模糊概念图知识表示及其推理机制研究*

通过对现有模糊概念图的研究,针对概念的所指域与模糊信息间的冗余问题和用模糊度表示模糊概念问题,提出一种改进的模糊概念图知识表示方法。在改进的模糊概念图中,用模糊集合表示概念图中的模糊概念和模糊关系,并将模糊概念的所指域同模糊集合合并,减少信息冗余。根据改进的模糊概念图,重点研究了模糊概念图的匹配推理机制,设计了基于语义约束的匹配推理算法,并定量分析了算法的时间复杂度和空间复杂度。经过在《计算机文化基础》课程中实验测试,算法反映了考生主观题的答卷情况,同人工阅卷结果基本一致。     

On generalization/specialization for conceptual graphs

Abstract

This paper centres on the generalization/specialization relation in the framework of conceptual graphs (this relation corresponds to logical subsumption when considering logical formulas associated with conceptual graphs). Results given here apply more generally to any model where knowledge is described by labelled graphs and reasoning is based on graph subsumption, as in semantic networks or in structural machine learning. The generalization/specialization relation, as defined by Sowa, is first precisely analysed, in particular its links with a graph morphism, called projection. Besides Sowa's specialization relation (which is a preorder), another one is actually used in some practical applications (which is an order). These are comparatively studied. The second topic of this paper is the design of efficient algorithms for computing these specialization relations. Since the associated problems are NP-hard, the form of the graphs is restricted in order to arrive at polynomial algorithms. In particular, polynomial algorithms are presented for computing a projection from a conceptual ‘tree’ to any conceptual graph, and for counting the number of such projections. The algorithms are also described in a generic way, replacing the projection by a parametrized graph morphism, and conceptual graphs by directed labelled graphs.     

Diagnostic and remedial learning strategy based on conceptual graphs

Abstract Numerous scholars have applied conceptual graphs for explanatory purposes. This study devised the ‘Remedial‐Instruction Decisive path (RID path)’ algorithm for diagnosing individual student learning situation. This study focuses on conceptual graphs. According to the concepts learned by students and the weight values of relations among these concepts, this study established the remedial‐instruction paths to identify their real missing concepts. This study applies diagnostic and remedial learning strategies to two courses –‘Introduction and Implementation of RS‐232’ and ‘Electronic Circuits Laboratory’. By analysing the scores of the midterm and final exams, evaluations of remedial learning yield positive experimental results. Participants who adopt the diagnostic and remedial learning strategy have better academic performance.     

基于粗糙描述逻辑的不精确时态知识表示研究

在粗糙描述逻辑基础上扩充不精确时态关系,以满足不精确时态知识表示与推理的需要。首先给出了粗糙集及粗糙描述逻辑的相关概念;接着通过定义粗糙时态描述逻辑不精确时态关系,扩展了粗糙描述逻辑中具体域,并给出了可靠性和完备性证明;最后通过实际例子说明粗糙时态描述逻辑的知识表示和应用,结果表明扩展后的粗糙时态描述逻辑可以实现不精确时态知识的表示与推理。     

不确定时态信息表示的统一模型

时态信息表示和推理是人工智能研究中的一个重要课题,现有的模型大多只能表示确定时态信息,然而现实生活中很多事件的发生结束等时态信息都是不确定的。故提出了一个表示不确定时态信息的统一模型,可用于描述各种具有确定或不确定时态信息的事件。该模型首先定义各类时态对象(如时间点、时间区间)以及它们之间的关系,并给出时态对象间的传递关系表,利用该表能进行时态一致性约束满足问题的求解。最后,给出了两个不确定时态推理的例子,表明了该模型的实际应用意义。     

时空相关性融合表征的知识追踪模型

知识追踪通过对知识点的表示来描述习题,以此建模知识状态,最终预测学习者的未来表现。然而目前的研究在知识点的表示方面既没有建模历史知识点对当前知识点产生的时间关系上的影响,又未能刻画习题内部各知识点之间产生的空间关系上的作用。为了解决上述问题,提出了时空相关性融合表征的知识追踪模型。首先,以知识点之间的时间相关程度为基础,建模历史知识点对当前知识点的时间作用;其次,利用图注意力网络建模习题所包含的若干知识点之间的空间作用,得到蕴涵了时空信息的知识点表示;最后,利用上述知识点的表示推导出习题的表示,通过自注意力机制得到当前的知识状态。在实验阶段,与五种相关知识追踪模型在四个真实数据集上进行性能对比,结果表明提出的模型在性能方面有更出色的表现。特别地,在ASSISTments2017数据集中所提模型比五个对比模型在AUC、Acc方面分别提升了1.7%~7.7%和7.3%~2.1%;消融实验证明了建模知识点之间时空相关影响的有效性,训练过程实验表明了提出的模型在知识点的表示及其相互作用关系的建模等方面具有一定的优势,应用实例也可看出该模型优于其他知识追踪模型的实际结果。     

航空制造知识图谱构建研究综述

目前航空装备制造企业的设计、制造相关流程中积累了大量数据,基于知识图谱技术可以对这些数据进行有效融合与管理,对不断更新的制造知识进行挖掘,将为航空制造企业智慧化升级提供有力的知识支撑。为探明知识图谱在航空制造领域的理论支撑体系与实际应用情况,通过文献调研分析航空制造知识图谱架构、定义及特点;阐明知识图谱领域构建过程中的核心技术并进行研究综述,对比航空制造知识图谱与通用知识图谱构建技术上的异同,并提出了三个切合实际的航空制造知识图谱应用方向及其解决方案;最后对未来航空制造知识图谱的挑战进行了分析及展望,为后续该领域的研究提供一些思路。     

基于强相关逻辑的不精确应急时态知识表示

在强相关逻辑基础上扩展不精确时态关系,以满足不精确应急时态知识表示与推理的需要。给出了粗糙集及强相关逻辑的相关概念;通过定义不精确时态关系扩展了强相关逻辑,形成了粗糙时态强相关逻辑,给出了可靠性和完备性证明;通过实际例子说明粗糙时态强相关逻辑的知识表示和应用。结果表明扩展后的粗糙时态强相关逻辑可以实现不精确时态知识的表示与推理。     

Representing reified relations in Loom

Abstract

This paper discusses the semantics and usage of reification as applied to relations and tuples. The reification of a tuple is a proposition object possessing a case role for each domain attribute in the tuple. The reification of a set of fillers of a role is an object sometimes referred to as a ‘roleset’. In the course of defining reification mechanisms for the Loom knowledge representation system, we have unearthed several open issues that come into focus when considering equivalence relations between these kinds of reified objects. Another type of reification produces an individual that represents a view of another individual filling a particular role. We present a number of semantic variations of this reification operation, and argue that the unbridled application of such reification operators has the potential to overwhelm the representation mechanism. We suggest that a regimen that merges various similar but non-equivalent classes of individuals might be preferable to a system that insists on unique representations for each possible abstraction of an individual.     

引入知识表示的图卷积网络谣言检测方法

在谣言检测的问题上,现有的研究方法无法有效地表达谣言在社交网络传播的异构图结构特征,并且没有引入外部知识作为内容核实的手段。因此,提出了引入知识表示的图卷积网络谣言检测方法,其中知识图谱作为额外先验知识来帮助核实内容真实性。采用预训练好的词嵌入模型和知识图谱嵌入模型获取文本表示后,融合图卷积网络的同时,能够在谣言传播的拓扑图中更好地进行特征提取以提升谣言检测的精确率。实验结果表明,该模型能够更好地对社交网络中的谣言进行检测。与基准模型的对比中,在Weibo数据集上的精确率达到96.1%,在Twitter15和Twitter16数据集上的F1值分别提升了3.1%和3.3%。消融实验也表明了该方法对谣言检测皆有明显提升效果,同时验证了模型的有效性和先进性。     

数据驱动的产品概念设计知识服务模型构建

为了满足消费者的个性化需求,提高产品概念创新设计阶段的设计效率和水平,同时提升设计阶段的创新能力,构建了数据驱动的产品概念设计创新知识服务模型。该模型基于产品的评论数据和专利数据等,运用文本挖掘和聚类分析等技术,向产品的设计者提供相应的知识服务,进而对设计过程提供相应的辅助支撑。最后,用实例验证了该模型的有效性。     

基于知识表示学习的KBQA答案推理重排序算法

现有的知识库问答（KBQA）研究通常依赖于完善的知识库,忽视了实际应用中知识图谱稀疏性这一关键问题。为了弥补该不足,引入了知识表示学习方法,将知识库转换为低维向量,有效摆脱了传统模型中对子图搜索空间的依赖,并实现了对隐式关系的推理,这是以往研究所未涉及到的。其次,针对传统KBQA在信息检索中常见的问句语义理解错误对下游问答推理的错误传播,引入了一种基于知识表示学习的答案推理重排序机制。该机制使用伪孪生网络分别对知识三元组和问句进行表征,并融合上游任务核心实体关注度评估阶段的特征,以实现对答案推理结果三元组的有效重排序。最后,为了验证所提算法的有效性,在中国移动RPA知识图谱问答系统与英文开源数据集下分别进行了对比实验。实验结果显示,相比现有的同类模型,该算法在hits@n、准确率、F1值等多个关键评估指标上均表现更佳,证明了基于知识表示学习的KBQA答案推理重排序算法在处理稀疏知识图谱的隐式关系推理和KBQA答案推理方面的优越性。     

基于知识图的领域本体构建方法

提出了一种基于知识图的领域本体半自动构建方法。以《知网》为语义知识资源,知识图为语义表示方法,采用成熟的软件工程流程,最终构建出的领域本体具有结构明确、语义清晰的特点。对于在其上的语义网、信息抽取等应用提供了有效支持。介绍了本体的概念、设计的准则、建模的流程,并对未来的本体的移植性进行展望。实验结果表明该方法在不确定性知识处理上优于传统本体构建方法。     

应急决策中基于时态知识的不确定性推理研究

针对应急决策中的不确定性,在传统区间代数方法的基础上,采用对区间时间断点模糊化处理并设定其取值范围的方法实现了应急领域不确定时态知识的表达,在此基础上,研究时态推理中的证据合成,通过时间区间集合,时态关系集合以及概率指派函数合成后的更新,给出了解决方案,结合应用算例进行分析。验证了该方法的有效性。     

个性化知识的表示方法

在当前信息暴涨的时代,网络信息正在面临着各取所需的要求,信息检索、话题检测、信息推荐等应用技术都逐渐开始面向个性化的发展趋势。然而目前的个性化技术大都依赖于对用户行为的了解,根据用户的历史行为,判断和预测用户的目的,没有同用户的当前所具有的知识结合起来。提出一种用户个性化知识的粗略表示方法--词形关系图,作为个性化应用技术的基础。具体内容包括：词形关系图表示知识的方式,结合遗忘规律从用户语料库中获取个性化词形关联的方法,以及结合实验结果对该表示方法应用可行性的初步分析。     

Representing Software Engineering Knowledge

We argue that one important role that Artificial Intelligence can play in Software Engineering is to act as a source of ideas about representing knowledge that can improve the state-of-the-art in software information management, rather than just building intelligent computer assistants. Among others, such techniques can lead to new approaches for capturing, recording, organizing, and retrieving knowledge about a software system. Moreover, this knowledge can be stored in a software knowledge base, which serves as corporate memory, facilitating the work of developers, maintainers and users alike. We pursue this central theme by focusing on requirements engineering knowledge, illustrating it with ideas originally reported in (Greenspan et al., 1982; Borgida et al., 1993; Yu, 1993) and (Chung, 1993b). The first example concerns the language RML, designed on a foundation of ideas from frame- and logic-based knowledge representation schemes, to offer a novel (at least for its time) formal requirements modeling language. The second contribution adapts solutions of the frame problem originally proposed in the context of AI planning in order to offer a better formulation of the notion of state change caused by an activity, which appears in most formal requirements modeling languages. The final contribution imports ideas from multi-agent planning systems to propose a novel ontology for capturing organizational intentions in requirements modeling. In each case we examine alterations that have been made to knowledge representation ideas in order to adapt them for Software Engineering use.     

时序知识图谱表示与推理的研究进展与趋势

知识图谱作为近年来人工智能领域的一大热点研究方向, 已应用于现实中多个领域. 但是随着知识图谱应用场景日益多样化, 人们逐渐发现不随着时间改变而更新的静态知识图谱不能完全适应知识高频更新的场景. 为此, 研究者们提出时序知识图谱的概念, 一种包含时间信息的知识图谱. 对现有所有时序知识图谱表示与推理模型进行整理, 并归纳和建立一个表示与推理模型理论框架. 然后基于此对当前时序表示推理研究进展进行简要介绍分析和未来趋势预测, 以期望帮助研究者开发设计出更为优异的模型.     

用于知识表示学习的对抗式负样本生成

知识表示学习目的是将知识图谱中符号化表示的关系与实体嵌入到低维连续向量空间。知识表示模型在训练过程中需要大量负样本,但多数知识图谱只以三元组的形式存储正样本。传统知识表示学习方法中通常使用负采样方法,这种方法生成的负样本很容易被模型判别,随着训练的进行对性能提升的贡献也会越来越小。为了解决这个问题,提出了对抗式负样本生成器（ANG）模型。生成器采用编码-解码架构,编码器读入头或尾实体被替换的正样本作为上下文信息,然后解码器利用编码器提供的编码信息为三元组填充被替换的实体,从而构建负样本。训练过程采用已有的知识表示学习模型与生成器进行对抗训练以优化知识表示向量。在链接预测和三元组分类任务上评估了该方法,实验结果表明该方法对已有知识表示学习模型在FB15K237、WN18和WN18RR数据集上的链接预测平均排名与三元组分类准确度都有提升。     

Future Event Prediction Based on Temporal Knowledge Graph Embedding

Accurate prediction of future events brings great benefits and reduces losses for society in many domains, such as civil unrest, pandemics, and crimes. Knowledge graph is a general language for describing and modeling complex systems. Different types of events continually occur, which are often related to historical and concurrent events. In this paper, we formalize the future event prediction as a temporal knowledge graph reasoning problem. Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process. As a result, they cannot effectively reason over temporal knowledge graphs and predict events happening in the future. To address this problem, some recent works learn to infer future events based on historical event-based temporal knowledge graphs. However, these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously. This paper proposes a new graph representation learning model, namely Recurrent Event Graph ATtention Network (RE-GAT), based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently. More specifically, our RE-GAT uses an attention-based historical events embedding module to encode past events, and employs an attention-based concurrent events embedding module to model the associations of events at the same timestamp. A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations. We evaluate our proposed method on four benchmark datasets. Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various baselines, which proves that our method can more accurately predict what events are going to happen.