learner. Then at second stage, the system enables automatically transformation of ERD to relational database schema by using common rules. Thus, the learner could understand more easily how to apply the theoretical material. A detailed description of system functionalities and algorithm for the conversion are proposed. Finally, a user interface and usage aspects are exposed.

PORLES:A Parallel Object Relational Database System

We developed a parallel object relational DBMS named PORLES. It uses BSP model as its parallel computing model, and monoid calculus as its basis of data model. In this paper, we introduce its data model, parallel query optimization, transaction processing system and parallel access method in detail.

Research of storage technique for C-Temporal Relation Data Model

As there is datum redundancy in tradition database and temporal database in existence and the quantities of temporal database are increasing fleetly. We put forward compress storage tactics for temporal datum which combine compress technology in existence in order to settle datum redundancy in the course of temporal datum storage and temporal datum of slow acting domain and momentary acting domain are accessed by using each from independence clock method and mutual clock method .We also bring forward strategy of gridding storage to resolve the problems of temporal datum rising rapidly.

Application of a mixed DEA model to evaluate relative efficiency validity

Data envelopment analysis(DEA) model is widely used to evaluate the relative efficiency of producers. It is a kind of objective decision method with multiple indexes. However, the two basic models frequently used at present, the C2R model and the C2GS2 model have limitations when used alone,resulting in evaluations that are often unsatisfactory. In order to solve this problem, a mixed DEA model is built and is used to evaluate the validity of the business efficiency of listed companies. An explanation of how to use this mixed DEA model is offered and its feasibility is verified.

Real-time 3-D space numerical shake prediction for earthquake early warning

In earthquake early warning systems, real-time shake prediction through wave propagation simulation is a promising approach. Compared with traditional methods, it does not suffer from the inaccurate estimation of source parameters. For computation efficiency, wave direction is assumed to propagate on the 2-D surface of the earth in these methods. In fact, since the seismic wave propagates in the 3-D sphere of the earth, the 2-D space modeling of wave direction results in inaccurate wave estimation. In this paper, we propose a 3-D space numerical shake pre- diction method, which simulates the wave propagation in 3-D space using radiative transfer theory, and incorporate data assimilation technique to estimate the distribution of wave energy. 2011 Tohoku earthquake is studied as an example to show the validity of the proposed model. 2-D space model and 3-D space model are compared in this article, and the prediction results show that numerical shake prediction based on 3-D space model can estimate the real-time ground motion precisely, and overprediction is alleviated when using 3-D space model.

GIS Conceptual Data Model

In order to set up a conceptual data model that reflects the real world as accurately as possible,this paper firstly reviews and analyzes the disadvantages of previous conceptual data models used by traditional GIS in simulating geographic space,gives a new explanation to geographic space and analyzes its various essential characteristics.Finally,this paper proposes several detailed key points for designing a new type of GIS data model and gives a simple holistic GIS data model.

On the Relation Redundancy in Fuzzy Databases

This paper concentrates on the problem of data redundancy under the extended-possibility-based model. Based on the information gain in data classification, a measure - relation redundancy - is proposed to evaluate the degree of a given relation being redundant in whole. The properties of relation redundancy are also investigated. This new measure is useful in dealing with data redundancy.

Data Models Comparison and Experimental Design of Database Course

Data model is the core knowledge of database course.A deep understanding of data model is the key to mastering database design and application.The data models of NoSQL databases are categorized as key-value stores,column-oriented stores,document-oriented stores and graph databases.This paper makes a comparative analysis of the characteristics of the relational data model and NoSQL data models,and gives the design and implementation of different data models combined with cases,so that students can master the relevant theories and application methods of the database model.

On Detecting and Enforcing the Non-Relational Constraints Associated to Dyadic Relations in MatBase

MatBase is a prototype data and knowledge base management expert intelligent system based on the Relational,Entity-Relationship,and(Elementary)Mathematical Data Models.Dyadic relationships are quite common in data modeling.Besides their relational-type constraints,they often exhibit mathematical properties that are not covered by the Relational Data Model.This paper presents and discusses the MatBase algorithm that assists database designers in discovering all non-relational constraints associated to them,as well as its algorithm for enforcing them,thus providing a significantly higher degree of data quality.

OBN地震数据成像处理基本逻辑与关键方法技术

海洋油气勘探逐渐进入深水深层勘探领域,地下地质构造复杂(横向变速剧烈)、目标油藏复杂(由以构造油气藏为主转向构造与地层岩性油气藏并重),同时还可能伴随海底地形及附近岩性的复杂变化,所有因素促使海洋油气地震勘探技术不断变革。提高海洋油气勘探效益的首要问题是发展尽可能满足高精度地震波成像需求的地震数据采集技术及对应的高精度地震波成像技术。当前,无论海上和陆上油气地震勘探,“两宽一高”地震数据采集技术和全波形反演(FWI)/最小二乘逆时偏移(LS_RTM)为代表的地震波成像技术是标志性的领先技术。海上油气地震勘探中,海底节点(OBN)地震数据采集是目前业界公认的、最有可能真正实现“两宽一高”地震数据采集的技术。与拖缆数据采集相比,OBN数据采集具有宽方位照明、数据信噪比高、无检端鬼波、存在实测的(至少一阶自由表面相关)下行波场、四分量观测等优点。尤其是宽方位照明和存在至少一阶自由表面下行波场的特点,使得OBN数据具备了对中深层复杂构造和近海底介质进行高精度成像的能力。着重讨论了高精度地震波成像对地震数据采集的要求,指出OBN数据采集在海洋油气勘探中的必要性;分析了OBN数据采集的地震波场的特点,据此提出OBN数据地震波成像处理的基本逻辑及相应的关键技术;认为海洋油气勘探中地震波成像处理的特殊问题主要由特征反射层引起,海水面、海底面和地下介质中若干强反射层构成了这些特征反射层,提出了模型驱动波动理论特征反射层相关多次波预测与压制的技术路线,并对比了几种代表性的多次波预测的基础理论;指出对应当前的线性化偏移成像算子叠前数据域与叠前成像域是等价的,据此以成像道集后处理为中心,给出期望成像道集的定义,将弱旁瓣、定量的反射系数作为保真高分辨地震波成像的目标,在两个域中尽可能完美实现地下同一反(绕/散)射点、不同炮检距反(绕/散)射子波的同相位叠加,尽可能好地实现保真高分辨带限反射系数的成像;提出最好把带限反射系数成像推进到宽带波阻抗成像的技术路线;结合OBN数据的特点,给出了OBN数据地震波成像处理的基本技术流程,指出各环节的关键方法技术。最后,针对OBN数据四分量观测的特点,指出是实际观测的多波地震波场中的波现象(主要是P_SV波)与地震波传播及模拟理论不匹配导致了当前多波成像结果达不到预期,建议重点研究实际观测的多波地震波场中的波现象与地震波传播及模拟理论不匹配的物理根源,而不是发展更高端的矢量波成像算法。期望本文的思想观点对OBN地震勘探在海洋油气勘探中的进一步应用产生积极的促进作用。

动态查询窗口引导的回复关系发现方法

在多方会话中,判断消息之间的回复关系是对话领域的一项重要任务。现有的相关工作还未关注、解决以下两个数据分布方面的问题:长度较短的消息往往出现的频率更高,而短文本包含的语义信息较少,限制了模型的学习能力;存在回复关系的正样本数量往往远少于负样本数量,导致模型在训练过程中容易出现数据偏斜问题,降低了模型处理正样本的性能。针对上述两个问题,作者提出一个基于预训练语言模型的改进模型,首先通过动态查询窗口建模缓解短文本相关问题;然后通过位置驱动的正样本权重优化缓解正样本相关问题。与前人研究工作进行比对,实验结果表明,与基于预训练语言模型的基线模型相比,改进模型将召回率平均提升了15.7%。此外,还构建了一个采集自Telegram平台的新数据集,可为后续相关研究提供数据支持。

基于贝叶斯网和RoBERTa的文本派生关系挖掘方法

对不实信息进行溯源分析是抑制社交网络中不实信息传播的重要手段,传统数据溯源方法主要针对结构化数据,难以准确判断文本之间的派生关系。针对这些问题,提出一种基于贝叶斯网和RoBERTa的文本派生关系挖掘方法,通过RoBERTa模型获得文本向量;通过RoBERTa模型初步预测文本间的派生关系,得到文本是否具有派生关系的分类标签;基于向量距离、文本距离、时间跨度和文本分类标签构建贝叶斯网,对文本派生关系进行判断。实验结果表明,所提方法查准率、查全率、F 1值均高于对比方法,验证了该方法的有效性。

Mechanistic modeling of copper corrosions in data center environments

Air-side economizers are increasingly used to take advantage of“free-cooling”in data centers with the intent of reducing the carbon footprint of buildings.However,they can introduce outdoor pollutants to indoor environment of data centers and cause corrosion damage to the information technology equipment.To evaluate the reliability of information technology equipment under various thermal and air-pollution conditions,a mechanistic model based on multi-ion transport and chemical reactions was developed.The model was used to predict Cu corrosion caused by Cl_(2)-containing pollutant mixtures.It also accounted for the effects of temperature(25℃and 28℃),relative humidity(50%,75%,and 95%),and synergism.It also identified higher air temperature as a corrosion barrier and higher relative humidity as a corrosion accelerator,which agreed well with the experimental results.The average root mean square error of the prediction was 13.7Å.The model can be used to evaluate the thermal guideline for data centers design and operation when Cl_(2)is present based on pre-established acceptable risk of corrosion in data centers’environment.

电网分析模型数据的图表组织结构对比与适用性研究

为了明晰电网分析模型的数据组织结构选择标准,对其图表组织方式的适用性研究。基于本体思想,构建电网分析模型的元件表、元件图和层次化图数据模型,并在不同规模电网下进行测试和对比性能。测试结果给出了三者的检索性能定量关系,表明所构建层次图的检索性能在多层拓扑检索中分别约为元件图和元件表的10倍和40倍,可为电网数字底座的数据组织结构选配提供依据。

面向网络安全关系抽取的大语言模型数据增强方法

关系抽取技术可用于威胁情报挖掘与分析,为网络安全防御提供关键信息支持,但网络安全领域的关系抽取任务面临数据集匮乏的问题。近年来,大语言模型展现了优秀的文本生成能力,为数据增强任务提供了强大的技术支撑。为了弥补传统数据增强方式在准确性和多样性方面的不足,文章提出一种面向网络安全关系抽取的大语言模型数据增强方法MGDA,该方法从单词、短语、语法和语义4个粒度使用大语言模型增强原始数据,从而在确保准确性的同时提升多样性。实验结果表明,文章所提数据增强方法有效改善了网络安全关系抽取任务上的有效性以及生成数据的多样性。