IndRT-GCNets: Knowledge Reasoning with Independent Recurrent Temporal Graph Convolutional Representations

Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurrent Temporal Graph Convolution Networks(IndRT-GCNets)framework to efficiently and accurately capture event attribute information.The framework models the knowledge graph sequences to learn the evolutionary represen-tations of entities and relations within each period.Firstly,by utilizing the temporal graph convolution module in the evolutionary representation unit,the framework captures the structural dependency relationships within the knowledge graph in each period.Meanwhile,to achieve better event representation and establish effective correlations,an independent recurrent neural network is employed to implement auto-regressive modeling.Furthermore,static attributes of entities in the entity-relation events are constrained andmerged using a static graph constraint to obtain optimal entity representations.Finally,the evolution of entity and relation representations is utilized to predict events in the next subsequent step.On multiple real-world datasets such as Freebase13(FB13),Freebase 15k(FB15K),WordNet11(WN11),WordNet18(WN18),FB15K-237,WN18RR,YAGO3-10,and Nell-995,the results of multiple evaluation indicators show that our proposed IndRT-GCNets framework outperforms most existing models on knowledge reasoning tasks,which validates the effectiveness and robustness.

Social Robot Detection Method with Improved Graph Neural Networks

Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social life.Existing social robot detection methods based on graph neural networks suffer from the problem of many social network nodes and complex relationships,which makes it difficult to accurately describe the difference between the topological relations of nodes,resulting in low detection accuracy of social robots.This paper proposes a social robot detection method with the use of an improved neural network.First,social relationship subgraphs are constructed by leveraging the user’s social network to disentangle intricate social relationships effectively.Then,a linear modulated graph attention residual network model is devised to extract the node and network topology features of the social relation subgraph,thereby generating comprehensive social relation subgraph features,and the feature-wise linear modulation module of the model can better learn the differences between the nodes.Next,user text content and behavioral gene sequences are extracted to construct social behavioral features combined with the social relationship subgraph features.Finally,social robots can be more accurately identified by combining user behavioral and relationship features.By carrying out experimental studies based on the publicly available datasets TwiBot-20 and Cresci-15,the suggested method’s detection accuracies can achieve 86.73%and 97.86%,respectively.Compared with the existing mainstream approaches,the accuracy of the proposed method is 2.2%and 1.35%higher on the two datasets.The results show that the method proposed in this paper can effectively detect social robots and maintain a healthy ecological environment of social networks.

Application of rough graph in relationship mining

Based on the definition of class shortest path in weighted rough graph, class shortest path algorithm in weighted rough graph is presented, which extends classical shortest path algorithm. The application in relationship mining shows effectiveness of it.

Research on Higher Education Collaborative Management Platform Based on Relationship Graph

According to the current problems of higher education management informatization,this paper puts forward a development scheme of collaborative platform on education management.The main technology includes three parts.First,integrate the distributed database and use two-tier linked list to realize dynamic data access.Second,the relation graph is used to display the data of each student,so as to realize the visual sharing of data.Third,realize the collaborative information security mechanism from three aspects to ensure the legal sharing of data.Finally,the platform development is completed with Java.It can help to improve the effectiveness of educating students.

The Correlation Coefficient of Hesitancy Fuzzy Graphs in Decision Making

The hesitancy fuzzy graphs(HFGs),an extension of fuzzy graphs,are useful tools for dealing with ambiguity and uncertainty in issues involving decision-making(DM).This research implements a correlation coefficient measure(CCM)to assess the strength of the association between HFGs in this article since CCMs have a high capacity to process and interpret data.The CCM that is proposed between the HFGs has better qualities than the existing ones.It lowers restrictions on the hesitant fuzzy elements’length and may be used to establish whether the HFGs are connected negatively or favorably.Additionally,a CCMbased attribute DM approach is built into a hesitant fuzzy environment.This article suggests the use of weighted correlation coefficient measures(WCCMs)using the CCM concept to quantify the correlation between two HFGs.The decisionmaking problems of hesitancy fuzzy preference relations(HFPRs)are considered.This research proposes a new technique for assessing the relative weights of experts based on the uncertainty of HFPRs and the correlation coefficient degree of each HFPR.This paper determines the ranking order of all alternatives and the best one by using the CCMs between each option and the ideal choice.In the meantime,the appropriate example is given to demonstrate the viability of the new strategies.

Railway Passenger Flow Forecasting by Integrating Passenger Flow Relationship and Spatiotemporal Similarity

Railway passenger flow forecasting can help to develop sensible railway schedules,make full use of railway resources,and meet the travel demand of passengers.The structure of passenger flow in railway networks and the spatiotemporal relationship of passenger flow among stations are two distinctive features of railway passenger flow.Most of the previous studies used only a single feature for prediction and lacked correlations,resulting in suboptimal performance.To address the above-mentioned problem,we proposed the railway passenger flow prediction model called Flow-Similarity Attention Graph Convolutional Network(F-SAGCN).First,we constructed the passenger flow relations graph(RG)based on the Origin-Destination(OD).Second,the Passenger Flow Fluctuation Similarity(PFFS)algorithm is used to measure the similarity of passenger flow between stations,which helps construct the spatiotemporal similarity graph(SG).Then,we determine the weights of the mutual influence of different stations at different times through an attention mechanism and extract spatiotemporal features through graph convolution on the RG and SG.Finally,we fused the spatiotemporal features and the original temporal features of stations for prediction.The comparison experiments on a railway bureau’s accurate railway passenger flow data show that the proposed F-SAGCN method improved the prediction accuracy and reduced the mean absolute percentage error(MAPE)of 46 stations to 7.93%.

基于异构图和语义融合的实体关系抽取

关系抽取是信息抽取中的一项重要任务,其目的是从非结构化文本中抽取出所有关系三元组。然而,如何有效地处理这一问题仍然是一个挑战,特别是对于关系重叠问题。为了有效处理重叠问题,该文提出一种基于异构图和语义融合的实体关系抽取方法:使用异构图将关系信息作为先验知识融入词表示,增强词表示的表示能力,使得模型能有效地处理单词实体重叠问题;使用语义融合模块将不同层次特征融合在一起作为关系分类模型的输入,使得模型能够有效地处理实体对重叠问题。所提方法在NYT和WebNLG数据集上取得了最好的效果,详细的实验也表明所提方法可以处理复杂的场景。

基于多序列隐关系的时序事件预测

时序事件预测是指基于历史事件预测下一个事件,事件包括时间和类型两个属性。当前主要工作集中在单方面(事件时间或事件类型)的预测,但这无法回答“何时发生何事”这类更精细的问题。此类问题的挑战主要是事件类型非常多样,而行为往往高度稀疏,给预测带来极大困难;需要预测的事件时间和事件类型分属两个域,如何把这两个域的信息加以融合并形成互补也是一个挑战。针对上述挑战,从融合多序列隐信息的角度探索了一种解决方法。基于某些事件序列之间具有模式相似性这一观察,提出建模事件序列的隐关系图,利用邻居序列的信息解决行为稀疏性的问题;通过合理设计神经网络模块,将事件的时间域和类型域的信息映射到共同的抽象空间,解决事件时间和事件类型信息的融合建模问题。通过在多个真实数据集上进行了大量实验,实验结果印证了多序列深度时序模型优于现有的一系列基准模型。

知识图谱技术及其在家禽产业中的应用

知识图谱作为结构化语义网络,能够存储实体间丰富的关系信息,广泛应用于多个领域,在家禽产业中展现出显著的实用价值。文章阐述了知识图谱的组成元素、主要技术流程及其在家禽产业中的应用现状和挑战,以期为知识图谱在家禽产业中的应用提供参考。

基于跨度和边界探测的实体关系联合抽取模型

针对大多数跨度模型将文本分割成跨度序列时,产生大量非实体跨度,导致了数据不平衡和计算复杂度高等问题,提出了基于跨度和边界探测的实体关系联合抽取模型(joint extraction model for entity relationships based on span and boundary detection,SBDM)。SBDM首先使用训练Transformer的双向编码器表征量(bidirectional encoder representations from Transformer,BERT)模型将文本转化为词向量,并融合了通过图卷积获取的句法依赖信息以形成文本的特征表示;接着通过局部信息和句子上下文信息去探测实体边界并进行标记,以减少非实体跨度;然后将实体边界标记形成的跨度序列进行实体识别;最后将局部上下文信息融合到1个跨度实体对中并使用sigmoid函数进行关系分类。实验表明,SBDM在SciERC(multi-task identification of entities,relations,and coreference for scientific knowledge graph construction)数据集、CoNLL04(the 2004 conference on natural language learning)数据集上的关系分类指标S F1分别达到52.86%、74.47%,取得了较好效果。SBDM用于关系分类任务中,能促进跨度分类方法在关系抽取上的研究。

结合对象属性识别的图像场景图生成方法研究

场景图生成在视觉场景深度理解任务中发挥着重要的作用。现有的场景图生成方法主要关注场景中对象的位置、类别以及对象之间的关系,而忽略了对象属性蕴含的丰富场景语义信息。为了将图像属性语义融入场景图,提出了一种结合对象属性识别的图像场景图生成方法。首先针对属性识别的多标签分类问题,提出了一种基于混合分类器的属性分类损失函数来进行属性识别,通过结合二值交叉熵函数训练的二分类器和改进的团组交叉熵函数训练的多分类器来实现单个属性分类的查准率和多个属性预测的查全率全面提升。其次,通过将属性识别分支与原有场景图框架进行融合,将提取的属性信息作为额外的上下文语义与对象特征进行融合后辅助对象之间关系的识别。最后,模型在VG150数据集上与多个基准模型进行了对比实验,结果表明所提模型的对象属性预测和关系识别均取得了更优的结果。

融合用户社交关系的自适应图卷积推荐算法

为了缓解推荐系统中不同用户社交空间与兴趣空间的内在信息差异和忽视高阶邻居的问题,提出了一种融合用户社交关系的自适应图卷积推荐算法(adaptive graph convolutional recommendation algorithm integrating user social relationships,AGCRSR)。首先,模型在嵌入层使用映射矩阵将初始特征向量转换为自适应嵌入;其次,引入注意力机制聚合不同方面的用户嵌入,通过图卷积网络来线性学习用户和项目的潜在表示;最后,通过自适应模块聚合用户表示并利用内积函数预测用户对项目的最终推荐结果。在数据集LastFM和Ciao上与其他基线算法进行了对比实验,实验结果表明AGCRSR的推荐效果较其他算法有显著提升。

基于多模态和知识蒸馏的教材知识图谱构建方法

为了高效构建教育领域多模态学科知识图谱,提出了基于大模型知识蒸馏和多模型协作推理的教材文本实体关系抽取算法。在模型训练阶段,利用闭源的千亿参数模型对文本数据进行标注,实现隐式知识蒸馏。然后对开源十亿规模参数模型进行领域数据指令微调,提升开源模型实体关系抽取任务的指令遵循能力。在模型推理阶段,闭源模型作为指导模型,开源的十亿规模参数模型作为执行模型。实验结果表明知识蒸馏、多模型协作、领域数据指令微调具有有效性,显著提高了基于指令提示的教材文本实体关系抽取任务的效果。提出了显隐式知识增强的教材示意图多模态命名实体识别算法。利用图像OCR、视觉语言模型等技术提取了教材示意图中的文字信息、全局内容描述信息。通过显式知识库检索增强和隐式LLM提示增强的方法,得到图像-标题对中可能关联的辅助知识,并将显式知识库和隐式LLM得到的知识进一步融合,形成最终的辅助知识。将示意图辅助知识和示意图标题进行拼接,实现教材示意图标题的多模态命名实体识别。实验结果表明,该算法具有先进性,同时增强了算法的可解释性。

基于卷积神经网络的医疗护理实体关系抽取

针对医疗护理领域知识复杂性强、数据量大以及对准确度要求较高的问题,该研究提出一种基于卷积神经网络的医疗护理学实体关系抽取方法,实现对护理学语义关系的细粒度文本挖掘。该研究构建了医疗护理学语料标注系统,通过将医疗语料转化为向量特征矩阵,实现了对医疗语料的自动过滤和标注。通过向神经网络模型嵌入所构建的医疗关系语料库,一定程度上提高了模型疾病分类的准确度。在医疗护理学数据集上的实验表明,基于卷积神经网络的模型在指标精确度、召回率、F1值可达到89.78%、87.59%、89.77%。综上所述,该研究提出的基于卷积神经网络的医疗护理学实体关系抽取方法能够有效地抽取医疗语料数据中的实体关系,优于传统的实体关系抽取模型。

基于大语言模型的职业院校区域间发展差异比较研究——以北京市和甘肃省为研究样本

鉴于中国地域辽阔、经济发展不均衡的国情,识别职业教育在各地表现的差异性对于科学统筹全国职业教育的高质量发展意义重大。利用大语言模型ChatGPT,通过Python程序调用API,对北京市和甘肃省职业院校发布的质量年度报告进行本体关系构建,深入对比分析两地区在人才培养与产教融合方面发展的相似性与差异性。结果显示,北京市凭借其丰富的教育资源,更加注重教师团队、课程设置等关键资源的投入,以增强职业院校的建设水平和创新能力;而甘肃省则更加侧重于学生在校的学习质量保障,就业所需的实际技能,致力于培养适应当地社会经济发展需求的实践性人才。

历史学维度下中国绘画的三种语图关系

在中国绘画史发展过程中,绘画和语言从来都是互为表里、相互补充的关系。从历史学维度涉及的语言和图像之间的关系角度,探讨中国绘画的三种语图关系。具体而言,中国绘画的语图关系主要包括语图一体、语图分体和语图合体这三大部分,包括分体关系、合体关系、直接影响古今文学艺术发展的特点及形成,并对当今艺术创作及发展有启示价值。

知识图谱中实体关系抽取方法研究

实体关系抽取作为知识图谱构建的基础得到了越来越多研究人员的关注。实体关系抽取能够自动、准确地从大量数据中获取知识,并以结构化形式表示和存储。因此,实体关系抽取的正确性直接影响到知识图谱构建的准确性和后续知识图谱应用效果。然而,针对复杂结构、开放领域、多语言、多模态、小样本数据和实体关系联合抽取等不同研究热点,现存的实体关系抽取方法仍存在一些局限性。基于当前实体关系抽取研究热点领域将实体关系抽取分为复杂结构研究领域、开放领域、多语言研究领域、多模态研究领域、小样本数据研究领域和实体关系联合抽取六个方面,将每个方面按照具体问题进行分类并列举出一些解决方法。不仅系统梳理了每一个类别当前存在的问题和解决方法,还归纳了每个类别的研究成果,并从定量分析和定性分析两个维度,详细地分析了每个方法的优点和缺点。最后,总结了当前热点领域中待解决的问题,同时展望了知识图谱中实体关系抽取方法未来的发展趋势。

基于知识图谱与加权贝叶斯机制的刑侦推断模型

随着信息化和数字化的高速发展,各类人工智能方法在现代公共安全领域得到充分应用,其中知识图谱以其强大的知识表征能力和数学建模能力,大大提高了智能决策的可解释性,成为领域内研究和应用的热点.一直以来,基于贝叶斯机制的推断模型是公安情报与刑侦分析的重要手段.本文将公安知识图谱引入传统贝叶斯模型,在充分考虑参数耦合性的基础上,对后验概率进行加权更新,有效提高了推断的准确性.本文回避敏感的真实数据,以《红楼梦》中“绣春囊”一案为例完成实证分析,科学地揭秘了经典悬案的真相.本文提出的基于知识图谱的自适应加权方案有效提高了贝叶斯模型的效率,是人工智能助力智慧公安的一种有益尝试.

完全图高阶关系驱动的链接预测

图卷积网络(graph convolutional network,GCN)因其在处理图数据方面的独特优势而被广泛应用于推荐系统中,它通过利用图中节点之间的依赖关系传播节点属性信息,极大地提高了节点表示的准确度从而提升推荐性能.然而现有基于GCN的推荐方法仍因过平滑问题而难以进行更深层的建模,从而限制了用户与项目间高阶关系的表达.为此,提出了一种基于项目间关系的完全图高阶关系驱动的链接预测(link prediction driven by high-order relations in complete graph,LinkCG)方法.LinkCG通过用户-项目交互图与项目间隐式关联关系全局图组成的异构图预测用户到项目的链接,跳过了中间的用户节点直接利用完全图建模每个用户历史交互的项目间的局部隐式关联关系,获得项目间的高阶关系从而缓解数据稀疏性问题;此外,不同于基于节点嵌入的推荐方法,LinkCG通过赋予项目间的链接权重来表示项目间关系的紧密程度,并根据紧密程度进行链接预测,优化了模型的训练过程.在3个公开数据集上的实验结果表明,LinkCG作为只包含2个超参数的非深度学习模型,与一些先进的基于深度学习的基线方法相比提供了更好的性能.在社交关系数据上的应用进一步表明LinkCG能够从用户历史交互项目中获取足够丰富的用户偏好信息.

基于提示增强与双图注意力网络的复杂因果关系抽取

针对复杂因果句实体密度高、句式冗长等特点导致的外部信息不足和信息传递遗忘问题,提出一种基于提示增强与双图注意力网络(BiGAT)的复杂因果关系抽取模型PE-BiGAT(PromptEnhancementandBi-Graph Attention Network)。首先,抽取句子中的结果实体并与提示学习模板组成提示信息,再通过外部知识库增强提示信息;其次,将提示信息输入BiGAT,同时结合关注层与句法和语义依存图,并利用双仿射注意力机制缓解特征重叠的情况,增强模型对关系特征的感知能力;最后,用分类器迭代预测句子中的所有因果实体,并通过评分函数分析句子中所有的因果对。在SemEval-2010 task 8和AltLex数据集上的实验结果表明,与RPA-GCN(Relationship Position and Attention-Graph Convolutional Network)相比,所提模型的F1值提高了1.65个百分点,其中在链式因果和多因果句中分别提高了2.16和4.77个百分点,验证了所提模型在处理复杂因果句时更具优势。