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.

A Semantic-Sensitive Approach to Indoor and Outdoor 3D Data Organization

Building model data organization is often programmed to solve a specific problem,resulting in the inability to organize indoor and outdoor 3D scenes in an integrated manner.In this paper,existing building spatial data models are studied,and the characteristics of building information modeling standards(IFC),city geographic modeling language(CityGML),indoor modeling language(IndoorGML),and other models are compared and analyzed.CityGML and IndoorGML models face challenges in satisfying diverse application scenarios and requirements due to limitations in their expression capabilities.It is proposed to combine the semantic information of the model objects to effectively partition and organize the indoor and outdoor spatial 3D model data and to construct the indoor and outdoor data organization mechanism of“chunk-layer-subobject-entrances-area-detail object.”This method is verified by proposing a 3D data organization method for indoor and outdoor space and constructing a 3D visualization system based on it.

Using Semantic Web Technologies to Improve the Extract Transform Load Model

Semantic Web(SW)provides new opportunities for the study and application of big data,massive ranges of data sets in varied formats from multiple sources.Related studies focus on potential SW technologies for resolving big data problems,such as structurally and semantically heterogeneous data that result from the variety of data formats(structured,semi-structured,numeric,unstructured text data,email,video,audio,stock ticker).SW offers information semantically both for people and machines to retain the vast volume of data and provide a meaningful output of unstructured data.In the current research,we implement a new semantic Extract Transform Load(ETL)model that uses SW technologies for aggregating,integrating,and representing data as linked data.First,geospatial data resources are aggregated from the internet,and then a semantic ETL model is used to store the aggregated data in a semantic model after converting it to Resource Description Framework(RDF)format for successful integration and representation.The principal contribution of this research is the synthesis,aggregation,and semantic representation of geospatial data to solve problems.A case study of city data is used to illustrate the semantic ETL model’s functionalities.The results show that the proposed model solves the structural and semantic heterogeneity problems in diverse data sources for successful data aggregation,integration,and representation.

融合语义感知与模型生成的异常医疗数据识别算法设计

为了能够对海量电子诊疗信息中的异常数据进行识别,提出一种融合语义感知与模型生成的异常医疗数据识别算法。通过融入胶囊神经网络并改进Transformer网络,实现了对医疗电子病历结构和生成语义特征的感知提取;结合胶囊神经网络和Transformer网络的损失函数,加速了模型的收敛,从而提高了模型的异常数据识别准确率。在电子病历数据集上进行的实验结果表明,所提模型的准确率可达94.2%,高于多种现有的主流异常数据识别诊断模型。证明该模型算法能够对医疗电子病历实现语义感知和异常数据识别,为实现智能化的辅助诊疗提供了技术基础。

Categorical Database Generalization

This paper focuses on the issues of categorical database gen-eralization and emphasizes the roles ofsupporting data model, integrated datamodel, spatial analysis and semanticanalysis in database generalization.The framework contents of categoricaldatabase generalization transformationare defined. This paper presents an in-tegrated spatial supporting data struc-ture, a semantic supporting model andsimilarity model for the categorical da-tabase generalization. The concept oftransformation unit is proposed in generalization.

Evaluation on Information Model about Sensors Featured by Relationships to Measured Structural Objects

In accordance with the requirements of expanding Machine-To-Machine communication (M2M), the network overlay is in progress in several domains such as Smart Grid. Consequently, it is predictable that opportunities and cases of integrating yielded data from devices such as sensors will increase more. Accordingly, the importance of Ontology and Information Models (IM) which normalize the semantics including sensor expressions, have increased, and the standards of these definitions have been more important as well. So far, there have been multiple initiatives for standardizing the Ontology and IM in regards to the sensors expression such as Sensor Standards Harmonization by the National Institute of Standards and Technology (NIST), W3C Semantic Sensor Network (SSN) and the recent W3C IoT-Lite Ontology. However, there is still room to improve the current level of the Ontology and IM on the viewpoint of the implementing structure. This paper presents a set of IMs on abstract sensors and contexts in regards to the phenomenon around these sensors from the point of view of a structure implementing these specified sensors. As several previous studies have pointed out, multiple aspects on the sensors should be modeled. Accordingly, multiple sets of Ontology and IM on these sensors should be defined. Our study has intended to clarify the relationship between configurations and physical measured quantities of the structures implementing a set of sensors. Up to present, they have not been generalized and have remained unformulated. Consequently, due to the result of this analysis, it is expected to implement a more generalized translator module easily, which aggregates the measured data from the sensors on the middleware level managing these Ontology and IM, instead of the layer of user application programs.

Exploration and Realization of Several Key Problems of Geological Big Data

With the rapid development of technology,geological big data is increasing explosively,and plays an increasingly important position in the national economy(Zhang and Zhou,2017;Zhou et al.,2018).Governments and agencies attach great importance to the open internet service of geological big data and information at home,and abroad(Yan et al.,2013;Guo et al.,2014).The basic norms of western countries’geological data information services are rich and varied products.

Study on 3D Geological Model of Highway Tunnels Modeling Method

Geology is the base for highways and tunnels construction. With the fast development of national highway construction, highway tunnel construction project are more and more complex. The completeness and accuracy are essential for the planning, design and construction of projects, while the ground information is quite poor in systematic, reliable and timely aspects. Therefore, the development of underground road tunnels, and the implementation of informationized spatial information management is urgent for highway construction. 3D geological tunnel model is intuitive, high efficient and convenience which greatly facilitates the maintenance and security of highway tunnels construction and it will be the trend for the future highway tunnel development.

IEC 61850 SCL Validation Using UML Model in Modern Digital Substation

The IEC 61850 standard stipulates the Substation Configuration Description Language (SCL) file as a means to define the substation equipment, IED function and also the communication mechanism for the substation area network. The SCL is an eXtensible Markup Language (XML) based file which helps to describe the configuration of the substation Intelligent Electronic Devices (IED) including their associated functions. The SCL file is also configured to contain all IED capabilities including data model which is structured into objects for easy descriptive modeling. The effective functioning of this SCL file relies on appropriate validation techniques which check the data model for errors due to non-conformity to the IEC 61850 standard. In this research, we extend the conventional SCL validation algorithm to develop a more advanced validator which can validate the standard data model using the Unified Modeling Language (UML). By using the Rule-based SCL validation tool, we implement validation test cases for a more comprehensive understanding of the various validation functionalities. It can be observed from the algorithm and the various implemented test cases that the proposed validation tool can improve SCL information validation and also help automation engineers to comprehend the IEC 61850 substation system architecture.

基于BIM和语义网的轨道智能运维管理方法

建筑信息模型(BIM)技术对提高轨道运维管理效率具有重要的推进作用。然而,不同的检查和维护活动产生的数据异构性高、时空关系复杂,阻碍了BIM解释和整合数据的进程。为此,开发了一个基于工业基础类(IFC)和语义Web技术的轨道运维本体(TOMO),其具有3个功能:①基于轨道运维生命周期的应用需求,简化BIM模型信息;②引入映射规则,建立数据提取与转换模块,集成多源异构数据,结构化定义数据之间复杂的时空关系;③结合数据驱动技术,研究轨道精调智能优化的方法,提供弹性决策支持。最后,以某高速铁路静检数据为例,验证了该框架的有效性与实用性,对于促进领域数据互操作性、降低运维人员劳动强度和提高运维管理智能化程度具有实际的工程指导意义。

A trajectory data warehouse solution for workforce management decision-making

In modern workforce management,the demand for new ways to maximize worker satisfaction,productivity,and security levels is endless.Workforce movement data such as those source data from an access control system can support this ongoing process with subsequent analysis.In this study,a solution to attaining this goal is proposed,based on the design and implementation of a data mart as part of a dimensional trajectory data warehouse(TDW)that acts as a repository for the management of movement data.A novel methodological approach is proposed for modeling multiple spatial and temporal dimensions in a logical model.The case study presented in this paper for modeling and analyzing workforce movement data is to support human resource management decision-making and the following discussion provides a representative example of the contribution of a TDW in the process of information management and decision support systems.The entire process of exporting,cleaning,consolidating,and transforming data is implemented to achieve an appropriate format for final import.Structured query language(SQL)queries demonstrate the convenience of dimensional design for data analysis,and valuable information can be extracted from the movements of employees on company premises to manage the workforce efficiently and effectively.Visual analytics through data visualization support the analysis and facilitate decisionmaking and business intelligence.

语言学知识驱动的空间语义理解能力评测数据集研究

近20年来,深度学习技术显著提升了机器的自然语言处理能力,使之在诸多任务上接近甚至超过人类水平。机器学习的对象不再是直接来自人类语言学研究成果(知识),而是人类语言材料(数据)。在靠数据和算力驱动的大语言模型几近建成巴别塔的当下,语言学家通过深挖语言现象总结的语言学知识价值何在?本文提出从知识到数据的研究思路,设计了空间语义理解的6项任务:空间信息正误判别、异常空间信息识别、缺失参照成分补回、空间语义角色标注、空间表达异形同义判别、空间方位关系推理,以构建中文空间语义理解能力评测数据集为例,介绍从SpaCE2021到SpaCE2024数据集的设计思想、数据集制作概况以及机器在空间语义理解任务上的表现。总的来看,参加SpaCE赛事的大语言模型,在依赖表面分布特征(形式线索)的任务上容易获得好成绩,在依赖深层语义理解(认知能力)的任务上容易表现不好。因此,在人工智能高速发展使得语言学知识在计算机信息处理领域被动边缘化的当下,语言学知识的价值需要拓展,即用于指导小而精的高品质语言数据,以提升机器学习的效果和效率。为了计算应用的目的,语法研究应该在观察充分、描写充分、解释充分之上,追求更具挑战性的目标——生成充分。

基于多源数据的街道空间品质测度研究——以芜湖市中心城区为例

在20世纪80年代后,城市经济与高速公路的发展使城市结构发生剧变,由街道构成的传统城镇空间形态被打破。而街道空间作为城市公共空间的重要组成部分,其空间品质的研究对城市在打造魅力街道、传统特色保留以及时代新元素的融入方面具有重大意义。研究发现:芜湖市中心城区街道综合空间品质整体上,呈现出中心放射状的整体结构,城市空间品质测度结构及城市建设强度的重心数值也呈现出南高北低、内高外低的指状分布特征;芜湖市中心城区5种类型的街道在空间分布上表现出较为分散的特征,不同类型的街道聚类伴随区位的迁移具有明显的差异性;交通导向型街道趋向于城市干道及快速路,但由于城市的各类服务型业态难以覆盖而导致街道服务性不足,生活导向型街道多数位于城市核心建设区,需要加强街道绿化和空间开敞度方面的建设。

基于改进SPRINT分类算法的数据挖掘模型

为解决目前数据挖掘模型分类时间长、挖掘准确率不高的问题,提出基于改进决策树分类算法(SPRINT)的数据挖掘模型。先采用最大-最小规范化公式完成原始数据线性变换,利用改进后的SPRINT分类算法按照输入数据特性进行分类,使用协同过滤技术生成与数据相近的属性集,计算数据属性相似度,生成语义规则集,为用户提供更优的数据服务。选取某公司营销数据集作为样本进行对比实验,结果表明,与对比模型相比,所提出的数据挖掘模型分类时间更短,挖掘准确率更高,能为用户提供更优质的数据服务。

语义网赋能建筑信息交付及模型数据模式分析

针对以建筑信息模型(BIM)进行交付的信息共享模式所依赖的工业基础类(IFC)标准行业适用性不足且难以拓展的问题,探讨在IFC基础上引入语义网实现异源数据集成共享,并于语义层面实现信息交付。首先,通过算法解析和模型转化介绍语义化建模方法,并以二层钢框架厂房结构为例对该方法进行说明;然后,通过对转化案例进行数据模式分析,以验证建筑信息交付的准确性和建筑语义的可传递性。案例实践论证基于IfcOWL本体的语义化建模方法的可实施性;通过分析该语义化模型单元实例的数据模式,探究制约该语义化建模方法赋能建筑信息交付的关键因素;针对语义化建模方法所面临的问题,提出冗余信息规避、领域本体开发和轻量化语义建模的初步解决思路。SPARQL查询实例表明,所解析的数据模式对规避冗余信息有效。因此,该方法在共享和集成建筑多源异构信息方面具有优势,能有效提升建筑信息管理的智能化水平。

一种基于数据增强的科技文献关键词提取模型

[研究目的]科技文献关键词提取研究具有重要价值,目前研究中关键词提取方法存在较大误差且只能提取文本中的关键词,难以根据深层语义信息提炼出更符合文本核心主旨的词语。本研究针对关键词提取对上下文隐含语义挖掘不足导致的局限性和重点信息关注不足问题开展研究。[研究方法]提出一种基于数据增强的关键词提取模型(GPT-2 BiLSTM Mul-Attention,GPBA),通过语言模型进行数据增强,并结合BiLSTM+Mul-Attention提取模型进行多特征语义信息融合理解。[研究结论]实验结果表明,基于数据增强的关键词提取模型GPBA总体表现优于其他基线模型,并且能更精确地凝练和提取文本中的关键词。

基于LDA主题模型的在途驾驶风格识别方法

为增强人机共驾条件下智能系统对个体驾驶行为的理解,提出一种基于潜在狄利克雷分配(LDA)主题模型的在途驾驶风格识别方法,从多维度挖掘车辆轨迹信息,快速提取和识别驾驶员潜在驾驶风格特征。首先,建立驾驶行为语义理解规则,从驾驶作业的场景感知层、模式层、操作层以及车辆状态层出发,将连续的轨迹时序数据阐述为驾驶行为语义理解词汇;其次,根据主题困惑度和主题一致性指标定义4类习惯性驾驶风格:稳定型、保守型、适中型以及激进型;最后,将每位驾驶员的在途驾驶风格识别为上述驾驶风格的概率组合。结果表明:所提出的在途驾驶风格识别方法考虑驾驶员在驾驶过程中的异质性和不一致性,能够解释同一驾驶员在不同驾驶环境下表现出差异化驾驶风格的现象,同时,有助于提高驾驶风格在途识别的全面性以及可理解性。

Knowledge Model for Electric Power Big Data Based on Ontology and Semantic Web

It is very important for the development of electric power big data technology to use the electric power knowledge.A new electric power knowledge theory model is proposed here to solve the problem of normalized modeled electric power knowledge for the management and analysis of electric power big data.Current modeling techniques of electric power knowledge are viewed as inadequate because of the complexity and variety of the relationships among electric power system data.Ontology theory and semantic web technologies used in electric power systems and in many other industry domains provide a new kind of knowledge modeling method.Based on this,this paper proposes the structure,elements,basic calculations and multidimensional reasoning method of the new knowledge model.A modeling example of the regulations defined in electric power system operation standard is demonstrated.Different forms of the model and related technologies are also introduced,including electric power system standard modeling,multi-type data management,unstructured data searching,knowledge display and data analysis based on semantic expansion and reduction.Research shows that the new model developed here is powerful and can adapt to various knowledge expression requirements of electric power big data.With the development of electric power big data technology,it is expected that the knowledge model will be improved and will be used in more applications.

新一代电子目标整编业务框架研究

电子目标整编是将零散、模糊、矛盾的原始素材,通过各种迹象对照、关联等去粗取精、去伪存真,转变为有序、精准、可靠的情报信息。文中剖析了传统电子目标整编面临的文本类资料处理负荷日益剧增、海量低密度价值数据提取困难、体系级情报的整编与分析欠缺等主要问题与挑战,提出了电子目标整编业务“智能+”新框架,并对其典型的核心技术进行了探讨与思考,最后给出了工程实践中的部分实例,旨在为大模型、大数据等新兴技术赋能电子目标整编业务模式研究,提供技术参考与借鉴。

语义通信模型联合训练框架中的隐私泄露

为了同时保障端边协同训练语义编解码模型过程中的模型训练效率与数据隐私保护,基于U型分割的语义编解码模型端边协同训练框架是一种可行的方法。然而,端边之间交互的中间特征值与特征梯度仍然可能会泄露终端设备的数据隐私。基于U型分割的语义编解码模型端边协同训练框架可以在一定程度上解决端边协同训练语义编解码模型过程中模型训练效率与数据隐私保护之间的矛盾。然而,该框架下端边之间的交互过程仍然可能泄露终端设备的数据隐私。针对这一问题,提出了一种面向U型分割语义编解码模型协同训练过程的特征泄露攻击算法,通过分析训练过程中终端设备与边缘服务器之间交互的中间特征值和特征梯度,对终端的私有隐私数据进行重构。仿真结果表明,当使用单回合中间特征值对终端数据进行推断时,语义编解码模型使用浅层分割点或模型训练轮次较多时,中间特征值会包含更多的数据语义信息。此外,当攻击者增加本地攻击迭代次数,并选取多回合中间特征值和特征梯度对终端数据进行推断时,重构的终端数据与真实数据的图像结构相似度可以从0.2759提升到0.4017。