知识图谱技术在全国取用水平台的应用

全国取用水平台整合是实现取用水业务“一网统管”的重要途径，但因拟整合的取用水业务系统繁多，信息资源分散，平台整合中存在一数多源、标准不统一、户证点关系不清晰等现实问题，由此尝试提出了利用知识图谱技术应用于平台整合过程，建设一套全国统一的数据库表结构标准，形成一套真实且唯一的户证点关系，构建一套智能且有效的监管数据产品。本文采用自顶向下的知识图谱构建方式，根据各系统的结构化数据，构造模式层中的本体及其相互关系，形成对应的概念模型和规则关系，然后依照此模式从数据中抽取实体及关系，进行数据融合，构造数据层，并及时进行知识更新，完成全国取用水平台知识图谱的构建。最后基于统一规范的数据库表结构标准，依据对取用水户取用水行为监管需求，开展时空尺度的数据信息统计分析，构建六类监管产品，形成取用水管控“一张图”。     

An automatic literature knowledge graph and reasoning network modeling framework based on ontology and natural language processing

With the advancement of scientific and engineering research, a huge number of academic literature are accumulated. Manually reviewing the existing literature is the main way to explore embedded knowledge, and the process is quite time-consuming and labor intensive. As the quantity of literature is increasing exponentially, it would be more difficult to cover all aspects of the literature using the traditional manual review approach. To overcome this drawback, bibliometric analysis is used to analyze the current situation and trend of a specific research field. In the bibliometric analysis, only a few key phrases (e.g., authors, publishers, journals, and citations) are usually used as the inputs for analysis. Information other than those phrases is not extracted for analysis, while that neglected information (e.g., abstract) might provide more detailed knowledge in the article. To tackle with this problem, this study proposed an automatic literature knowledge graph and reasoning network modeling framework based on ontology and Natural Language Processing (NLP), to facilitate the efficient knowledge exploration from literature abstract. In this framework, a representation ontology is proposed to characterize the literature abstract data into four knowledge elements (background, objectives, solutions, and findings), and NLP technology is used to extract the ontology instances from the abstract automatically. Based on the representation ontology, a four-space integrated knowledge graph is built using NLP technology. Then, reasoning network is generated according to the reasoning mechanism defined in the proposed ontology model. To validate the proposed framework, a case study is conducted to analyze the literature in the field of construction management. The case study proves that the proposed ontology model can be used to represent the knowledge embedded in the literatures’ abstracts, and the ontology elements can be automatically extracted by NLP models. The proposed framework can be an enhancement for the bibliometric analysis to explore more knowledge from the literature.     

New methods of creating MBD process model: On the basis of machining knowledge

Traditional machining process planning, which passes manufacturing information through 2D drawing, fails to meet the requirement of current 3D manufacturing environment. Thus, model based definition technology, which uses 3D technology to upgrade the current manufacturing capacity, comes into being. This paper focuses on the creation methods of 3D machining process model. In the first place, the relation between machining knowledge and 3D modeling knowledge has been analyzed, establishing machining ontology and modeling ontology. Then, forward creation method and reversed creation method of machining-knowledge-based 3D process model are proposed. In forward creation method, to drive 3D modeling with machining knowledge, process model is created in commercial CAD platform with modeling ontology transferred from machining ontology for knowledge reasoning through the decision tree constructed from training set and test set. Reversed creation method is established by identifying and suppressing the volumetric machining features and surface machining features after building attributed adjacent graph of process model, and the machining knowledge contained in 3D process model is extracted for subsequent reuse. Finally, the validity of this method is verified with the proposed prototype system.     

基于多视角知识图谱嵌入的量刑预测

量刑预测是智慧司法建设的重要组成部分.为了解决量刑预测的可解释性问题,文中将量刑预测任务重新定义为基于知识图谱的链路预测任务,提出多视角的知识图谱嵌入方法,预测案件量刑.首先,文中设计知识图谱本体模式,用于指导案情描述中关键要素的提取.然后,使用图嵌入技术,从案件要素构成的辅助图中学习要素的初始表示.最后,融合知识图谱的结构化特征,对案件要素进行增强表示.以贩卖毒品类案件为研究对象,文中方法在基于知识图谱的量刑预测任务中性能较优,量刑结果有较好的可解释性.     

A knowledge graph-based data representation approach for IIoT-enabled cognitive manufacturing

The Industrial Internet of Things (IIoT) interconnects a large number of interconnected sensors, actuators, and edge computing devices in the manufacturing systems, where the massive data collected in the manufacturing process has the characteristics of multi-dimensional, heterogeneous, and time series. An effective data representation manner, which can fuse such complex information and enable cognitive manufacturing decision-making from a global perspective, is necessary and challenging. To solve this issue, this paper proposes a knowledge graph-based data representation approach for IIoT-enabled cognitive manufacturing and applies it in a Cyber-Physical Production System (CPPS) scenario. Based on the digital thread of manufacturing process data, a multi-layer manufacturing knowledge graph is established, including device sensing data, production processing data, and business processing data. With the established knowledge graph, a cognition-driven approach is proposed with a perception-cognition dual system, which achieves perception analysis and cognition decision-making in the resource allocation of the manufacturing process. Finally, responding to the orders of personalized products in a workshop is taken as an illustrative example. The performance of allocating resources of workshop devices under dynamic demand changes shows the advantages of the proposed approach. The proposed manner will lay the foundation for a human-like cognition for processing massive real-time industrial information in CPPS, thus paving a pathway towards the era of cognitive manufacturing.     

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。     

A knowledge engineering approach to knowledge management

Knowledge management facilitates the capture, storage, and dissemination of knowledge using information technology. Methods for managing knowledge have become an important issue in the past few decades, and the KM community has developed a wide range of technologies and applications for both academic research and practical applications. In this paper, we propose a knowledge engineering approach (KMKE) to knowledge management. First, a knowledge modeling approach is used to organize and express various types of knowledge in a unified knowledge representation. Second, a verification mechanism is used to verify knowledge models based on the formal semantics of the knowledge representation. Third, knowledge models are classified and stored in a hierarchical ontology system. Fourth, a knowledge query language is designed to enhance the dissemination of knowledge. Finally, a knowledge update process is applied to modify the knowledge storage with respect to users’ needs. A knowledge management system for computer repair is used as an illustrative example.     

气象记录档案知识图谱构建

为提升气象档案管理和社会化利用能力,提出了一种气象记录档案知识图谱构建方法.以安徽省馆藏气象记录档案资源为基础,通过自顶向下的方式设计概念层及层次关系来构建本体库,基于本体库对接实体构建知识模型,分别采取D2RQ、图像识别和定制包装器对不同存储格式的档案进行知识抽取构建数据层,通过建立同义词库等来完成知识融合,利用My...     

基于无采样协作知识图网络的推荐系统

知识图谱（KG）可以通过高效组织海量数据实现信息的有效抽取,因而基于知识图谱的推荐方法得到了广泛的研究和应用。针对图神经网络在知识图谱建模中的采样误差问题,提出了一种无采样协作知识图网络（NCKN）的方法。首先,设计了无采样知识传播模块,通过在单个卷积层使用不同大小的线性聚合器来捕捉深层次的信息,实现高效的无采样预计算;然后,为了区分邻居节点贡献度,在传播过程中引入注意力机制;最后,协作传播模块将知识嵌入同用户交互中的协作信号相结合,以更好地描述用户偏好。基于三个真实数据集,评估了NCKN在CTR预测和Top-k预测中的性能。实验结果表明,与主流算法RippleNet、知识图卷积神经网络（KGCN）相比,NCKN在CTR预测中的准确率平均分别提升了2.71%、4.60%;Top-k预测中,NCKN的准确率平均分别提升了5.26%、3.91%。所提方法不仅解决了图神经网络在知识图谱建模中的采样误差问题,且提升了推荐模型的准确率。     

飞机故障知识的本体建模及语义检索

针对目前飞机维修保障工作中故障知识共享应用的实际困难,对飞机故障知识的表达建模以及检索应用进行了研究。依据飞机故障知识的领域特性和共享需求,采用本体作为知识表示的方法。根据本体组成元素分析了飞机故障本体的知识来源,并提出了飞机故障知识的本体工程构建方法。在本体模型的基础上,研究了飞机故障知识的语义检索模型,基于最近相邻检索策略提出了飞机故障本体的语义检索相似匹配算法及其实现流程。开发飞机故障知识管理原型系统并在某航空制造企业进行应用验证。     

Ontology-based enterprise knowledge integration

Enterprises are getting more knowledge intensive, and the integration of various types of knowledge becomes a challenge. It has been accepted that ontology is an important concept for knowledge integration. In this paper, three issues have been addressed: (i) ontology construction which includes the method and implementation of a Concept Map based ontology construction, and the evaluation of the constructed ontology; (ii) a dynamic workflow, in which an ontology-based workflow system is used to accumulate knowledge during the business process, and (iii) the rules and constraints used for knowledge representation, in which a Semantic Web Rule Language (SWRL) is used to group the rules and constraints into different classes executed by a inference engine. Two cases have been studied using the above methods and tools. Case one is an acquisition prototype for the aircraft industry. The other is for an on-going bar code management project carried out by this research team. Both cases show that the developed methods can be used for knowledge integration.     

Towards a sales assistant using a product knowledge graph

The phenomenal growth in the consumer electronics industry over the last decade is mainly due to rapid advances in integration technologies. The market is ever evolving with new products made available on a frequent basis. However, typically, the average consumer tends to have insufficient knowledge of the features and functions of an electronic device. Although most manufacturers provide product specifications, they are often difficult for consumers to understand and it is hard for customers to grasp the details of a product. This study introduces the concept of a product knowledge graph, which is constructed by transforming a set of data from a product management system and external data. This study overcomes the technical barriers for customers with the use of knowledge graph technologies. To construct large-scale product knowledge, an ontology model is designed and a platform for knowledge extraction and transformation is also developed. Then, a sales assistant called God of Sales is demonstrated. This study provides a novel approach to explaining product features and functions in a comprehensive manner with semantic recommendations.     

企业自演化动态本体表示策略的研究

领域知识的非规范化组织严重阻碍了本体及知识库的共享,本体的主观性和知识的快速更新提出了本体演化需求,也就需要对领域知识本体的动态属性进行表示,建立动态本体,适应对本体及知识库共享的需求。本文以情景演算理论为基础,对活动动态本体进行了刻画;在分析企业活动之后构建了企业动态本体,并以构建企业生产管理的动态过程信息表示为例进行了实例描述;提出了本体自演化动态模型;给出了基于本体学习与冲突触发的本体自演化版本态迁移图,对本体演化过程中的版本进行管理,实现动态本体的自动复盘,最终建立实现企业职能的动态的共享本体模型。     

Supporting connectivism in knowledge based engineering with graph theory,filtering techniques and model quality assurance

Mass-customization has forced manufacturing companies to put significant efforts to digitize and automate their engineering and production processes. When new products are to be developed and introduced the production is not alone to be automated. The application of knowledge regarding how the product should be designed and produced based on customer requirements also must be automated. One big academic challenge is helping industry to make sure that the background knowledge of the automated engineering processes still can be understood by its stakeholders throughout the product life cycle.The research presented in this paper aims to build an infrastructure to support a connectivistic view on knowledge in knowledge based engineering. Fundamental concepts in connectivism include network formation and contextualization, which are here addressed by using graph theory together with information filtering techniques and quality assurance of CAD-models. The paper shows how engineering knowledge contained in spreadsheets, knowledge-bases and CAD-models can be penetrated and represented as filtered graphs to support a connectivistic working approach. Three software demonstrators developed to extract filtered graphs are presented and discussed in the paper.     

A new process knowledge representation approach using parameter flow chart

Knowledge in various stages of the product development process has become increasingly important for manufacturing companies to improve their performance, especially for those One-of-a-Kind Production (OKP) companies producing highly customized products. Process knowledge is a very special type of knowledge that controls how products are best manufactured. This knowledge can help OKP companies produce high value-added products with better quality at shorter times and at a competitive cost. Process knowledge is normally hard to capture and manage and is even more difficult to represent. This paper proposes a Parameter Flow Chart (PFC) based new knowledge representation method which efficiently combines parameter information, flow chart technology, and visualization technology. The goal of this research is to provide a user-friendly and effective way of representing process knowledge for OKP companies so they can develop and accumulate their own process knowledge repository. The basic definition and principle of the approach will be introduced first and the software system model then proposed. Two related key issues, the modeling of various chart units used in the PFC approach and dealing with expressions containing various parameters, are discussed in detail. The prototype version of the system has been developed and demonstrated with case studies, which has proven the feasibility of the proposed approach.     

图形化与知识形式企业模型间的相互转换

为有效地支持生产运营的知识共享和协同建模,提出一种在图形化形式与OWL本体形式企业模型间相互转换的方法。建立模型本体,图形化元模型对应于本体中的类,图形化模型元素对应于本体中类的实例。图形化模型元素之间的关联,对应于OWL本体中实例之间的对象属性。建模系统则作为一个建立模型本体实例的工具,将整个图形模型转化为OWL描述的本体实例。反之,通过解析OWL本体形式的模型,建模系统生成相应的图形化模型。     

An end-to-end tabular information-oriented causality event evolutionary knowledge graph for manufacturing documents

Industrial tabular information extraction and its semantic fusion with text (ITIESF) is of great significance in converting and fusing industrial unstructured data into structured knowledge to guide cognitive intelligence analysis in the manufacturing industry. A novel end-to-end ITIESF approach is proposed to integrate tabular information and construct a tabular information-oriented causality event evolutionary knowledge graph (TCEEKG). Specifically, an end-to-end joint learning strategy is presented to mine the semantic information in tables. The definition and modeling method of the intrinsic relationships between tables with their rows and columns in engineering documents are provided to model the tabular information. Due to this, an end-to-end joint entity relationship extraction method for textual and tabular information from engineering documents is proposed to construct text-based knowledge graphs (KG) and tabular information-based causality event evolutionary graphs (CEEG). Then, a novel NSGCN (neighborhoods sample graph convolution network)-based entity alignment is proposed to fuse the cross-knowledge graphs into a unified knowledge base. Furthermore, a translation-based graph structure-driven Q&A (question and answer) approach is designed to respond to cause analysis and problem tracing. Our models can be easily integrated into a prototype system to provide a joint information processing and cognitive analysis. Finally, the approach is evaluated by employing the aerospace machining documents to illustrate that the TCEEKG can considerably help workers strengthen their skills in the cause-and-effect analysis of machining quality issues from a global perspective.     

Interactive and iterative visual exploration of knowledge graphs based on shareable and reusable visual configurations

Knowledge graphs denote structured data which represent entities and relationships between them in a form of a graph, often expressed in the RDF data model. It may be hard for lay users to explore existing knowledge graphs, especially when graphs from different data sources need to be integrated. In this paper, we present an approach to knowledge graph visual exploration based on the concept of shareable and reusable visual configurations. A visual configuration comprises domain specific views on a knowledge graph which define operations such as node detail or expansion. These operations are easy to understand for lay users who can use them to explore a graph while complexities unnecessary in a given application context remain hidden. We introduce an ontology which enables to express and publish visual configurations and reuse their components in other configurations. We also provide an experimental implementation called KGBrowser. We evaluate the proposed approach with real users. We also compare our implementation KGBrowser with other existing tools for knowledge graph visualization and exploration.     

Process-centered knowledge model and enterprise ontology for the development of knowledge management system

Among many enterprise assets, knowledge is treated as a critical driving force for attaining enterprise performance goals. This is because knowledge facilitates the better business decision makings in a timely fashion. However, since knowledge is created and utilized during the execution of business processes, if knowledge is separated from the business process context, it does not lead to the ability to take the right action for target performance.This paper proposes the framework for process-centered knowledge model and enterprise ontology for the context-rich and networked knowledge storage and retrieval required during task execution. The enterprise knowledge object for a process-centered knowledge model is classified into two types: process knowledge and task support knowledge. In the proposed enterprise ontology, which represents major enterprise concepts, and the relationships between them, all domain concepts are related to the “process” concept, both directly and indirectly. As a result, networked and sophisticated knowledge, rather than single-level knowledge, is provided to the participant of unit activity.In order to show the applicability of the proposed framework, a process-centered KMS (knowledge management system) was also developed, which is classified into 3 parts: (1) project management sub-system based on process knowledge. (2) Knowledge management sub-system for maintaining task support knowledge. (3) Infrastructure sub-system which supports the above two sub-systems.     

知识图谱综述——表示、构建、推理与知识超图理论

针对知识图谱（KG）在知识驱动的人工智能研究中发挥的强大支撑作用,分析并总结了现有知识图谱和知识超图技术。首先,从知识图谱的定义与发展历程出发,介绍了知识图谱的分类和架构;其次,对现有的知识表示与存储方式进行了阐述;然后,基于知识图谱的构建流程,分析了各类知识图谱构建技术的研究现状。特别是针对知识图谱中的知识推理这一重要环节,分析了基于逻辑规则、嵌入表示和神经网络的三类典型的知识推理方法。此外,以异构超图引出知识超图的研究进展,并提出三层架构的知识超图,从而更好地表示和提取超关系特征,实现对超关系数据的建模及快速的知识推理。最后,总结了知识图谱和知识超图的典型应用场景并对未来的研究作出了展望。